ACM Multimedia 2019 Sponsors

2/88

Bronze

Sponsors

Gold

Sponsors

Silver

Sponsors

Supporters

  

Table of Contents

Monday 21, Workshops 31

Monday 21, Tutorials 39

Tuesday 22, Program 41

Wednesday 23, Program 59

Thursday 24, Program 74

Friday 25, Workshops 80

Friday 25, Tutorials 85

  3/88

General Chairs’ Welcome Message

We are delighted to welcome you to Nice, France, for ACM Multimedia 2019, the 27th ACM International Conference on Multimedia. ACM Multimedia is the premier international conference in the area of multimedia within the field of computer science. Since 1993, ACM Multimedia has been bringing together researchers and practitioners from academia and industry to present innovative research and discuss recent advancements.

This year’s conference delivers the cutting-edge research results, covering the latest findings in the field, for which the ACM Multimedia conference series is already widely known. In addition, we are offering some key innovations, which we would like to highlight in this welcome message.

We are proud to introduce, for the first time at ACM Multimedia, a Reproducibility Track, whose goal is to incentivize and support researchers in sharing resources that will help others to reproduce their work. The track is dedicated to publishing papers that document the reproducibility of work that has previously appeared at ACM Multimedia, and implements the ACM Artifact Review and Badging system.

Also, for the first time, the conference features a Sisters and Ambassadors session. This session provides a window on what is happening at other conferences of the SIGMM, as well as related conferences in other fields.

It is a special pleasure to host an innovative networking event at the conference, called “Meet the Chairs”. The event will bring together newcomers with established members of the community in a “ConfLab”, which is a natural interaction activity, which simultaneously serves two goals: allowing people to get to know each other and also creating a multimodal data set. The data set will be made available to the community to study multimodal research questions related to human behavior and communication. ConfLab serves as a model for best practices in ethical sourcing of data for multimedia research.

You will quickly notice that this year posters are a centerpiece of the conference. Reading posters and interacting with authors during poster sessions are a highly effective channel of communication of research results and discussion of findings. All conference papers will be presented as posters, which are hanging throughout the conference. We hope that you take advantage of the poster sessions, but also other breaks, to study the posters and to interact directly with the paper authors.

During the oral sessions, selected papers will be presented as 10 minute presentations, followed by a question and answer period. Make good use of this opportunity to ask the authors about their work. Other papers will be presented as two minute “flash” presentations. These presentations will direct the audience to specific posters for further interaction with the authors. There is no status distinction between these presentation modes. Selection of presentation format for accepted papers is based on breadth of interest and topical balance of the program.

Continuing ACM Multimedia’s commitment to building diversity, this year’s conference will feature a special conference-wide diversity event. Maria Menendez-Blanco and Pernille Bjørn of the Department of Computer Science, University of Copenhagen, Denmark, will make a presentation on their experiences in broadening the participation of women in computer science research. They will also offer an interactive installation, which supports discussions about inclusion in computer science, and actively contributes to building new perspectives beyond the narratives that currently dominate in our field.

We are pleased to have a diverse and interesting art exhibition at this year’s conference, please take time to engage with and appreciate the art. We hope that you enjoy the lunch keynote of Jean-Marc Chomaz of the Hydrodynamics Laboratory of CNRS/École Polytechnique, France who will introduce us to his world where art and science intertwine.

This year we are honored to welcome two distinguished morning keynote speakers. The opening keynote will be delivered by Jean Carrive of the National Audiovisual Institute of France (INA). Multimedia is an important part of the culture of a nation, and Carrive’s keynote will discuss how Artificial Intelligence can be used to preserve audiovisual archives, which contain national treasure. The second keynote will be delivered by Mireille Hildebrandt of Free University of Brussels (VUB), Belgium and Radboud University, Netherlands. She will be introducing us to the new European General Data Protection Regulation, which has been receiving international attention, and explaining how this regulation works in support of the reproducibility of scientific research results.

In addition to the main track, the conference has tracks devoted to brave new ideas and to multimedia demos. As always, a particular highlight is the Open Source Software Competition and a Doctoral Symposiums offers the opportunity for young researchers to present and discuss their work with experts.

Acceptance statistics are presented in the following table:

4/88

  

Reviewed Accepted

Main track 936 252

Brave New Ideas 28 4

Demos 48 33

Reproducibility Track 9 4

Open Source Software Competition 10 6

Doctoral Symposium 6 3

The conference offers two panels. One panel has the aim of opening a discussion about “Ethical Challenges in Multimedia Research”. Due to the critical importance of ethics, this panel is a plenary session. The other panel will look forward to the future of the field, deliberating “Challenges for Multimedia/Multimodal Research in the Next Decade”.

No ACM Multimedia would be complete without Grand Challenges. This year we are very happy to offer seven different Grand Challenges. A special effort was made to focus on Challenges that will run for multiple years, allowing the community to build on the successes of past years in order to achieve comprehensive solutions.

On the tutorial and workshop days, eight tutorials provide the opportunity to learn about new directions in multimedia research, and stay up to date on the latest developments. We are also pleased to offer a diverse set of 10 workshops which cover a range of cutting-edge topics important for the field of multimedia.

A conference such as ACM Multimedia is made possible by the expertise, dedication, and hours of hard work of a large number of people. We would like to extend a resounding word of thanks to everyone who contributed. It has been our pleasure to collaborate with this year’s outstanding organizing committee, who have worked to deliver an interesting and impressive program. We would also like to thank everyone who served as area chairs for their work in guaranteeing the novelty and scientific rigor of the main-conference program. A special thanks goes to the reviewers for their work in reviewing submissions across all tracks of the conference. Finally, we would like to thank all the authors who submitted to ACM Multimedia. The heart of the conference is your research discoveries, which is what drives our field forward.

We close by wishing all conference participants a wonderful stay in the Côte d'Azur. This stretch of the Mediterranean coast has historically exerted an irresistible pull on the world, and appeals strongly to the human senses: the stunning visual beauty of the blue sea, the audio-visual magic of the Cannes Film Festival, and the flavor and color as Italian and French traditions collide to create the local cuisine. For the same reason, this area of France also exerts a pull on the ACM MM community, whose focus is content that addresses multiple human senses. Have a good conference, and a wonderful stay in France.

Laurent Amsaleg ACM Multimedia’19 General Co-Chair CNRS-IRISA, France

Benoit Huet ACM Multimedia’19 General Co-Chair EURECOM, France

Martha Larson ACM Multimedia’19 General Co-Chair Radboud University and TU Delft, Netherlands

  5/88

  

Message from the Technical Program Chairs and the Program Coordinator

It is our great pleasure to give you a quick insight on the program of the 27th ACM International Conference on Multimedia, which we hope you will find as exciting as we did when designing it. We would also like to take this opportunity to highlight specific aspects of the paper selection and program construction process that we feel are important to share with you.

We received this year a record-breaking number of 1,275 submissions for the main conference tracks, covering all areas and subareas of multimedia as well as, sometimes, neighbor research topics. The high number of submissions and the diversity of the contributions result in a program of exceptional scientific quality, with an overall acceptance rate of 27%, which we hope covers the wide diversity of the multimedia field, ranging from the system perspective to the user perspective, obviously not forgetting content, which constitutes the multimedia material that unites us all.

The field of multimedia is today more than ever in dire need for a clear definition of its scope at the frontier of computer systems, signal processing, machine learning, databases, computer vision, language and audio processing, virtual reality, human-computer interfaces, and much more. The Technical Program Chairs, in collaboration with the General Chairs and the Program Coordinator, proposed a definition in which a contribution to the multimedia field is “expected to involve more than a single modality, or [...] to be related to the challenge of how people interpret and use multimedia”. This translates into a division of the field in four main themes, each further subdivided into three areas. In alphabetical order, the Engagement theme groups areas related to how users engage with multimedia material: What emotions or social signals are conveyed or induced? How to search and browse efficiently? How can we gain insight from large multimedia collections? The Experience theme focuses on the user experience when engaging with multimedia material: What are interaction and quality of experience? How can we better understand art and cultural material? What applications can be designed and how? The System theme is devoted to the mechanisms and frameworks for building large-scale multimedia applications: How can we improve system components? How can we transport and deliver multimedia content efficiently? What mechanisms for data management and indexing? And finally, the Understanding theme is about machines analyzing and interpreting content with an emphasis on a multimodal perspective: How can we combine multiple modalities? How do vision and language interact? How to process different modalities for a new interpretation?

For each of the 12 areas, a number of Area Chairs were nominated with the goal of steering and monitoring the review process, with Area Chairs acting as meta-reviewers. Secondary Area Chairs were available to provide a second opinion on the reviews and meta reviews of each paper. Area Chairs proposed reviewers, controlled review quality, steered the discussion among reviewers, proposed recommendations and finally made decisions during the final physical Technical Program Committee (TPC) meeting held in Amherst, USA on 16-17 June 2019, co-located this year with the ACM Multimedia Systems conference. The location and timing of the conference was a deliberate attempt to break the recent tradition of holding the meeting at the ACM International Conference on Multimedia Retrieval as a positive signal to support other satellite communities to ACM Multimedia. Nominations of the ACs were done based on a mix of call for volunteers and of invitation to ensure representativeness and diversity. In total, 98 ACs served the TPC and we would like here to heartily thank them for their invaluable contribution in striving for a fair review process.

In total, we received 1,275 submissions from which 26 were withdrawn due to being out of scope after nomination by ACs and unanimous final decision by the TPC chairs. We adhered strictly to the definition of the multimedia field that we adopted in the call and in the reviewer guidelines. We also did significant area re-allocation prior to review to enforce consistency within areas and ensure that similar papers could be easily compared. After manually removing duplicates and papers without a reasonable abstract or title, 936 papers were considered first for the review process. All of the 936 remaining submissions were assigned to at least 3 reviewers under the supervision of an area chair and were given the opportunity of rebuttal to enable review adjustment and discussion among reviewers. The paper review was conducted in a double-blind manner. 37 papers were brought to the attention of the author’s advocate, of which 12 papers were judged by the author’s advocate to require amendments to the reviews. On the few occasions that the author’s advocate was invoked, he made sure that all submissions were fairly treated, possibly requesting additional or more elaborated reviews. Last but not least, all papers within an area were compared and discussed during the TPC meeting before final decisions were collegially made by the TPC.

The whole process ran for almost 10 months and mobilized a large part of our community, with a total of 758 reviewers, whose names are listed in the proceedings, in addition to the 98 area chairs. We take this opportunity to thank them all for their commitment to the community and for their constructive comments.

  6/88

  

The program highlights the final selection of best paper candidates. A long list of initial candidates was proposed by the area chairs on a per area basis and cross-checked against nominations made by reviewers. The final selection was made jointly by the TPC chairs, program coordinator and GCs to highlight excellent examples of multimedia research according to our conference scoping guidelines.

As a conclusion, we would like to open the debate on the definition of the perimeter of our multimedia community. We obviously do not claim that the definition and area division that we adopted this year are perfect: Both can certainly be improved and adjusted before we reach a consensus among the community. We were encouraged, however, that those who did express confusion were satisfied after discussion and further elaboration of the scope of the conference. We are therefore very positive about the step this takes towards establishing clearer boundaries for the community in order to improve cohesion and also unique innovations. The fact that we had to re-allocate a fair number of submissions to different areas clearly shows that we haven’t reached the consensus yet. Neither have we achieved a clear delimitation and definition of the areas that constitute our field of research. Reaching this consensus is probably a difficult path, with its load of frustrations. But we also firmly believe that it is more than ever necessary to walk down that path today and hope that the work achieved for ACM Multimedia 2019, together with an in-depth analysis of the submissions and final contributions, is a first step in the right direction.

Guillaume Gravier ACM Multimedia’19 Technical Program Chair CNRS-IRISA, France

Hayley Hung ACM Multimedia’19 Technical Program Chair Delft University of Technology, Netherlands

Chong-Wah Ngo ACM Multimedia’19 Technical Program Chair City University of Hong Kong, Hong Kong

Wei-Tsang Ooi ACM Multimedia’19 Technical Program Chair National University of Singapore, Singapore

Tat-Seng Chua ACM Multimedia’19 Program Coordinator National University of Singapore, Singapore

  7/88

  

Organizing Committee

General Chairs: Laurent Amsaleg, CNRS-IRISA (France) Benoit Huet, EURECOM (France) Martha Larson, Radboud University Nijmegen (The Netherlands)

Program coordination: Tat-Seng Chua, National University of Singapore (Singapore)

Technical Program Chairs:

Guillaume Gravier, CNRS-IRISA (France) Hayley Hung, Delft University of Technology (Netherlands) Chong-Wah Ngo, City University of Hong Kong (Hong Kong) Wei Tsang Ooi, National University of Singapore (Singapore)

Author’s Advocate: Alan Hanjalic, Delft University of Technology (The Netherlands)

Brave New Ideas: Yiannis Kompatsiaris, CERTH (Greece) Grace Ngai, Hong Kong Polytechnic University (Hong Kong)

Grand Challenge:

Tao Mei, JD.com (China) Vivek Singh, Rutgers University (USA)

Tutorial Chairs:

Giulia Boato, University of Trento (Italy) Ichiro Ide, Nagoya University (Japan)

Panels Chairs:

Alberto Del Bimbo, University of Florence (Italy) Yu-Gang Jiang, Fudan University (China)

Workshop Chairs:

Yannis Avrithis, Inria (France) Daniel Gatica-Perez, Idiap (Switzerland)

Sponsorship Chairs:

Cathal Gurrin, Dublin City University (Ireland) Frédéric Jurie, GREYC (France) Qi Tian, Huawei/UTSA (China)

Demo and Video Program Chair:

Qiong Liu, FXPAL (USA) Bart Thomee, YouTube (USA)

Doctoral Symposium:

Hervé Bredin, LIMSI (France) Suzanne Little, Dublin City University (Ireland)

Open Source:

Stéphane Marchand-Maillet, University of Geneva (Switzerland) Klaus Schoeffmann, Klagenfurt University (Austria)

Art Chairs: Maurice Benayoun, City University of Hong Kong (Hong Kong) Nathalie Delprat, LIMSI (France)

Reproducibility chairs: Laurent Amsaleg, CNRS-IRISA (France) Björn Þór Jónsson, IT University of Copenhagen (Denmark)

Publicity Chairs: Bogdan Ionescu, Politehnica University of Bucharest (Romania) Herman Engelbrecht, Stellenbosch University (South Africa) Jinhui Tang, Nanjing University of Science and Technology (China) Yi Fang, NYU (USA) Silvio J. Guimarães, PUC Minas (Brazil) John Smith, IBM TJ Watson (USA) Lexing Xie, Australian National University (Australia) Rajiv Ratn Shah, IIIT-Delhi (India)

Web and Social Media Chairs: Danny Francis, EURECOM (France) Dian Tjondronegoro, Queensland University of Technology (Australia)

  8/88

  

Publication Chairs: Pradeep K. Atrey, State University of New York at Albany (USA) Wen-Huang Cheng, National Chiao Tung University (Taiwan)

Program Design: Lizi Liao, National University of Singapore (Singapore)

Student Travel Grant Chairs: Chiou-Ting Candy Hsu, National Tsing Hua University (Taiwan) Georges Quénot, LIG-CNRS (France) Alex Hauptmann, Carnegie Mellon University (USA)

  9/88

Area Chairs Theme: Engaging users with multimedia

Emotional and social signals:

Oya Celiktutan, King's College London (United Kingdom) Bruno Lepri, FBK-Irst (Italy) Fabien Ringeval, Université Grenoble Alpes (France) Albert Ali Salah, Utrecht University (Netherlands) Karan Sikka, SRI International (United States) Subhabrata Bhattacharya, Netflix (United States)

Multimedia search and

recommendation:

Werner Bailer, JOANNEUM RESEARCH (Austria) Zhineng Chen, Institute of Automation, Chinese Academy of Sciences (China) Phoebe Chen, La Trobe University (Australia) Cathal Gurrin, Dublin City University (Ireland) Xiangnan He, University of Science and Technology of China (China) Qingming Huang, University of the Chinese Academy of Sciences (China) An-An Liu, Tianjin University (China) Yadong Mu, Peking University (China) Markus Schedl, Johannes Kepler University Linz (Austria) Jialie Shen, Queen's University, Belfast (United Kingdom) Changsheng Xu, Institute of Automation, Chinese Academy of Sciences (China)

Summarization, analytics, and

storytelling:

Richang Hong, Hefei University of Technology (China) João Magalhaes, Universidade NOVA de Lisboa (Portugal) Benjamin Renoust, Osaka University (Japan) Klaus Schöffmann, Klagenfurt University (Austria)

Theme: Multimedia experience Interactions and

Quality of Experience:

Axel Carlier, University of Toulouse (France) Tingting Jiang, Peking University (China) Mario Montagud, i2CAT Foundation & University of Valencia (Spain) Niall Murray, Athlone Institute of Technology (Ireland) Christian Timmerer, Klagenfurt University and Bitmovin (Austria)

Art and culture: Teresa Chambel, Universidade de Lisboa (Portugal) Jia Jia, Tsinghua University (China) Lorenzo Seidenari, University of Florence (Italy) James Z. Wang, The Pennsylvania State University (United States)

Multimedia applications:

Mohammad Akbari, University College London (United Kingdom) Anand Bhojan, National University of Singapore (Singapore) Minh-son Dao, National Institute of Information and Communications Technology (Japan) Jiashi Feng, National University of Singapore (Singapore) Ichiro Ide, Nagoya University (Japan) Fons Kuijk, Centrum Wiskunde & Informatica (Netherlands) Jong-Seok Lee, Yonsei University (South Korea) Balakrishnan Prabhakaran, The University of Texas at Dallas (United States) Michael Riegler, Simula Research Laboratory (Norway) Ramanathan Subramanian, Institute of High Performance Computing (Singapore) Roger Zimmermann, National University of Singapore (Singapore)

Theme: Multimedia systemsSystems and middleware:

Yao Liu, SUNY Binghamton (United States) Shervin Shirmohammadi, University of Ottawa (Canada) Gwendal Simon, IMT Atlantique (France) Zhisheng Yan, Georgia State University (United States)

Transport and delivery:

Ali C. Begen, Ozyegin University and Networked Media (Turkey) Yong Cui, Tsinghua University (China)

10/88

  

Carsten Griwodz, University of Oslo (Norway) Yuansong Qiao, Athlone Institute of Technology (Ireland)

Data systems management

and indexing:

Qinzhong Liu, Sam Houston State University (United States) Vincent Oria, New Jersey Institute of Technology (United States) Guo-jun Qi, University of Central Florida (United States)

Theme: Understanding multimedia content Multimodal fusion

and embedding: Xavier Alameda-Pineda, Inria (France) Chen Chen, University of North Carolina at Charlotte (United States) Cheng Jin, Fudan University (China) Shuqiang Jiang, Institute of Computing Technology, Chinese Academy of Sciences (China) Akisato Kimura, The Nippon Telegraph and Telephone Corporation (NTT) (Japan) Wu Liu, JD AI Research (China) Liqiang Nie, Shandong University (China) Shuhui Wang, Institute of Computing Technology, Chinese Academy of Sciences (China) Tianzhu Zhang, University of Science and Technology of China (China)

Vision and language:

Piotr Bilinski, University of Warsaw (Poland) Xiaojun Chang, Monash University (Australia) Ralph Ewerth, TIB - Leibniz Information Centre for Science and Technology (Germany) Lu Jiang, Google Research (United States) Xirong Li, Renmin University of China (China) Xueliang Liu, Hefei University of Technology (China) Vasileios Mezaris, Information Technologies Institute / Centre for Research and Technology Hellas (Greece) Elisa Ricci, University of Trento (Italy) Jitao Sang, Beijing Jiaotong University (China) Cees Snoek, University of Amsterdam (Netherlands) Jinhui Tang, Nanjing University of Science and Technology (China)

Media interpretation:

Lamberto Ballan, University of Padova (Italy) Bingkun Bao, Nanjing University of Posts and Telecommunications (China) Wen-Huang Cheng, National Chiao Tung University (Taiwan) Zhiyong Cheng, Shandong Artificial Intelligence Institute (China) Wei-Ta Chu, National Cheng Kung University (Taiwan) Yuchao Dai, Northwestern Polytechnical University (China) Lingyu uan, Peking University (China) Chuang Gan, MIT-Watson Lab (United States) Xavier Giro-i-Nieto, Universitat Politècnica de Catalunya (Catalonia) Junhui Hou, City University of Hong Kong (Hong Kong SAR) Di Huang, Beihang University (China) Bogdan Ionescu, University “Politehnica” of Bucharest (Romania) Rongrong Ji, Xiamen University (China) Yu-Gang Jiang, Fudan University (China) Ewa Kijak, Université de Rennes 1 / IRISA (France) Yu Kong, Rochester Institute of Technology (United States) Xianglong Liu, Beihang University (China) Xiaobai Liu, San Diego State University (United States) Tao Mei, JD AI Research (China) Florian Metze, Carnegie Mellon University (United States) Yuxin Peng, Peking University (China) Shin'ichi Satoh, National Institute of Informatics (Japan) Jelena Tesic, Texas State University (United States) Marcel Worring, University of Amsterdam (Netherlands) Xiao Wu, Southwest Jiaotong University (China) Zheng-Jun Zha, University of Science and Technology of China (China)

  11/88

  

ACM Multimedia 2019 Technical Program Committee  

Dirk Ahlers, Norwegian University of Science & Technology (Norway) Kiyoharu Aizawa, The University of Tokyo (Japan) Kevin Almeroth, University of California, Santa Barbara

(USA) Pedro A. Amado Assuncao, Politecnico de Leiria (Portugal) Giuseppe Amato, ISTI-CNR (Italy) Noorul Amin, La Trobe University (Australia) Davide Andrea Mauro, Marshall University (USA) Grenville Armitage, Netflix (Australia) Pradeep K. Atrey, State University of New York at Albany

(USA) Martin Aumüller, IT University of Copenhagen (Denmark) George Awad, Georgetown University; NIST (USA) Roberto Azevedo, Ecole Polytechnique Fédérale de

Lausanne (Switzerland) Claudio Baecchi, University of Florence (Italy) Dragana Bajovic, University of Novi Sad, Serbia (Serbia) Reshmashree Bangalore Kantharaju, Sorbonne Université

(France) Qian Bao, JD AI Research (China) Wentao Bao, Rochester Institute of Technology (USA) Lorenzo Baraldi, University of Modena and Reggio Emilia

(Italy) Kai Uwe Barthel, HTW - University of Applied Sciences

Berlin (Germany) Ilaria Bartolini, University of Bologna (Italy) Christine Bauer, Johannes Kepler University Linz (Austria) Vasileios Belagiannis, Ulm University (Germany) Olivier Belanger, Université de Montréal (Canada) Jessica Beltran, Consejo Nacional de Ciencia y Tecnología

(Mexico) Olfa Ben Ahmed, University of Poitiers (France) Boulbaba Ben Amor, Inception Institute of Artificial

Intelligence (United Arab Emirates) Jenny Benois-Pineau, University of Bordeaux (France) Abdelhak Bentaleb, National University of Singapore

(Singapore) Raffaella Bernardi, DISI and CIMeC, University of Trento

(Italy) Mark Bernstein, Eastgate Systems, Inc (USA) Cigdem Beyan, Istituto Italiano di Tecnologia (Italy) Chidansh Bhatt, FXPAL (USA) Thibault Blanc-Beyne, IRIT - University of Toulouse (France) Rune J. Borgli, Simula (Norway) Fernando Boronat, Universitat Politècnica de València

(Spain) Damian Borth, University of St. Gallen (Switzerland) Khaled Boussetta, University Paris 13 (France) Annelies Braffort, CNRS, LIMSI (France) Hervé Bredin, CNRS, LIMSI (France) Federica Bressan, Ghent University (Belgium) Alexia Briassouli, Maastricht University (Netherlands) Pierrick Bruneau, Luxembourg Institute of Science &

Technology (Luxembourg) Alessio Brutti, Fondazione Bruno Kessler (Italy) Juan Carlos Guerri, Universitat Politècnica de València

(Spain)

Laura Cabrera-Quirós, Delft University of Technology (Netherlands)

Ying Cai, Iowa State University (USA) Jianfei Cai, Nanyang Technological University (Singapore) Junjie Cai, SAIC Innovation Center (USA) Wei Cai, The Chinese University of Hong Kong, Shenzhen

(China) Juan Cao, Institute of Computing Technology, Chinese

Academy of Sciences (China) Yang Cao, University of Science & Technology of China

(China) Niklas Carlsson, Linkoping University (Sweden) Fabio Carrara, ISTI CNR (Italy) Scott Carter, FX Palo Alto Laboratory, Inc. (USA) Leocadio G. Casado, University of Almeria (Spain) Marc Cavazza, University of Greenwich (UK) Fabio Celli, R&D Maggioli Group (Italy) Pablo Cesar, CWI: Centrum Wiskunde & Informatica

(Netherlands) Alberto Cetoli, Context Scout (UK) Sharath Chandra Guntuku, University of Pennsylvania

(USA) Krishna Chandramouli, Venaka Media Limited (UK) Guillaume Chanel, University of Geneva (Switzerland) Elisavet Chatzilari, Information Technologies Institute

(Greece) Edgar Chavez, CICESE (Mexico) Cunjian Chen, Michigan State University (USA) Da Chen, Qilu University of Technology (Shandong

Academy of Sciences), (China) Haoming Chen, Google (USA) Jiasi Chen, University of California, Riverside (USA) Jie Chen, Nanyang Technological University (Singapore) Jingjing Chen, Fudan University (China) Junwen Chen, Rochester Institute of Technology (USA) Laura Chen, University of Toronto (Canada) Peihao Chen, South China University of Technology (China) Phoebe Chen, La Trobe University (Australia) Pin-Yu Chen, IBM Research (USA) Shaoxiang Chen, Fudan University (China) Songqing Chen, George Mason University (USA) Tao Chen, Columbia University, NYC (USA) Xinlei Chen, Facebook (USA) Xuejin Chen, University of Science & Technology of China

(China) Yan Chen, University of Science & Technology of China

(China) Zhibo Chen, University of Science & Technology China

(China) Zhixiang Chen, Imperial College London (UK) Jin Cheng, Fudan University (China) Wen-Huang Cheng, National Chiao Tung University

(Taiwan) Zhi-Qi Cheng, Southwest Jiaotong University (China) Aladine Chetouani, PRISME, University of Orleans (France) Ngai-Man Cheung, Singapore University of Technology and

Design (Singapore) Chen-Kuo Chiang, National Chung Cheng University

(Taiwan)

  12/88

  

Luca Chiarandini, Google (USA) Patrick Chiu, FXPAL (USA) Jaeyoung Choi, TU Delft (Netherlands) / ICSI (USA) Biswarup Choudhury, Imagination Technologies (UK) Niluthpol Chowdhury Mithun, SRI International (USA) Marc Christie, Inria (France) Chenhui Chu, Osaka University (Japan) Lingyang Chu, Huawei Technologies Canada, Co., Ltd.

(Canada) Wei-Ta Chu, National Cheng Kung University (Taiwan) Tat-Seng Chua, National University of Singapore

(Singapore) Yung-Yu Chuang, National Taiwan University (Taiwan) Christopher Clarke, Lancaster University (UK) Mark Claypool, Worcester Polytechnic Institute (USA) Cesar A. Collazos, Universidad del Cauca (Colombia) Nicola Conci, University of Trento (Italy) Mihai Gabriel Constantin, University Politehnica of

Bucharest (Romania) Marcella Cornia, University of Modena and Reggio Emilia

(Italy) Nuno Correia, Universidade NOVA de Lisboa (Portugal) Pasquale Coscia, University of Padova (Italy) Rémi Cozot, Université de Rennes 1 (France) Carlos Fernando Crispim-Junior, LIRIS - Université Lumière

Lyon 2 (France) Michel Crucianu, CNAM (France) Chaoran Cui, Shandong University of Finance and

Economics (China) Peng Cui, Tsinghua University (China) Yong Cui, Tsinghua University (China) Nicholas Cummins, University of Augsburg (Germany) Rui Dai, University of Cincinnati (USA) Teney Damien, The University of Adelaide (Australia) Ritendra Datta, Google (USA) Maaike H.T. de Boer, TNO (Netherlands) Giorgio De Michelis, University of Milano - Bicocca (Italy) Katrien De Moor, Norwegian University of Science &

Technology (Norway) Marco De Nadai, Fondazione Bruno Kessler (Italy) Giovanni De Poli, University of Padova (Italy) Francesca De Simone, CWI: Centrum Wiskunde &

Informatica (Netherlands) Arjen P. de Vries, Radboud University (Netherlands) Daisuke Deguchi, Nagoya University (Japan) Alberto Del Bimbo, University of Firenze (Italy) Yashar Deldjoo, Polytechnic University of Bari (Italy) Claire-Hélène Demarty, InterDigital (France) Laurent Denoue, FXPAL (USA) Abhinav Dhall, Monash University (Australia) Mariella Dimiccoli,Institut de Robòtica i Informàtica

(CSIC-UPC) (Spain) Guiguang Ding, Tsinghua University (China) Mihai Dogariu, University Politehnica of Bucharest

(Romania) Keisuke Doman, Chukyo University (Japan) Jianfeng Dong, Zhejiang GongShang University (China) Weisheng Dong, Xidian University (China) Hassen Drira, IMT Lille Douai (France)

Lingyu Duan, Peking University (China) Xuguang Duan, Tsinghua University (China) Amanda Duarte, Universitat Politecnica de Catalunya

(Spain) Pinar Duygulu, Hacettepe University (Turkey) Touradj Ebrahimi, Ecole Polytechnique Fédérale de

Lausanne (EPFL) (Switzerland) Hazim Kemal Ekenel, Istanbul Technical University (Turkey) Mohammed El Hassouni, Mohammed V University in Rabat

(Morocco) Magda El Zarki, University of California, Irvine (USA) Herman Engelbrecht, University of Stellenbosch (South

Africa) Fabrizio Falchi, ISTI-CNR (Italy) Mingming Fan, University of Toronto (Canada) Chengfang Fang, Huawei International (Singapore) Mylene Farias, University of Brasilia (Brazil) Fuli Feng, National University of Singapore (Singapore) Jie Feng, Amazon (USA) Wenxin Feng, Google (USA) Wu-chi Feng, Portland State University (USA) Antonio Fernández-Caballero, Universidad de Castilla-La

Mancha (Spain) Isabelle Ferrané, IRIT - University of Toulouse (France) Markus Fiedler, Blekinge Institute of Technology (Belgium) Michael Filhol, CNRS - LIMSI (France) Manuel J. Fonseca, Universidade de Lisboa (Portugal) Thomas Forgione, University of Toulouse (France) Hajer Fradi, University of Sousse (Tunisia) Bernd Freisleben, University of Marburg (Germany) Jianlong Fu, Microsoft (China) Yujun Fu, The Hong Kong Polytechnic University (Hong

Kong) Xueyang Fu, University of Science & Technology of China

(China) Issei Fujishiro, Keio University (Japan) Antonino Furnari, University of Catania (Italy) Damianos Galanopoulos, Centre For Research &

Technology Hellas (Greece) Philip Galanter, Texas A&M University (USA) Leonardo Galteri, University of Florence, MICC (Italy) Zhe Gan, Microsoft (USA) Tian Gan, Shandong University (China) Vineet Gandhi, International Institute of Information

Technology Hyderabad (India) Jinyang Gao, Alibaba (China) Jiyang Gao, Waymo (USA) Junyu Gao, Chinese Academy of Sciences (China) Lianli Gao, University of Electronic Science & Technology of

China (China) Zan Gao, Tianjin University of Technology (China) Miguel Garcia-Pineda, University of Valencia (Spain) Noa Garcia, Osaka University (Japan) Paul Gay, LumenAI (France) Shiming Ge, Chinese Academy of Sciences (China) Marc Gelgon, University of Nantes (France) Francesco Gelli, National University of Singapore

(Singapore) Gheorghita Ghinea, Brunel University (UK)

  13/88

Ivan Giangreco, University of Basel (Switzerland) Xavier Giro-i-Nieto, Universitat Politècnica de Catalunya

(Catalonia) Nikolaos Gkalelis, Centre for Research and

Technology-Hellas (Greece) Vicente González-Ruiz, University of Almería (Spain) Guillaume Gravier, CNRS - IRISA (France) Xiaoling Gu, Hangzhou Dianzi University (China) Ke Gu, Beijing University of Technology (China) Tanaya Guha, University of Warwick (UK) Yuanfang Guo, Beihang University (China) Xiaoxiao Guo, IBM (USA) Wen Guo, Shandong Technology and Business University

(China) Yuchen Guo, Tsinghua University (China) Cathal Gurrin, Dublin City University (Ireland) Jesœús Gutiérrez, Université de Nantes (France) Pål Halvorsen, SimulaMet (Norway) Abdelwahab Hamam, Florida Polytechnic University (USA) Jungong Han, University of Warwick (UK) Jing Han, University of Augsburg (Germany) Alan Hanjalic, Delft University of Technology (Netherlands) Yanbin Hao, City University of Hong Kong (Hong Kong) David Harwath, Massachusetts Institute of Technology

(USA) Atsushi Hashimoto, OMRON SINIC X Corp. (Japan) Devamanyu Hazarika, National University of Singapore

(Singapore) Gaoqi He, East China Normal University (China) Jun He, Hefei University of Technology (China) Jun-Yan He, Southwest Jiaotong University (China) Mingyi He, Northwestern Polytechnical University (China) Mohamed Hefeeda, Simon Fraser University (Canada) Thorsten Herfet, Saarland Informatics Campus (Germany) Sorin Hermon, The Cyprus Institute (Cyprus) Luis Herranz, Computer Vision Center (Spain) Steven Hicks, SimulaMet (Norway) Shintami Chusnul Hidayati, Academia Sinica, Taipei

(Taiwan) Andrew Hines, University College Dublin (Ireland) Matthias Hirth, Technische Universität Ilmenau (Germany) Keiichiro Hoashi, KDDI Research, Inc. (Japan) Xiaopeng Hong, Xi'an Jiaotong University (China) Frank Hopfgartner, The University of Sheffield (UK) Mohammad Hosseini, University of Illinois at

Urbana-Champaign (USA) Cheng-Hsin Hsu, National Tsing Hua University (Taiwan) Chih-Chung Hsu, National Pingtung University of Science &

Technology (Taiwan) Jun Hu, Hefei University of Technology (China) Junlin Hu, Beijing University of Chemical Technology

(China) Zhenzhen Hu, Hefei University of Technology(China) Min-Chun Hu, National Tsing Hua University (Taiwan) Yupeng Hu, Shandong University (China) Hao Hu, University of Central Florida (USA) Kien Hua, University of Central Florida (USA) Jun Huan, Baidu (USA) Xuping Huang, Tokyo Metropolitan University (Japan)

Jun Huang, Anhui University of Technology (China) Haibin Huang, Megvii Technology (USA) Michael Xuelin Huang, Google (USA) Wei Huang, Nanchang University (China) Chingchun Huang, National Chung Cheng University

(Taiwan) Xiaowen Huang, Institute of Automation, Chinese Academy

of Sciences (China) Lei Huang, Ocean University of China (China) Lei Huang, Inception Institute of Artificial Intelligence (United

Arab Emirates) Xin Huang, Peking University (China) Wenbing Huang, Tsinghua University (China) Xiaohua Huang, University of Oulu (Finland) Pan Hui, HKUST (Hong Kong) & University of Helsinki

(Finland) Kwok-Wai Hung, Shenzhen University (China) Jenq-Neng Hwang, University of Washington (USA) Ichiro Ide, Nagoya University (Japan) Masaaki Iiyama, Kyoto University (Japan) Yoshihisa Ijiri, OMRON (Japan) Katsufumi Inoue, Osaka Prefecture University (Japan) Nakamasa Inoue, Tokyo Institute of Technology (Japan) Razib Iqbal, Missouri State University (USA) Go Irie, NTT (Japan) Ahmet Iscen, Google (France) Masahiko Itoh, Hokkaido Information University (Japan) Takayuki Itoh, Ochanomizu University (Japan) Patricia Ivette Cornelio Martinez, University of Sussex (UK) Alejandro Jaimes, Aicure (USA) Carl James Debono, University of Malta (Malta) Rittwik Jana, AT&T Labs - Research (USA) Lucjan Janowski, AGH University of Science & Technology

(Poland) Debesh Jha, SimulaMet (Norway) Lin Ji, Massachusetts Institute of Technology (USA) Shihao Ji, Georgia State University (USA) Wen Ji, Chinese Academy of Sciences (China) Zhong Ji, Tianjin University (China) Jia Jia, Tsinghua University (China) Yuheng Jia, City University of Hong Kong (Hong Kong) Meng Jian, Beijing University of Technology (China) Dongmei Jiang, Northwestern Polytechnical University

(China) Hongbo Jiang, Hunan University (China) Jianmin Jiang, Shenzhen University (China) Junjun Jiang, Harbin Institute of Technology (China) Lu Jiang, Google Research (USA) Wang Jiang, Google (USA) Wenhao Jiang, Tencent (China) Chen Jin, Fudan University (China) Jing Jin, City University of Hong Kong (Hong Kong) Peiguang Jing, Tianjin University (China) Alexis Joly, Inria (France) Joemon M. Jose, University of Glasgow (UK) Tomoko Kajiyama, Hiroshima City University (Japan) Fotis Kalaganis, Information Technologies Institute (Greece) Mahdi Kalayeh, Netflix (USA) Kyriaki Kalimeri, I.S.I. Foundation (Italy)

14/88

  

Takuhiro Kaneko, NTT (Japan) Zhao Kang, University of Electronic Science & Technology

of China (China) Wenxiong Kang, South China University of Technology

(China) Xiangui Kang, Sun Yat-Sen University (China) Narasimha Karthik Yadati, Delft University of Technology

(Netherlands) Kunio Kashino, NTT (Japan) Marie Katsurai, Doshisha University (Japan) Harish Katti, Indian Institute of Science (India) Yukiko Kawai, Kyoto Sangyo University (Japan) Yasutomo Kawanishi, Nagoya University (Japan) Heysem Kaya, Namik Kemal University (Turkey) John Kender, Columbia University (USA) Lyndon Kennedy, FXPAL (USA) Eng Tat Khoo, National University of Singapore (Singapore) Hung Khoon Tan, Universiti Tunku Abdul Rahman

(Malaysia) Chelhwon Kim, FXPAL (USA) Shirahama Kimiaki, Kindai University (Japan) Ravi Kiran Sarvadevabhatla, International Institute of

Information Technology, Hyderabad (India) Matthias Kirchner, Binghamton University (USA) Suresh Kirthi Kumaraswamy, IRISA/INRIA (France) Günter Klambauer, Johannes Kepler University Linz

(Austria) Sabrina Kletz, Klagenfurt University (Austria) Peter Knees, TU Wien (Austria) Joachim Koehler, Fraunhofer Institute for Intelligent Analysis

and Information Systems IAIS (Germany) Ioannis Kompatsiaris, Centre for Research & Technology

Hellas (Greece) Narayanan C Krishnan, Indian Institute of Technology Ropar

(India) Maja Krivokuća, Inria (France) Lai-Kuan Wong, Multimedia University (Malaysia) Hilde Kuehne, MIT-IBM Watson Lab (USA) Suryansh Kumar, Australian National University (Australia) Jorma Laaksonen, Aalto University (Finland) Xiangyuan Lan, Hong Kong Baptist University (Hong Kong) Zhenzhong Lan, Google (USA) Congyan Lang, Beijing Jiaotong University (China) Duy-Dinh Le, University of Information Technology,

VNU-HCM (Vietnam) Trung-Nghia Le, University of Tokyo (Japan) Stéphane Lathuilière, University of Trento (Italy) Hervé Le Borgne, CEA LIST (France) Patrick Le Callet, Université de Nantes (France) Chi-Chun Lee, National Tsing Hua University (Taiwan) Donghoon Lee, Seoul National University (South Korea) Simon Leglaive, Inria (France) Andreas Leibetseder, Alpen-Adria-Univerisität Klagenfurt

(Austria) Elisabeth Lex, Graz University of Technology (Austria) Baochun Li, University of Toronto (Canada) Bo Li, Inception Institute of Artificial Intelligence (United Arab

Emirates) Bochen Li, University of Rochester (USA)

Chenglong Li, Anhui University (China) Chongyi Li , City University of Hong Kong (Hong Kong) Dingzeyu Li, Adobe Research (USA) Guorong Li, University of Chinese Academy of Sciences

(China) Jia Li, Beihang University (China) Jiannan Li, University of Toronto (Canada) Jun Li, Massachusetts Institute of Technology (USA) Junnan Li, National University of Singapore (Singapore) Kai Li, Megvii Technology (USA) Kai Li, Facebook (USA) Leida Li, Xidian University (China) Liang Li, Chinese Academy of Sciences (China) Ming Li, California State University, Fresno (USA) Ruifan Li, Beijing University of Posts and

Telecommunications (China) Ruoteng Li, National University of Singapore (Singapore) Shuai Li, Beihang University (China) Shuang Li, Beijing Institute of Technology (China) Shuda Li, University of Oxford (UK) Weixin Li, Beihang University (China) Xiangyang Li, Chinese Academy of Sciences (China) Xirong Li, Renmin University (China) Yandong Li, University of Central Florida (USA) Yi Li, PowerInfo Co, Ltd. (China) Zechao Li, Nanjing University of Science & Technology

(China) Zhouhui Lian, Peking University (China) Junwei Liang, Carnegie Mellon University (USA) Wei Liang, Beijing Institute of Technology (China) Robert Likamwa, Arizona State University (USA) Chia-Wen Lin, National Tsing Hua University (Taiwan) Weiyao Lin, Shanghai Jiao Tong University (China) Suzanne Little, Dublin City University (Ireland) Aishan Liu, Beihang University (China) Bei Liu, Microsoft Research Asia (China) Dong Liu, University of Science & Technology of China

(China) Fiona Liu, The Hong Kong Polytechnic University (Hong

Kong) Hantao Liu, Cardiff University (UK) Hongfu Liu, Brandeis University (USA) Hui Liu, City University of Hong Kong (Hong Kong) Jiangchuan Liu, Simon Fraser University (Canada) Jiawei Liu, University of Science & Technology of China

(China) Jiaying Liu, Peking University (China) Jing Liu, NLPR of CASIA (China) Jing Liu, Tianjin University (China) Meng Liu, Shandong University (China) Mengyuan Liu, Nanyang Technological University

(Singapore) Miaomiao Liu, Australian National University (Australia) Si Liu, Beihang University (China) Sijia Liu, MIT-IBM Watson AI Lab, IBM Research (USA) Xianglong Liu, Beihang University (China) Xinchen Liu, JD.com (China) Yan Liu, The Hong Kong Polytechnic University (Hong

Kong)

  15/88

Ye Liu, National University of Singapore (Singapore) Yong Liu, New York University (USA) Yu Liu, Katholieke Universiteit Leuven (Belgium) Yu-Shen Liu, Tsinghua University (China) Zhenguang Liu, Zhejiang Gongshang University (China) Zhijian Liu, Massachusetts Institute of Technology (USA) Zhilei Liu, Tianjin University (China) Jakub Lokoc, Charles University in Prague (Czechia) Xin Lu, Adobe (USA) Yu-Ding Lu, FXPAL (USA) Yung-Hsiang Lu, Purdue University (USA) Guoyu Lu, Rochester Institute of Technology (USA) Jiwen Lu, Tsinghua University (China) Xiangju Lu, iQiyi (China) Xin Luo, Shandong University (China) Wenhan Luo, Tencent AI Lab (China) Minnan Luo, Xi'an Jiaotong University (China) Mihai Lupu, Research Studios Austria (Austria) Mathias Lux, Klagenfurt University (Austria) Yuqing Ma, Beihang University (China) Kede Ma, City University of Hong Kong (Hong Kong) Huadong Ma, Independent Researcher (China) Lin Ma, Tencent AI Lab (China) Shuang Ma, The State University of New York at Buffalo

(USA) Mengmeng Ma, University of Southern California (USA) Xinhong Ma, Institute of Automation, Chinese Academy of

Sciences, China (China) Dwight Makaroff, University of Saskatchewan (Canada) Maurizio Mancini, University College Cork (Ireland) Zhendong Mao, University of Science & Technology of

China (China) Luca Maria Aiello, Nokia Bell Labs (UK) Flavio Martins, Universidade NOVA de Lisboa (Portugal) Yusuke Matsui, The University of Tokyo (Japan) Ketan Mayer-Patel, University of North Carolina (USA) Troy Mcdaniel, Arizona State University (USA) Naimul Mefraz Khan, Ryerson University (Canada) Shuhuan Mei, Beijing PuhuiCorp Science & Technology Ltd.

(China) Shaohui Mei, Northwestern Polytechnical University (China) Hongying Meng, Brunel University London (UK) Pablo Mesejo, University of Granada (Spain) Pascal Mettes, University of Amsterdam (Netherlands) Stuart E. Middleton, University of Southampton (UK) Weiqing Min, Institute of Computing Technology, CAS

(China) Hisashi Miyamori, Kyoto Sangyo University (Japan) Géraldine Morin, IRIT - University of Toulouse (France) Xuanqin Mou, Xi'an Jiaotong University (China) Stavroula Mougiakakou, University of Bern (Switzerland) Andre Mourao, Universidade NOVA de Lisboa (Portugal) Yadong Mu, Peking University (China) Mu Mu, University of Northampton (UK) Liam Murphy, University College Dublin (Ireland) Phivos Mylonas, National Technical University of Athens

(Greece) Frank Nack, University of Amsterdam (Netherlands) Hidehisa Nagano, NTT (Japan)

Katashi Nagao, Nagoya University (Japan) Klara Nahrstedt, University of Illinois at Urbana-Champaign

(USA) Kazuaki Nakamura, Osaka University (Japan) Yukiko Nakano, Seikei University (Japan) Yuta Nakashima, Osaka University (Japan) Ryohei Nakatsu, Kyoto University (Japan) Venkatesh N. Murthy, Siemens Healthineers (USA) Grace Ngai, The Hong Kong Polytechnic University (Hong

Kong) AnhPhan Nguyen, Georgia State University (USA) Duc Tien Dang Nguyen, University of Bergen (Norway) Tam V. Nguyen, University of Dayton (USA) Weizhi Nie, Tianjin University (China) Xiushan Nie, Shandong Jianzhu University (China) Spiros Nikolopoulos, Centre For Research & Technology

Hellas (CERTH) (Greece) Naoko Nitta, Osaka University (Japan) Lyndon Nixon, MODUL Technology GmbH (Austria) Andreas Nürnberger, Otto-von-Guericke University

Magdeburg (Germany) Noel E. O’Connor, Dublin City University (Ireland) Neil O'Hare, Yahoo Research (USA) Ard Oerlemans, Google (USA) Catharine Oertel, Delft University of Technology

(Netherlands) Wei Tsang Ooi, National University of Singapore

(Singapore) Xavier Ouvrard, University of Geneva / CERN (Switzerland) Deepak Padmanabhan, Queen's University Belfast (UK) Yingwei Pan, JD AI Research (China) Lei Pang, Peng Cheng Lab (China) Symeon Papadopoulos, Centre for Research & Technology

Hellas (Greece) Thales Parreira, Universidade NOVA de Lisboa (Portugal) Mitesh Patel, FXPAL (USA) Ioannis Patras, Queen Mary University of London (UK) Marius Pedersen, Norwegian University of Science &

Technology (Norway) Xi Peng, A*STAR (Singapore) Xi Peng, Rutgers University (USA) Xingchao Peng, Boston University (USA) Diego Perino, Telefonica Research (Spain) Renaud Péteri, La Rochelle University (France) Andreas Petlund, Augere Medical (Norway) Stavros Petridis, Imperial College London (UK) Andrea Pilzer, University of Trento (Italy) Bruno Pinaud, Université de Bordeaux (France) Claudio Pinhanez, IBM Research (Brazil) Antonio Pinheiro, University of Beira Interior (Portugal) Siripen Pongpaichet, Mahidol University (Thailand) Ronald Poppe, Utrecht University (Netherlands) Sébastien Poullot, Median Technologies (France) Reza Pourreza, Qualcomm AI Research (USA) Ravi Prakash, The University of Texas at Dallas (USA) Frédéric Precioso, Université Côte d’Azur (France) William Puech, LIRMM, Université Montpellier, CNRS

(France) Yuankai Qi, Harbin Institute of Technology (China)

16/88

  

Buyue Qian, Xi'an Jiaotong University (China) Shengsheng Qian, Institute of Automation, Chinese

Academy of Sciences (China) Yue Qian, City University of Hong Kong (Hong Kong) Mu Qiao, IBM Research (USA) Jie Qin, Inception Institute of Artificial Intelligence (United

Arab Emirates) Jason Quinlan, University College Cork (Ireland) Alexander Raake, Technische Universität Ilmenau

(Germany) Nicholas Race, Lancaster University (UK) Nikunj Raghuvanshi, Microsoft Research (USA) Kiran Raja, Norwegian University of Science & Technology

(Norway) Shiv Ram Dubey, Indian Institute of Information Technology,

Sri City (India) Mehran Ramin, Zillow (USA) Nimesha Ranasinghe, University of Maine (USA) Miriam Redi, Wikimedia Foundation (UK) Christoph Reinders, Leibniz UniversitäŠt Hannover

(Germany) Fengyuan Ren, Tsinghua University (China) Tongwei Ren, Nanjing University (China) Wenqi Ren, Chinese Academy of Sciences (China) Michael Riegler, SimulaMet (Norway) Amr Rizk, Universität Ulm (Germany) Bernardino Romera-Paredes, DeepMind (UK) Hoda Roodaki, K. N. Toosi University of Technology (Iran) Luca Rossetto, University of Zurich (Switzerland) Amit Roy-Chowdhury, University of California Riverside

(USA) Hiranmoy Roy, RCC Institute of Information Technology

(India) Stevan Rudinac, University of Amsterdam (Netherlands) Eric S. Tellez, CONACyT - INFOTEC (Mexico) Mukesh Saini, Indian Institute of Technology Ropar (India) Albert Ali Salah, Utrecht University (Netherlands) Nabil Sarhan, Wayne State University (USA) Evangelos Sariyanidi, Queen Mary, University of London

(UK) Lucile Sassatelli, Université Côte d’Azur (France) Raimund Schatz, AIT Austrian Institute of Technology

(Austria) Rossano Schifanella, University of Turin (Italy) Alexander Schindler, AIT Austrian Institute of Technology

(Austria) Nicu Sebe, University of Trento (Italy) John See, Multimedia University (Malaysia) Jaume Segura Garcia, University of Valencia (Spain) K. Selcuk Candan, Arizona State University (USA) David Semedo, Universidade NOVA de Lisboa (Portugal) Mehdi Semsarzadeh, AMD (Canada) Michael Seufert, University of Würzburg (Germany) Zachary Seymour, SRI International (USA) Rajiv Ratn Shah, International Institute of Information

Technology Delhi (India) An Shan, JingDong (China) Xindi Shang, National University of Singapore (Singapore)

Xi Shao, Nanjing University of Posts and Telecommunications (China)

Ming Shao, University of Massachusetts Dartmouth (USA) Aidean Sharghi, University of Central Florida (USA) Piyush Sharma, Google (USA) Ujjwal Sharma, University of Amsterdam (Netherlands) Guangyao Shen, Tsinghua University (China) Jialie Shen, Queen's University Belfast (UK) Hailin Shi, JD AI Research (China) Miaojing Shi, Inria (France) Shu Shi, AT&T Labs Research (USA) Vivek K. Singh, Rutgers University (USA) Koichi Shinoda, Tokyo Institute of Technology (Japan) Xiangbo Shu, Nanjing University of Science & Technology

(China) Gwendal Simon, IMT Atlantique (France) - Adobe Research

(USA) Yogesh Singh Rawat, University of Central Florida (USA) Pia H. Smedsrud, SimulaMet (Norway) Cees Snoek, University of Amsterdam (Netherlands) Ashkan Sobhani, Huawei Technologies (Canada) Dan Song, Tianjin University (China) Guoli Song, University of Chinese Academy of Sciences

(China) Guoli Song, Chinese Academy of Sciences (China) Jingkuan Song, University of Electronic Science &

Technology of China (China) Shi Song, iQiyi (China) Xinhang Song, Institute of Computing Technology, Chinese

Academy of Sciences (China) Xuemeng Song, National University of Singapore

(Singapore) Concetto Spampinato, University of Catania (Italy) Cormac Sreenan, University College Cork (Ireland) Liviu-Daniel Ștefan, University Politehnica of Bucharest

(Romania) Gjorgji Strezoski, University of Amsterdam (Netherlands) Guan-Ming Su, Dolby Labs (USA) Alvaro Suarez, University of Las Palmas de Gran Canaria

(Spain) Kazunari Sugiyama, Kyoto University (Japan) Shih-Wei Sun, Taipei National University of the Arts

(Taiwan) Lifeng Sun, Tsinghua University (China) Qianru Sun, Singapore Management University (Singapore) Mirko Suznjevic, University of Zagreb (Croatia) Viswanathan Swaminathan, Adobe (USA) Andreas Symeonidis, Aristotle University of Thessaloniki

(Greece) Mingkui Tan, South China University of Technology (China) Masayuki Tanaka, Tokyo Institute of Technology (Japan) Sheng Tang, Chinese Academy of Sciences (China) Jinhui Tang, Nanjing University of Science & Technology

(China) Yukinobu Taniguchi, Tokyo University of Science (Japan) Makarand Tapaswi, Inria (France) Mario Taschwer, Klagenfurt University (Austria) Wallapak Tavanapong, Iowa State University (USA) Yi Tay, Nanyang Technological University (Singapore)

  17/88

  

Ahmet Murat Tekalp, Koç University (Turkey) Mehrdad Teratani, Nagoya University (Japan) Georg Thallinger, JOANNEUM RESEARCH (Austria) Vajira Thambawita, SimulaMet (Norway) Bart Thomee, Google (USA) Yi Tian, Beijing Jiaotong University (China) Yicong Tian, Google LLC (USA) Huawei Tian, Beijing Jiaotong University (China) Christian Timmerer, Klagenfurt University (Austria) Marko Tkalcic, Free University of Bozen-Bolzano (Italy) Mercan Topkara, Luminary Media (USA) Mercedes Torres Torres, University of Nottingham (UK) Ruben Tous, Universitat Politècnica de Catalunya (Spain) Minh-Triet Tran, University of Science, VNU-HCM (Vietnam) Jolanda Tromp, Duy Tan University (Viet Nam) Cong-Thang Truong, University of Aizu (Japan) Tiberio Uricchio, University of Florence (Italy) Marian F. Ursu, University of York (UK) Yoshitaka Ushiku, OMRON SINIC X Corp. (Japan) Hong Va Leong, The Hong Kong Polytechnic University

(Hong Kong) Nanne van Noord, University of Amsterdam (Netherlands) Giovanna Varni, Télécom Paris, Institut polytechnique de

Paris, France (France) Dominique Vaufreydaz, University Grenoble Alpes/Inria/LIG

(France) Padmanabha Venkatagiri Seshadri, IBM Research (India) Gualtiero Volpe, University of Genoa (Italy) Stefanos Vrochidis, Information Technologies Institute,

CERTH (Greece) Ji Wan, Baidu (China) Cheng Wang, NEC Labs Europe (Germany) Chuan Wang, Megvii Technology LLC (USA) Dong Wang, Dalian University of Technology (China) Feng Wang, East China Normal University (China) Haibo Wang, Philips Research (USA) Hanli Wang, Tongji University (China) Haoliang Wang, Adobe Research (USA) Jingwen Wang, Tencent AI Lab (China) Jinqiao Wang, Chinese Academy of Sciences (China) Kai Wang, GIPSA-Lab, CNRS (France) Kai Wang, Nankai University (China) Meng Wang, Hefei University of Technology (China) Nannan Wang, Xidian University (China) Peng Wang, Hulu (China) Qing Wang, Northwestern Polytechnical University (China) Rui Wang, Chinese Academy of Sciences (China) Shiqi Wang, City University of Hong Kong (Hong Kong) Shuhui Wang, Chinese Academy of Sciences (China) Siyue Wang, Northeastern University (USA) Tao Wang, iQiyi (China) Wei Wang, Independent Researcher (American Samoa) Wei Wang, National University of Singapore (Singapore) Xiang Wang, National University of Singapore (Singapore) Xiao Wang, Beijing University of Posts and

Telecommunications (China) Xiaofang Wang, Siradel (France) Yang Wang, Hefei University of Technology (China)

Yu-Chiang Frank Wang, National Taiwan University (Taiwan)

Yu-Shuen Wang, National Chiao Tung University (Taiwan) Zhangyang Wang, Texas A&M University (USA) Zheng Wang, National Institute of Informatics (Japan) Zhi Wang, Tsinghua University (China) Zilei Wang, University of Science & Technology of China

(China) Sheng Wei, University of Nebraska-Lincoln (USA) Shikui Wei, Beijing Jiaotong University (China) Tao Wei, University at Buffalo (USA) Xiao-Yong Wei, Sichuan University (China) Xingxing Wei, Tsinghua University (China) Wei Wei, Northwestern Polytechnical University (China) Yonggang Wen, Nanyang Technological University

(Singapore) Yang Wenhan, City University of Hong Kong (China) Maarten Wijnants, Hasselt University (Belgium) Stefan Winkler, National University of Singapore

(Singapore) Bernard Wong, University of Waterloo (Canada) Hau-San Wong, City University of Hong Kong (Hong Kong) Yongkang Wong, National University of Singapore

(Singapore) Bo Wu, Columbia University (USA) Jinjian Wu, Xidian University (China) Le Wu, Hefei University of Technology (China) Qi Wu, The University of Adelaide (Australia) Song Wu, Southwest University (China) Yiling Wu, Institute of Computing Technology, Chinese

Academy of Sciences (China) Yingcai Wu, Zhejiang University (China) Zuxuan Wu, University of Maryland (USA) Siyu Xia, Southeast University (China) Xide Xia, Boston University (USA) Shiming Xiang, Chinese Academy of Sciences (China) Xiang Xiang, Johns Hopkins University (USA) Mengbai Xiao, The Ohio State University (USA) Junbin Xiao, National University of Singapore (Singapore) Yu Xiao, Aalto University (Finland) Hongtao Xie, University of Science & Technology of China

(China) Wuyuan Xie, Shenzhen University (China) Xiaohui Xie, Hulu (China) Xin Xin, University of Glasgow (UK) Chang Xu, The University of Sydney (Australia) Changqiao Xu, Beijing University of Posts and

Telecommunications (China) Chunxu Xu, Hulu (China) Dan Xu, University of Oxford (UK) Jin Xu, University College Dublin (Ireland) Jun Xu, JD AI Research (China) Min Xu, University of Technology, Sydney (Australia) Ning Xu, Tianjin University (China) Pingmei Xu, Google (USA) Qianqian Xu, Chinese Academy of Sciences (China) Xin-Shun Xu, Shandong University (China) Yuanlu Xu, University of California, Los Angeles (USA) Geng Xue, A*STAR (Singapore)

  18/88

  

Zhe Xue, Beijing University of Posts and Telecommunications (China)

Ryosuke Yamanishi, Ritsumeikan University (Japan) Toshihiko Yamasaki, The University of Tokyo (Japan) Takayoshi Yamashita, Chubu University (Japan) Hanshu Yan, National University of Singapore (Singapore) Jinyao Yan, Communication University of China (China) Junchi Yan, Shanghai Jiao Tong University (China) Keiji Yanai, The University of Electro-Communications,

Tokyo (Japan) Gaobo Yang, Hunan University (China) Huan Yang, Nanyang Technological University (Singapore) Taojiannan Yang, University of North Carolina at Charlotte

(USA) Xiaopeng Yang, Huawei Technologies (Canada) Xiaoshan Yang, Institute of Automation, Chinese Academy

of Sciences (China) Xun Yang, National University of Singapore (Singapore) Yang Yang, University of Science & Technology of China

(China) Yin Yang, University of New Mexico (USA) Hantao Yao, Institute of Automation,Chinese Academy of

Sciences (China) Lina Yao, The University of New South Wales (Australia) Ting Yao, JD AI Research (China) Chengxi Ye, University of Maryland (USA) Jianbo Ye, Amazon (USA) Jun Ye, Microsoft (USA) Yuhang Ye, Athlone Institute of Technology (Ireland) Mei-Chen Yeh, National Taiwan Normal University (Taiwan) Kexin Yi, Harvard University (USA) Zhaozheng Yin, Stony Brook University (USA) Mingyu You, Tongji University (China) Chunfeng Yuan, Institute of Automation Chinese Academy

of Sciences (China) Zhaoquan Yuan, Southwest Jiaotong University (China) Jan Zahálka, bohem.ai (Czech Republic) Eva Zangerle, University of Innsbruck (Austria) Huanqiang Zeng, Huaqiao University (China) Runhao Zeng, South China University of Technology

(China) Matthias Zeppelzauer, University of Applied Sciences St.

Pölten (Austria) Xiaohua Zhai, Google Brain (Switzerland) Kun Zhan, Lanzhou University (China) Baochang Zhang, Beihang University (China) Cheng Zhang, The Ohio State University (USA) Hanwang Zhang, Nanyang Technological University

(Singapore) Hao Zhang, City University of Hong Kong (Hong Kong) Hua Zhang, Chinese Academy of Sciences (China) Jiao Zhang, Beijing University of Posts and

Telecommunications (China) Jing Zhang, Australian National University (Australia) Jing Zhang, University of Technology, Sydney (Australia) Libo Zhang, Institute of Software Chinese Academy of

Sciences (China)

Ning Zhang, JD.com (USA) Peng Zhang, Northwestern Polytechnical University (China) Tianzhu Zhang, University of Science & Technology of

China (China) Tong Zhang, Australian National University (Australia) Wei Zhang, JD AI Research (China) Xiao-Yu Zhang, Chinese Academy of Sciences (China) Xiaodan Zhang, Beijing University of Technology (China) Xinggong Zhang, Peking University (China) Xiuming Zhang, Massachusetts Institute of Technology

(USA) Yang Zhang, University of Central Florida (USA) Yanxia Zhang, FXPAL (USA) Yongfei Zhang, Beihang University (China) Zhao Zhang, Hefei University of Technology (China) Zhebin Zhang, Megvii Research (USA) Zhen Zhang, The University of Adelaide (Australia) Zheng Zhang, Beijing University of Posts and

Telecommunications (China) Zixing Zhang, Imperial College London (UK) Handong Zhao, Adobe Research (USA) Jian Zhao, FXPAL (USA) Ruiwei Zhao, Nanyang Technological University (Singapore) Sicheng Zhao, University of California, Berkeley (USA) Tiesong Zhao, Fuzhou University (China) Wan-Lei Zhao, Xiamen University (China) Zhou Zhao, Zhejiang University (China) Sheng-Hua Zhong, Shen Zhen University (China) Zichun Zhong, Wayne State University (USA) Jiantao Zhou, University of Macau (Macao) Luowei Zhou, University of Michigan (USA) Wengang Zhou, University of Science & Technology of

China (China) Chao Zhu, University of Science & Technology Beijing

(China) Hongyuan Zhu, A*STAR (Singapore) Lei Zhu, Shandong Normal University (China) Pengefei Zhu, Tianjin University (China) Sijie Zhu, University of North Carolina at Charlotte (USA) Xiaobin Zhu, University of Science & Technology Beijing

(China) Yanjun Zhu, University at Buffalo (USA) Yixin Zhu, University of California, Los Angeles (USA) Bingbing Zhuang, National University of Singapore

(Singapore) Naifan Zhuang, University of Central Florida (USA) Tao Zhuo, National University of Singapore (Singapore) Maciej Zieba, Wroclaw University of Science & Technology

(Poland) Thomas Zinner, TU Berlin (Germany) Chuhang Zou, University of Illinois at Urbana-Champaign

(USA)

  19/88

Schedule Overview -- Monday Oct. 21, morning sessions

20/88

Schedule Overview -- Monday Oct. 21, afternoon sessions

21/88

Schedule Overview -- Tuesday Oct. 22, morning sessions

22/88

Schedule Overview -- Tuesday Oct. 22, afternoon sessions

23/88

Schedule Overview -- Wednesday Oct. 23, morning sessions

24/88

Schedule Overview -- Wednesday Oct. 23, afternoon sessions

Conference Banquet: 19:30--22:00. Palais de la Méditerranée

See map at the end of the program

25/88

Schedule Overview -- Thursday Oct. 24, morning sessions

26/88

Schedule Overview -- Thursday Oct. 24, afternoon sessions

27/88

Schedule Overview -- Friday Oct. 25, morning sessions

28/88

Schedule Overview -- Friday Oct. 25, afternoon sessions

29/88

Floor Map

Network Name: ACMMM2019Login & Password: acmmm2019

30/88

  

Workshop 1: AI4TV — AI for Smart TV Content Production, Access and Delivery

Abstract: Technological developments in comprehensive video understanding – detecting and identifying visual elements of a scene, combined with audio understanding (music, speech), as well as aligned with textual information such as captions, subtitles, etc. and background knowledge – have been undergoing a significant revolution during recent years. The workshop brings together experts from academia and industry in order to discuss the latest progress in artificial intelligence research in topics related to multimodal information analysis, and in particular, semantic analysis of video, audio, and textual information for smart digital TV content production, access and delivery.

Organizers:

● Raphaël Troncy, EURECOM ● Jorma Laaksonen, Aalto University ● Hamed R. Tavakoli, Nokia Technologies ● Lyndon Nixon, MODUL Technology ● Vasileios Mezaris, CERTH-ITI

Monday October 21 — Full day workshop — 09:30-17:30 — location Risso 6

09:30 Workshop opening and welcome AI4TV Workshop Chairs 09:40 Keynote talk: Annotation Automation to Support Dynamic Exploration and Creative

Retrieval of Audiovisual Archives Johan Oomen (Netherlands National Institute for Sound and Vision) 10:30 Refreshments (Central Space) 11:00 L-STAP: Learned Spatio-Temporal Adaptive Pooling for Video Captioning Danny Francis (EURECOM) and Benoit Huet (EURECOM) 11:20 A Stepwise, Label-based Approach for Improving the Adversarial Training in Unsupervised

Video Summarization Evlampios Apostolidis (CERTH and QMUL), Alexandros Metsai (CERTH), Eleni Adamantidou

(CERTH), Vasileios Mezaris (CERTH) and Ioannis Patras (QMUL) 11:40 On the Robustness of Deep Learning Based Face Recognition Werner Bailer (JOANNEUM RESEARCH) and Martin Winter (JOANNEUM RESEARCH) 12:00 Gender Representation in French Broadcast Corpora and Its Impact on ASR Performance Mahault Garnerin (Univ. Grenoble Alpes), Solange Rossato (Univ. Grenoble Alpes) and Laurent

Besacier (Univ. Grenoble Alpes) 12:30 Lunch (Central Space) 14:00 Keynote talk: AI Gets Creative Marta Mrak (BBC) 14:50 AI for Audience Prediction and Profiling to Power Innovative TV Content Recommendation

Services Lyndon Nixon (MODUL Technology GmbH), Krzysztof Ciesielski (Genistat AG) and Basil Philipp

(Genistat AG) 15:10 Data-driven Summarization and Synchronized Second-screen Enrichment of Cycling Races Steven Verstockt (Ghent University), Erik Mannens (Ghent University) and Jelle De Bock (Ghent

University) 15:30 Refreshments (Central Space) 16:00 Pitch your demos (2 min each). All demo sessions’ presenters: Examples of Uses of Artificial Intelligence in Video Archives Antoine Mercier (Radio Télévision Suisse), Sébastien Ducret (Radio Télévision Suisse),

Charlotte Bürki (Radio Télévision Suisse) and Léonard Bouchet (Radio Télévision Suisse) Automatically Adapting and Publishing TV Content for Increased Effectiveness and

Efficiency Basil Philipp (Genistat AG), Krzysztof Ciesielski (Genistat AG; and Polish Academy of

  31/88

Sciences) and Lyndon Nixon (MODUL Technology GmbH) Personalized Movie Trailer Using Thumbnail Containers Ghulam Mujtaba (Gachon University) and Eun-Seok Ryu (Gachon University) A Workstation for Real-time Processing of Multi-channel TV Mathieu Delalandre (LIFAT Laboratory)

17:00 Wrap up, Next steps and closing All workshop participants

32/88

  

Workshop 2: AVEC — Audio/Visual Emotion Challenge and Workshop Abstract: The ninth Audio-Visual Emotion Challenge and workshop AVEC 2019 was held in conjunction with ACM Multimedia’19. This year, the AVEC series addressed major novelties with three distinct tasks: State-of-Mind Sub-challenge (SoMS), Detecting Depression with Artificial Intelligence Sub-challenge (DDS), and Cross-cultural Emotion Sub-challenge (CES). The SoMS was based on a novel dataset (USoM corpus) that includes self-reported mood (10-point Likert scale) after the narrative of personal stories (two positive and two negative). The DDS was based on a large extension of the DAICWOZ corpus (c f. AVEC 2016) that includes new recordings of patients suffering from depression with the virtual agent conducting the interview being, this time, wholly driven by AI, i. e., without any human intervention. The CES was based on the SEWA dataset (c. f. AVEC 2018) that has been extended with the inclusion of new participants in order to investigate how emotion knowledge of Western European cultures (German, Hungarian) can be transferred to the Chinese culture. In this summary, we mainly describe participation and conditions of the AVEC Challenge. Organizers:

● Fabien Ringeval, Grenoble Alps University ● Michel F. Valstar, University of Nottingham ● Roddy Cowie, Queen's University Belfast ● Björn W. Schuller, Imperial College London/University of Augsburg ● Nicholas Cummins, University of Augsburg ● Maja Pantic, Imperial College London/University of Twente

Monday October 21 — Full day workshop — 09:00-17:30 — location Risso 7 09:00 Workshop Opening and Welcome Words — AVEC Organizers 09:05 The Socio-Affective Robot: Aimed to Understand Human Links? Véronique Aubergé (Laboratoire d'Informatique de Grenoble, CNRS) 10:05 AVEC 2019 Workshop and Challenge: State-of-Mind, Detecting Depression with AI, and

Cross-Cultural Affect — AVEC Organizers

10:30 Refreshments (Central Space)

11:00 A Multimodal Framework for State of Mind Assessment with Sentiment Pre-classification Yan Li (Northwestern Polytechnical University) 11:20 Efficient Spatial Temporal Convolutional Features for Audiovisual Continuous Affect

Recognition — Haifeng Chen (NorthWestern Polytechnical University) 11:40 Predicting Depression and Emotions in the Cross-roads of Cultures, Para-linguistics, and

Non-linguistics — Albert Ali Salah (Utrecht University) 12:00 Adversarial Domain Adaptation for Multi-Cultural Dimensional Emotion Recognition in

Dyadic Interactions — Shizhe Chen (Renmin University of China) 12:30 Lunch (Central Space) 14:00 Evaluating Acoustic and Linguistic Features of Detecting Depression Sub-Challenge

Dataset Larry Zhang (University of Washington) 14:20 Multimodal Fusion of BERT-CNN and GCNN Representations for Depression Detection Mariana Rodrigues Makiuc (Tokyo Institute of Technology) 14:40 Multi-modality Depression Detection via Multi-scale Temporal Dilated CNNs Weiquan Fan (South China University of Technology) 15:00 A Multi-Modal Hierarchical Recurrent Neural Network for Depression Detection Shangfei Wang (University of Science and Technology of China) 15:20 Multi-level attention network using text, audio and video for Depression Prediction Prerana Mukherjee (Indian Institute of Information Technology) 15:40 Refreshments (Central Space) 16:00 AVEC 2019 Challenge Results — AVEC Organizers

 

33/88

Workshop 3: MADiMa — Multimedia Assisted Dietary Management Abstract: After the success of the past MADiMa workshops, we would like to present you the MADiMa2019 to be held with ACM Multimedia2019 in Nice, France. The main scope of MADiMa2019 is to bring together researchers from the diverse fields of engineering, computer science and nutrition who investigate the use of information and communication technologies for better monitoring, assessment and management of food intake. The combined use of multimedia, artificial intelligence algorithms, ubiquitous computing and mobile technologies permit the development of applications and systems able to monitor the dietary behavior, analyze food intake, identify eating patterns and provide feedback to the user towards healthier nutrition. The researchers will present and demonstrate their latest progress, discuss novel ideas and challenges in the field.

Organizers: ● Stavroula Mougiakakou, University of Bern● Keiji Yanai, The University of Electro-Communications, Tokyo● Giovanni Maria Farinella, University of Catania● Dario Allegra, University of Catania

Monday October 21 — Full day workshop — 09:20-17:30 — location Galliéni 4

09:20 Workshop Opening and Welcome Words MADiMa2019 Workshop organizers

09:30 Keynote 1: Personalized Nutrition in the Connected Era: Challenges and Opportunities Frederic Ronga (Nestlé Research Center, Lausanne)

10:00 Oral 1: Deep Cooking: Predicting Food Ingredient Amounts from Images Jiatong Li (Rutgers University)

10:15 Oral 2: Impact of Mixed Reality Food Labels on Product Selection: Insights from a User Study Using Headset-mediated Food Labels at a Vending Machine Klaus Fuchs (ETH Zurich)

10:30 Refreshments (Central Space)

11:00 Keynote 2: Eat, Drink and be Happy Ramesh Jain (University of California, Irvine and Peng Cheng Lab)

11:30 Keynote 3: Learning User Preferences from Social Multimedia Analysis and Overview of the iFood2019 Challenge Karan Sikka (SRI International)

12:00 Oral 3: Unseen Food Creation by Mixing Existing Food Images with Conditional StyleGAN Daichi Horita (The University of Electro-Communications)

12:15 Oral 4: Self-Attention and Ingredient-Attention Based Model for Recipe Retrieval from Image Queries Matthias Fontanellaz (University of Bern)

12:30 Lunch (Central Space)

14:00 Keynote 4: FoodLog: Multimedia Food Recording Platform and Its Application for Athletes' Nutrition Management Kiyoharu Aizawa (University of Tokyo)

14:30 Oral 5: Convolutional Neural Networks for Food Image Recognition: An Experimental Study Yi Sen Ng (National University of Singapore)

14:45 Oral 6: Categorization of Cooking Actions Based on Visual Similarity Yixin Zhang (Kyoto University)

15:00 Oral 7: Scraping Social Media Photos Posted in Kenya and Elsewhere to Detect and Analyze Food Types Mona Jalal (Boston University)

15:15 Oral 8: Flavour Enhanced Food Recommendation Nitish Nag (University of California, Irvine)

15:30 Refreshments (Central Space)

34/88

  

16:00 MADiMa 2019 Posters and demos

Towards Tailoring Digital Food Labels: Insights of a Smart-RCT on User-specific Interpretation of Food Composition Data

Klaus Fuchs (ETH Zurich)

DepthCalorieCam: A Mobile Application for Volume-Based FoodCalorie Estimation using Depth Cameras

Takumi Ege (The University of Electro-Communications)

A New Large-scale Food Image Segmentation Dataset and Its Application to Food Calorie Estimation Based on Grains of Rice

Takumi Ege (The University of Electro-Communications) Deep Cooking: Predicting Food Ingredient Amounts from Images Jiatong Li (Rutgers University)

Impact of Mixed Reality Food Labels on Product Selection: Insights from a User Study using Headset-mediated Food Labels at a Vending Machine

Klaus Fuchs (ETH Zurich) Unseen Food Creation by Mixing Existing Food Images with Conditional StyleGAN Daichi Horita (The University of Electro-Communications)

Self-Attention and Ingredient-Attention Based Model for Recipe Retrieval from Image Queries

Matthias Fontanellaz (University of Bern) Convolutional Neural Networks for Food Image Recognition: An Experimental Study Yi Sen Ng (National University of Singapore) Categorization of Cooking Actions Based on Visual Similarity Yixin Zhang (Kyoto University)

Scraping Social Media Photos Posted in Kenya and Elsewhere to Detect and Analyze Food Types

Mona Jalal (Boston University) Flavour Enhanced Food Recommendation Nitish Nag (University of California, Irvine)

  35/88

  

Workshop 4: SALMM — Search as Learning with Multimedia Information Abstract: The First International Workshop on "Search as Learning with Multimedia Information" (SALMM’19) presents interdisciplinary contributions that address multimedia aspects in search as learning scenarios. The research topic of search as learning (SAL) recently emerged in the field of information retrieval and investigates informal, web-based learning processes as they happen every day with the help of search engines. While highly active, the SAL community still shows a focus on textual documents. This conflicts with research on multimedia learning in educational psychology: Humans tend to grasp and internalize new knowledge easier and more efficiently when it is conveyed using multiple modalities. The workshop SALMM aims to bridge the gap between the communities of SAL and multimedia. Organizers:

● Ralph Ewerth, L3S Research Center, Leibniz Universität Hannover ● Anett Hoppe, Leibniz Information Centre for Science and Technology (TIB) ● Stefan Dietze, Heinrich Heine University Düsseldorf ● Ran Yu, GESIS – Leibniz Institute for the Social Sciences

Monday October 21 — Half day workshop — 09:00-12:30 — location Galliéni 5 09:00 Welcome & Introductory session by organizers Ralph Ewerth, Anett Hoppe (TIB Germany) 09:15 First Keynote: Search Interfaces and Learning about Controversial Topics Ladislao Salmerón (University of Valencia) 10:00 Metacognitive Judgments in Searching as Learning (SAL) Tasks: Insights on (Mis-)

Calibration, Multimedia Usage, and Confidence Johannes von Hoyer (IWM Tübingen) 10:30 Refreshments (Central Space) 11:00 Investigating Correlations of Automatically Extracted Multimodal Features and Lecture

Video Quality Christian Otto (TIB Hannover) 11:30 Second Keynote: HyperTED: Exploring Video Lectures at the Fragment Levels for

Enhancing Learning Raphaël Troncy (EURECOM) 12:15 Discussion: Future Research Challenges in Search as Learning with Multimedia

Information All participants (moderated by Ralph Ewerth and Anett Hoppe)

  36/88

  

Workshop 5: SUMAC — Structuring and Understanding of Multimedia heritAge Contents Abstract: SUMAC 2019 is the first workshop on Structuring and Understanding of Multimedia heritAge Contents. It is held in Nice, France on October 21, 2019 and is co-located with the 27th ACM International Conference on Multimedia. Its objective is to present and discuss the latest and most significant trends and challenges in the analysis, structuring and understanding of multimedia contents dedicated to the valorization of heritage, with the emphasis on the unlocking of and access to the big data of the past. A representative scope of Computer Science methodologies dedicated to the processing of multimedia heritage contents and their exploitation is covered by the works presented, with the ambition of advancing and raising awareness about this fully developing research field. Organizers:

● Valérie Gouet-Brunet, IGN/LaSTIG ● Liming Chen, Centrale Lyon/LIRIS ● Sander Münster, Technische Universität Dresden ● Margarita Khokhlova, IGN/Cogit, Liris/Centrale Lyon

Monday October 21 — Full day workshop — 09:00-17:30 — location Galliéni 7 09:00 Welcome & Introductory session by organizers Valérie Gouet-Brunet (IGN/LaSTIG), Margarita Khokhlova (IGN/LaSTIG, Centrale Lyon/LIRIS),

Liming Chen (Centrale Lyon/LIRIS), Sander Münster (Technische Univ. Dresden) 09:15 Keynote #1: Beyond Three Dimensions: Managing Space, Time and Subjectivity in Your

Data Fabio Vitali (University of Bologna) 10:00 Pseudo-Cyclic Network for Unsupervised Colorization with Handcrafted Translation and

Output Spatial Pyramids Rémi Ratajczak (LIRIS/Université Lumière Lyon 2) 10:30 Refreshments (Central Space) 11:00 Recognizing Characters in Art History Using Deep Learning Prathmesh Madhu (Friedrich-Alexander-Universität Erlangen-Nürnberg) 11:30 Historical and Modern Features for Buddha Statue Classification Benjamin Renoust (Osaka University) 12:00 Poster Session during lunch time Jenny Benois-Pineau (LABRI/Université Bordeaux), Samarth Bhargav (University of Amsterdam),

Sakino Ando (Kumamoto University) 12:30 Lunch (Central Space) 14:15 Challenging Deep Image Descriptors for Retrieval in Heterogeneous Iconographic

Collections Dimitri Gominski (Centrale Lyon/LIRIS, IGN) 14:45 Keynote #2: Visualizing Orientations of Large Numbers of Photographs Florian Niebling (Universität Würzburg) 15:30 Refreshments (Central Space) 16:00 Processing Historical Film Footage with Photogrammetry and Machine Learning for

Cultural Heritage Documentation Francesca Condorelli (Politecnico di Torino) 16:30 An Interactive Web Application for the Creation, Organization, and Visualization of Repeat

Photographs Axel Schaffland (University of Osnabrück)

  37/88

Workshop 6: HealthMedia — Multimedia for Personal Health and Health Care Abstract: Managing one’s health is among the most personal and most important challenges. HealthMedia can be viewed as one response from the multimedia community to rise to this challenge. There is an increasing number of research work that shows how core multimedia research is becoming an important enabler for solutions with applications and relevance for the societal questions of health. Within this workshop, we continue to explore the relevance, contribution and future directions of multimedia to health care and personal health. This workshop brings together researchers from diverse topics such as multimedia, tracking, lifelogging, accessibility, HCI, but also health, medicine, and psychology to address challenges and opportunities of multimedia in and for health.

Organizers: ● Susanne Boll, University of Oldenburg● Noel E. O’Connor, Dublin City University● Nitish Nag, University of California, Irvine● Jochen Meyer, OFFIS Institute for Information Technology● Jeannie Lee, Singapore Institute of Technology

Monday October 21 — Half day workshop — 14:00-17:30 — location Galliéni 5

14:00 Welcome Susanne Boll (Carl von Ossietzky-University Oldenburg); Jochen Meyer (OFFIS Institute for Information Technology); Noel E. O'Connor (Dublin City University); Jeannie Lee (Singapore Institute of Technology); Nitish Nag (University of California, Irvine)

14:05 Keynote: Clinical Applications of Brain Computer Interfaces Maureen Clerc, Research Director, INRIA Sophia Antipolis-Méditerranée France

15:00 Am I Coughing More than Usual? Patient Reflections on Tracking COPD Data in Telehealth Systems Stephanie Nadarajah (Aalborg U.); Peder Walz Pedersen (Aalborg U.); Bastian Ilsø Hougaard (Aalborg U.); Hendrik Knoche (Aalborg U.)

15:15 One-Dimensional Convolutional Neural Networks on Motor Activity Measurements in Detection of Depression Joakim Ihle Frogner (U. of Oslo); Farzan Majeed Noori (U. of Oslo); Paal Halvorsen (U. of Oslo); Steven Hicks (Simula Metropolitan Center for Digitalization); Enrique Garcia-Ceja (Software and Service Innovation, SINTEF Digital); Jim Torresen (U. of Oslo); Michael Riegler (U. of Oslo)

15:30 Refreshments (Central Space)

16:00 Do Trait Anxiety Scores Reveal Information About Our Response to Anxious Situations? A Psycho-Physiological VR Study Ramesh Tadayon (Arizona State U.); Chetan Gupta (Arizona State U.); Debra Crews (Arizona State U.); Troy Mcdaniel (Arizona State U.)

16:15 Mobile Application for Crowdsourced Gamification of Automated External Defibrillator (AED) Locations Muhammad Imran Hakim Bin Hussein (U. of Glasgow); Jun Hao Fong (Singapore Institute of Technology); Chu Xuan Lim (Singapore Institute of Technology); Jeannie Lee (Singapore Institute of Technology); Chek Tien Tan (Singapore Institute of Technology); Yih Yng Ng (Tan Tock Seng Hospital)

16:30 Towards Personalizing Participation in Health Studies Vlad Manea (U. of Copenhagen); Mads Schnoor Hansen (U. of Copenhagen); Semahat Ece Elbeyi (U. of Copenhagen); Katarzyna Wac (U. of Geneva)

16:45 Interactivity All participants

38/88

  

Tutorial 1: AutoML and Meta-learning for Multimedia Abstract: This tutorial disseminates and promotes the recent research achievements on AutoML and meta-learning as well as their applications on multimedia, which is an exciting and fast-growing research direction in the general field of machine learning and multimedia. We will present novel, high-quality research findings, as well as innovative solutions to the challenging problems in AutoML and meta-learning on multimedia. The tutorial contains five sections:

1. The research and industrial motivation, 2. Hyperparameter optimization for multimedia applications, 3. Neural architecture search and its applications in multimedia, 4. Meta-learning for multimedia, 5. Discussions and future directions

Speakers: ● Wenwu Zhu, Tsinghua University ● Xin Wang, Tsinghua University ● Wenpeng Zhang, Tsinghua University

Monday October 21 — Half day tutorial — 09:00-12:30 — location Rhodes 9

Tutorial 2: Learning from 3D (Point Cloud) Data Abstract: Learning on (3D) point clouds is vital for a broad range of emerging applications such as autonomous driving, robot perception, augmented reality, gaming, and security. Such needs have increased recently due to the prevalence of 3D sensors such as LiDAR, 3D camera, and RGB-D. Point clouds consist of thousands to millions of points; They contain rich information and are complementary to the traditional 2D cameras that we have been working on for years in the multimedia (or vision) community. 3D learning algorithms on point cloud data are new, and exciting, for numerous core problems such as 3D classification, detection, semantic segmentation, and face recognition. This tutorial covers the requirements of point cloud data, the background of capturing the data, 3D representations, emerging applications, core problems, state-of-the-art learning algorithms, and future research opportunities. Speaker: Winston Hsu, National Taiwan University Monday October 21 — Half day tutorial — 09:00-12:30 — location Galliéni 1&2

  39/88

Tutorial 3: Multimedia Forensics

Abstract: With the availability of powerful and easy-to-use media editing tools, falsifying images and videos has become widespread in the last few years. Coupled with ubiquitous social networks, this allows for the viral dissemination of fake news. This raises huge concerns on multimedia security. This scenario became even worse with the advent of deep learning. New, sophisticated methods have been proposed to accomplish manipulations that were previously unthinkable (e.g., deepfake). This tutorial will present the most reliable methods for detection of manipulated images and for source identification. These are important tools nowadays to carry out fact checking and authorship verification. State-of-the-art solutions exploiting either model-based or data-driven techniques will be presented. The most innovative approaches based on deep learning will be described, considering both supervised and unsupervised approaches. Results will be presented on challenging datasets and realistic scenarios.

Speakers: ● Luisa Verdoliva, University Federico II of Naples● Paolo Bestagini, Politecnico di Milano

Monday October 21 — Half day tutorial — 14:00-17:30 — location Rhodes 9

Tutorial 4: A Journey towards Fully Immersive Media Access

Abstract: Universal media access as proposed almost two decades ago is now reality. We can generate, distribute, share, and consume any media content, anywhere, anytime, and with/on any device. A technical breakthrough was the adaptive streaming over HTTP resulting in the standardization of MPEG-DASH, which is now successfully deployed in a plethora of environments. The next big thing in adaptive media streaming is virtual reality applications and, specifically, omnidirectional (360°) media streaming, which is currently built on top of the existing adaptive streaming ecosystems. This tutorial provides a detailed overview of adaptive streaming of both traditional and omnidirectional media. The tutorial focuses on the basic principles and paradigms for adaptive streaming as well as on already deployed content generation, distribution, and consumption workflows. Additionally, the tutorial provides insights into standards and emerging technologies in the adaptive streaming space. Finally, the tutorial includes the latest approaches for immersive media streaming enabling 6DoF DASH through Point Cloud Compression (PCC) and concludes with open research issues and industry efforts in this domain.

Speakers: ● Christian Timmerer, Klagenfurt University and Bitmovin● Ali C. Begen, Ozyegin University and Networked Media

Monday October 21 — Half day workshop — 14:00-17:30 — location Galliéni 1&2

40/88

  

Art Exhibition From Tuesday October 22 to Thursday October 24 09:00-18:00 — location Foyer Athéna The art exhibition will run in parallel to the main conference. Please visit the exhibition during the Reception, but also at any time during the conference. There will also be ample opportunities to meet the artists. The opening of the art exhibition takes place on Monday October 21, 18:00, during the Reception. Latent History Refik Anadol (media artist/director, United States) The Data Stones Peter Nelson (visual artist/academic, Australia/East Asia) Unresolved Sun: An Interactive Art-Science Installation to Explore the Behaviour of Mist Jean-Marc Chomaz (artist /physicist, Ecole Polytechnique and Labofactory, France); Laurent Karst (architect /designer, ENSA Dijon and Labofactory, France); Filippo Fabbri (researcher/composer, Paris-Saclay University and Labofactory, France); Greg Louis (composer, ESSS and Labofactory, France) Toasters Olivain Porry (artist/researcher, ENSAD Paris, France) The One: An Interactive Installation for Visualizing the Cognition of Mind State by Capturing Face Expression, Body Shape, Wearing Cloth and Talking Voice Lyn Chao-Ling Chen (artist, Banqiao 435 Art Zone,Taiwan) I, You, We: Multimedia Interactive Installation and Performance Cecilia Suhr (artist/researcher, Miami University Regional, United States) MovIPrint: Move, Explore and Fabricate Yen-Ting Cho (National Cheng Kung University, Taiwan); Yen-Ling Kuo (Massachusetts Institute of Technology, United States); Yen-Ting Yeh (University of Waterloo, Canada); Yi-Chin Lee (Carnegie Mellon University, United States) Macro-groove - A Sound 3D-sculpture Interactive Player Paul Chable (University of Toulouse, France); Gilles Arrazo (Independent Artist, France); Yvain Quéau (University of Toulouse, France); Axel Cartier (CNRS - University of Caen, France); Jean-Denis Durou (University of Toulouse, France)

  41/88

  

Tuesday Keynote — Using Artificial Intelligence to Preserve Audiovisual Archives: New Horizons, More Questions

Speaker: Jean Carrive, Research & Innovation Department / French National Audiovisual Institute (INA) Session Chair: Laurent Amsaleg, CNRS-IRISA (France) Tuesday October 22 — 09:00-10:00 — location Athéna France has a long tradition of preserving its archives as well as its cultural heritage, as demonstrated by the “legal deposit”. Established in the Renaissance for printed documents, the legal deposit aims to allow the collection and consultation of various kinds of documents. INA, the French National Audiovisual Institute, is in charge of this task for France’s radio and television, as well as French media on the web. INA’s mission is to make the most of its collections: commercially by selling programs, and academically by making these collections available to researchers working on humanities and social sciences. Since its creation in 1975, INA has constantly developed its tools and methodologies for describing and documenting its collections: databases, thesauri, lexicons, documentation software, indexing methods indexing, search engines, etc. Its Research and Innovation Department has for many years been interested in partnering with academic laboratories to explore the possibilities of automatic content analysis technologies. The emergence of AI-derived technologies is now making it possible to consider new uses of these collections, but also raises new questions. INA has thus demonstrated that it now becomes possible to mass-treat large audiovisual corpora to identify various kinds of information, thus facilitating indexing, documentation and search in order to provide better services to users. For researchers in humanities and social sciences working on these resources at Inathèque de France, these new means of analysis allow to conduct new types of Digital Humanities investigations, but also introduce new methodological challenges. For INA’s archivists and librarians, AI’s assistance facilitates the documentation process but also poses questions about the impact of these technologies on professional practices, as well as on the scalability of these technologies over time. The presentation will address these questions, building on the research projects and experiments carried out at INA.

  42/88

  

Session 1A: Multimodal Fusion & Visual Relations Session Chair: Chong-Wah Ngo, City University of Hong Kong (Hong Kong) Tuesday October 22 — Main Track — 10:30-12:00 — location Athéna

10:30 *P1A-01 Focus Your Attention: A Bidirectional Focal Attention Network for Image-Text Matching Chunxiao Liu (Institute of Information Engineering, Chinese Academy of Sciences); Zhendong Mao (Institute of Information Engineering, Chinese Academy of Sciences); An-An Liu (Tianjin U.); Tianzhu Zhang (U. of Science and Technology of China); Bin Wang (Xiaomi AI Lab); Yongdong Zhang (U. of Science and Technology of China)

10:45 *P1A-02 Matching Images and Text with Multi-modal Tensor Fusion and Re-ranking Tan Wang (U. of Electronic Science and Technology of China); Xing Xu (U. of Electronic Science and Technology of China); Yang Yang (U. of Electronic Science and Technology of China); Alan Hanjalic (Delft U. of Technology); Heng Tao Shen (U. of Electronic Science and Technology of China); Jingkuan Song (U. of Electronic Science and Technology of China)

11:00 P1A-03 Vision-Language Recommendation via Attribute Augmented Multimodal Reinforcement Learning Tong Yu; Yilin Shen; Xiangyu Zeng; Ruiyi Zhang; Hongxia Jin — (Samsung Electronics)

P1A-04 Multi-modal Multi-layer Fusion Network with Average Binary Center Loss for Face Anti-spoofing Huafeng Kuang (Xiamen U.); Rongrong Ji (Xiamen U.); Hong Liu (Xiamen U.); Shengchuan Zhang (Xiamen U.); Xiaoshuai Sun (Harbin Institute of Technology); Feiyue Huang (Tencent Youtu Lab); Baochang Zhang (Beihang U.)

P1A-05 Dual-alignment Feature Embedding for Cross-modality Person Re-identification Yi Hao (Xidian U.); Nannan Wang (Xidian U.); Xinbo Gao (Xidian U.); Jie Li (Xidian U.); Xiaoyu Wang (Intellifusion)

P1A-06 Video Text Detection by Attentive Spatiotemporal Fusion of Deep Convolutional Features Lan Wang; Jiahao Shi; Yang Wang; Feng Su — (Nanjing U.)

P1A-07 Cross-Modal Subspace Learning with Scheduled Adaptive Margin Constraints David Semedo; Joao Magalhaes — (U. NOVA de Lisboa)

11:15 *P1A-08 Structured Stochastic Recurrent Network for Linguistic Video Prediction Shijie Yang (U. of Chinese Academy of Sciences); Liang Li (U. of Chinese Academy of Sciences); Shuhui Wang (Institute of Computing Technology, Chinese Academy of Sciences); Dechao Meng (U. of Chinese Academy of Sciences); Qingming Huang (U. of Chinese Academy of Sciences); Qi Tian (Huawei Noah's Ark Lab)

11:30 *P1A-09 Visual Relationship Detection with Relative Location Mining Hao Zhou (Shanghai Jiao Tong U.); Chongyang Zhang (Shanghai Jiao Tong U.); Chuanping Hu (Railway Police College)

11:45 P1A-10 Video Relation Detection with Spatio-Temporal Graph Xufeng Qian (Zhejiang U.); Yueting Zhuang (Zhejiang U.); Yimeng Li (Zhejiang U.); Shaoning Xiao (Zhejiang U.); Shiliang Pu (Hikvision Research Institute); Jun Xiao (Zhejiang U.)

P1A-11 Hierarchical Visual Relationship Detection Xu Sun (Nanjing U.); Yuan Zi (Nanjing U.); Tongwei Ren (Nanjing U.); Jinhui Tang (Nanjing U. of Science and Technology); Gangshan Wu (Nanjing U.)

P1A-12 Cost-free Transfer Learning Mechanism: Deep Digging Relationships of Action Categories Yanan Ma (The Institute of Computing Technology of the Chinese Academy of Sciences, U. of Chinese Academy of Sciences); Wanneng Wang (The Institute of Computing Technology of the Chinese Academy of Sciences, U. of Chinese Academy of Sciences); Ke Gao (The Institute of Computing Technology of the Chinese Academy of Sciences); Juan Cao (The Institute of Computing Technology of the Chinese Academy of Sciences)

P1A-13 Mixed-dish Recognition with Contextual Relation Networks Lixi Deng (Institute of Computing Technology, Chinese Academy of Sciences); Jingjing Chen (National U. of Singapore); Qianru Sun (National U. of Singapore); Xiangnan He (U. of Science and Technology of China); Sheng Tang (Institute of Computing Technology, Chinese Academy of Sciences); Zhaoyan Ming (National U. of Singapore); Yongdong Zhang (Institute of Computing Technology, Chinese Academy of Sciences); Tat Seng Chua (National U. of Singapore)

P1A-14 Visual Relation Detection with Multi-Level Attention Sipeng Zheng; Shizhe Chen; Qin Jin — (The Renmin U. of China)

  43/88

  

Session 1B: Affective Computing & Facial Analytics Session Chair: Albert Ali Salah, Utrecht University (Netherlands) Tuesday October 22 — Main Track — 10:30-12:00 — location Hermès 10:30 *P1B-01 Multimodal Deep Denoise Framework for Affective Video Content Analysis

Yaochen Zhu (Wuhan U.); Zhenzhong Chen (Wuhan U.); Feng Wu (U. of Science and Technology of China)

10:45 *P1B-02 Predicting and Understanding News Social Popularity with Emotional Salience Features Raj Kumar Gupta (Institute of High Performance Computing); Yinping Yang (Agency for Science, Technology and Research (A*STAR), Institute of High Performance Computing)

11:00 P1B-03 A Multimodal View into Music's Effect on Human Neural, Physiological, and Emotional Experience Timothy Greer; Benjamin Ma; Matthew Sachs; Assal Habibi; Shrikanth Narayanan — (U. of Southern California)

P1B-04 Emotion Recognition using Multimodal Residual LSTM Network Jiaxin Ma (OMRON SINIC X Corporation); Hao Tang (Dept. of Computer Science and Engineering, SJTU); Wei-Long Zheng (Dept. of Neurology, Massachusetts General Hospital, Harvard Medical School); Bao-Liang Lu (Dept. of Computer Science and Engineering, SJTU)

P1B-05 Stereoscopic Visual Discomfort Prediction Using Multi-scale DCT Features Yang Zhou (Hangzhou Dianzi U.); Wanli Yu (Hangzhou Dianzi U.); Zhu Li (Missouri U. of Kansas City); Haibing Yin (Hangzhou Dianzi U.)

P1B-06 PDANet: Polarity-consistent Deep Attention Network for Fine-grained Visual Emotion Regression Sicheng Zhao (U. of California, Berkeley); Zizhou Jia (Tsinghua U.); Hui Chen (Tsinghua U.); Leida Li (China U. of Mining and Technology); Guiguang Ding (Tsinghua U.); Kurt Keutzer (U. of California, Berkeley)

P1B-07 Towards Increased Accessibility of Meme Images with the Help of Rich Face Emotion Captions Prajwal K R (Int. Institute of Information Technology, Hyderabad); Jawahar C V (Int. Institute of Information Technology, Hyderabad); Ponnurangam Kumaraguru (Indraprastha Institute of Information Technology Delhi)

11:15 *P1B-08 Effective Sentiment-relevant Word Selection for Multi-modal Sentiment Analysis in Spoken Language Dong Zhang; Shoushan Li; Qiaoming Zhu; Guodong Zhou — (Soochow U.)

11:30 *P1B-09 Mutual Correlation Attentive Factors in Dyadic Fusion Networks for Speech Emotion Recognition Yue Gu (Rutgers U.); Xinyu Lyu (Rutgers U.); Weijia Sun (Rutgers U.); Weitian Li (Rutgers U.); Shuhong Chen (Rutgers U.); Xinyu Li (Amazon AI); Ivan Marsic (Rutgers U.)

11:45 P1B-10 Comp-GAN: Compositional Generative Adversarial Network in Synthesizing and Recognizing Facial Expression Wenxuan Wang (Fudan U.); Qiang Sun (Fudan U.); Yanwei Fu (Fudan U.); Tao Chen (Fudan U.); Chenjie Cao (Ping An OneConnect); Ziqi Zheng (Ping An OneConnect); Guoqiang Xu (Ping An OneConnect); Han Qiu (Ping An OneConnect); Yu-Gang Jiang (Fudan U.); Xiangyang Xue (Fudan U.)

P1B-11 TC-GAN: Triangle Cycle-Consistent GANs for Face Frontalization with Facial Features Preserved Juntong Cheng (Shanghai Key Lab of Intelligent Information Processing, School of Computer Science, Fudan U.); Yi-Ping Phoebe Chen (La Trobe U., Melbourne); Yu-Gang Jiang (Fudan U. and Jilian Technology Group); Minjun Li (Shanghai Key Lab of Intelligent Information Processing, School of Computer Science, Fudan U.)

P1B-12 Fewer-Shots and Lower-Resolutions: Towards Ultrafast Face Recognition in the Wild Shiming Ge (Chinese Academy of Sciences); Shengwei Zhao (Chinese Academy of Sciences); Xindi Gao (Chinese Academy of Sciences); Jia Li (Beihang U.)

P1B-13 Identity- and Pose-Robust Facial Expression Recognition through Adversarial Feature Learning Can Wang; Shangfei Wang; Guang Liang — (U. of Science and Technology of China)

P1B-14 Self-supervised Face-Grouping on Graphs Veith Röthlingshöfer (Karlsruhe Institute of Technology); Vivek Sharma (KIT, MIT); Rainer Stiefelhagen (Karlsruhe Institute of Technology)

  44/88

  

Session 1C: Fashion & Human Analysis Session Chair: Noel E. O’Connor, Dublin City University (Ireland) Tuesday October 22 — Main Track — 10:30-12:00 — location Rhodes 9 10:30 *P1C-01 Who, Where, and What to Wear? Extracting Fashion Knowledge from Social Media

Yunshan Ma; Xun Yang; Lizi Liao; Yixin Cao; Tat-Seng Chua — (National U. of Singapore)

10:45 *P1C-02 Virtually Trying on New Clothing with Arbitrary Poses Na Zheng (Shandong U.); Xuemeng Song (Shandong U.); Zhaozheng Chen (Shandong U.); Linmei Hu (Beijing University of Posts and Telecommunications); Da Cao (Hunan U.); Liqiang Nie (Shandong U.)

11:00 P1C-03 M2E-Try On Net: Fashion from Model to Everyone Zhonghua Wu; Guosheng Lin; Qingyi Tao; Jianfei Cai — (Nanyang Technological U.)

P1C-04 Personalized Capsule Wardrobe Creation with Garment and User Modeling Xue Dong (Shandong U.); Xuemeng Song (Shandong U.); Fuli Feng (National U. of Singapore); Peiguang Jing (Tianjin U.); Xin-Shun Xu (Shandong U.); Liqiang Nie (Shandong U.)

P1C-05 Aesthetic Attributes Assessment of Images Xin Jin (Beijing Electronic Science and Technology Institute); Le Wu (Beijing Electronic Science and Technology Institute); Geng Zhao (Beijing Electronic Science and Technology Institute); Xiaodong Li (Beijing Electronic Science and Technology Institute); Xiaokun Zhang (Beijing Electronic Science and Technology Institute); Shiming Ge (Institute of Information Engineering, Chinese Academy of Sciences); Dongqing Zou (Sense Time); Bin Zhou (Beihang University); Xinghui Zhou (Beijing Electronic Science and Technology Institute)

P1C-06 GP-BPR: Personalized Compatibility Modeling for Clothing Matching Xuemeng Song (Shandong U.); Xianjing Han (Shandong U.); Yunkai Li (Shandong U.); Jingyuan Chen (Alibaba Group); Xin-Shun Xu (Shandong U.); Liqiang Nie (Shandong U.)

P1C-07 Outfit Compatibility Prediction and Diagnosis with Multi-Layered Comparison Network Xin Wang (Donghua U., JD AI Research); Bo Wu (Columbia U.); Yueqi Zhong (Donghua U.)

11:15 *P1C-08 FashionOn: Semantic-guided Image-based Virtual Try-on with Detailed Human and Clothing Information Chia-Wei Hsieh (National Chiao Tung U.); Chieh-Yun Chen (National Chiao Tung U.); Chien-Lung Chou (National Chiao Tung U.); Hong-Han Shuai (National Chiao Tung U.); Jiaying Liu (Peking U.); Wen-Huang Cheng (National Chiao Tung U.)

11:30 *P1C-09 POINet: Pose-Guided Ovonic Insight Network for Multi-Person Pose Tracking Weijian Ruan (Wuhan U.); Wu Liu (AI Research of JD.com); Qian Bao (AI Research of JD.com); Jun Chen (Wuhan U.); Yuhao Cheng (AI Research of JD.com); Tao Mei (AI Research of JD.com)

11:45 P1C-10 BraidNet: Braiding Semantics and Details for Accurate Human Parsing Xinchen Liu (AI Research of JD.com); Meng Zhang (AI Research of JD.com); Wu Liu (AI Research of JD.com); Jingkuan Song (University of Electronic Science and Technology of China, UESTC); Tao Mei (AI Research of JD.com)

P1C-11 Modality-aware Collaborative Learning for Visible Thermal Person Re-Identification Mang Ye (Hong Kong Baptist University); Xiangyuan Lan (Hong Kong Baptist University, Hong Kong); Qingming Leng (Jiujiang University)

P1C-12 Adaptive Multi-Path Aggregation for Human DensePose Estimation in the Wild Yuyu Guo (U. of Electronic Science and Technology of China); Lianli Gao (U. of Electronic Science and Technology of China); Jingkuan Song (U. of Electronic Science and Technology of China); Peng Wang (The U. of Adelaide); Wuyuan Xie (Shenzhen U.); Heng Tao Shen (U. of Electronic Science and Technology of China)

P1C-13 Illumination-Invariant Person Re-Identification Yukun Huang (U. of Science and Technology of China); Zheng-Jun Zha (U. of Science and Technology of China); Xueyang Fu (U. of Science and Technology of China); Wei Zhang (Shandong U.)

P1C-14 AI Coach: Creating Personal Athletic Training Experiences by Human Pose Analysis in Videos Jianbo Wang (Zhejiang U.); Kai Qiu (Microsoft); Houwen Peng (Microsoft); Jianlong Fu (Microsoft); Jianke Zhu (Zhejiang U.)

  45/88

  

Session 1D: Live Multimedia Applications & Streaming Session Chair: Wei Tsang Ooi, National University of Singapore (Singapore) Tuesday October 22 — Main Track — 10:30-12:00 — location Risso 6 10:30 *P1D-01 Online Camera Pose Optimization for the Surround-view System

Xiao Liu; Lin Zhang; Ying Shen; Shaoming Zhang; Shengjie Zhao — (Tongji University) 10:45 *P1D-02 LiveSense: Contextual Advertising in Live Streaming Videos

Xiang Chen (Adobe Research); Tam V. Nguyen (U. of Dayton); Zhiqi Shen (National U. of Singapore); Mohan Kankanhalli (National U. of Singapore)

11:00 P1D-03 Livesmart: A QoS-Guaranteed Cost-Minimum Framework of Viewer Scheduling for Crowdsourced Live Streaming Rui-Xiao Zhang (Tsinghua U.); Ming Ma (Beijing Kuaishou Technology Co., Ltd, P.R. China); Tianchi Huang (Tsinghua U.); Haitian Pang (Tsinghua U.); Chenglei Wu (Tsinghua U.); Xin Yao (Tsinghua U.); Jiangchuan Liu (Simon Fraser U.); Lifeng Sun (Tsinghua U.)

P1D-04 Comyco: Quality-Aware Adaptive Video Streaming via Imitation Learning Tianchi Huang (Tsinghua U.); Chao Zhou (China Beijing Kuaishou Technology Co., Ltd.); Rui-Xiao Zhang (Tsinghua U.); Chenglei Wu (Tsinghua U.); Xin Yao (Tsinghua U.); Lifeng Sun (Tsinghua U.)

P1D-05 Low-Latency Network-Adaptive Error Control for Interactive Streaming Silas L. Fong (U. of Toronto); Salma Emara (U. of Toronto); Baochun Li (U. of Toronto); Ashish Khisti (U. of Toronto); Wai-Tian Tan (Cisco Systems); Xiaoqing Zhu (Cisco Systems); John Apostolopoulos (Cisco Systems)

P1D-06 Navigation Graph for Tiled Media Streaming Jounsup Park; Klara Nahrstedt — (U. of Illinois at Urbana-Champaign)

P1D-07 CACA: Learning-based Content-aware Cache Admission for Video Content in Edge Caching Yu Guan; Xinggong Zhang; Zongming Guo — (Peking U.)

11:15 *P1D-08 Real-Time Gesture Recognition Using 3D Sensory Data and a Light Convolutional Neural Network Nick Diliberti (U. of Alabama in Huntsville); Chao Peng (U. of Alabama in Huntsville); Christopher Kaufman (U. of Alabama in Huntsville); Yangzi Dong (U. of Alabama in Huntsville); Jeff Hansberger (Army Research Lab)

11:30 *P1D-09 Embodied One-Shot Video Recognition: Learning from Actions of a Virtual Embodied Agent Yuqian Fu (Fudan U.); Chengrong Wang (Shanghai Tech. U.); Yanwei Fu (Fudan U.); Yu-Xiong Wang (CMU); Cong Bai (Zhejiang U. of Technology); Xiangyang Xue (Fudan U.); Yu-Gang Jiang (Fudan U. and Jilian Technology Group)

11:45 P1D-10 Dense Feature Aggregation and Pruning for RGBT Tracking Yabin Zhu; Chenglong Li; Bin Luo; Jin Tang; Xiao Wang — (Anhui U.)

P1D-11 Asynchronous Tracking-by-Detection on Adaptive Time Surfaces for Event-based Object Tracking Haosheng Chen; Qiangqiang Wu; Yanjie Liang; Xinbo Gao; Hanzi Wang — (Xiamen U.)

P1D-12 Exploit the Connectivity: Multi-Object Tracking with TrackletNet Gaoang Wang; Yizhou Wang; Haotian Zhang; Renshu Gu; Jenq-Neng Hwang — (U. of Washington)

P1D-13 Themis: Efficient and Adaptive Resource Partitioning for Reducing Response Delay in Cloud Gaming Yusen Li (Nankai U.); Haoyuan Liu (Nankai U.); Xiwei Wang (Nankai U.); Lingjun Pu (Nankai U.); Trent Marbach (Nankai U.); Shanjiang Tang (Tianjin U.); Gang Wang (Nankai U.); Xiaoguang Liu (Nankai U.)

P1D-14 PAN: Persistent Appearance Network with an Efficient Motion Cue for Fast Action Recognition Can Zhang (Peking U., Shenzhen); Yuexian Zou (Peking U., Shenzhen; Peng Cheng Laboratory); Guang Chen (Peking U., Shenzhen); Lei Gan (Peking U., Shenzhen)

  46/88

  

Diversity Lunch Keynote — FemTech.dk: Broadening Participation to Computing

Speakers: ● Maria Menendez-Blanco, University of Copenhagen ● Pernille Bjørn, University of Copenhagen

Session Chair: Susanne Boll, University of Oldenburg (Germany) Tuesday October 22 — 13:00-13:30 — location Central Space In the digital age, the fields and professions related to computing are having an unprecedented impact on our lives, and on societies. As computing becomes integrated in fundamental ways in healthcare, labor markets, and political processes, questions about who participates and takes decisions in developing digital technologies are becoming increasingly crucial and unavoidable. This keynote addresses this pressing issue by discussing gender issues in computing through our experience running FemTech.dk. Denmark is often viewed as a progressive country with gender equality; therefore, the gender homogeneity displayed in computer science education often comes as a surprise. However, in 2016, only 8% of the incoming bachelor students were women at DIKU. This situation was the trigger for FemTech.dk, an action research project started in 2017 at DIKU. The project focuses on creating opportunities for young women with no prior interest in Computer Science to explore ways in which computing could match their personal interests. Unsurprisingly, our results show that there is no silver bullet to address the gender gap in computing. Throughout this project we have developed a great amount of insights which can be useful for engaging in similar endeavors and prompting discussions among those interested in addressing the issue of women as gender minority in computing. These insights include the importance of changing computer science departments from “within”, the relevance of challenging stereotypical and narrow definitions of computer science, and the instrumentality of interactive artefacts in prompting change.

  47/88

  

Session 2A: Knowledge Processing & Action Analysis Session Chair: Arnold Smeulders, University of Amsterdam (Netherlands) Tuesday October 22 — Main Track — 13:30-15:00 — location Athéna 13:30 *P2A-01 Training Efficient Saliency Prediction Models with Knowledge Distillation

Peng Zhang (U. of Chinese Academy of Sciences); Li Su (U. of Chinese Academy of Sciences ; Liang Li (Key Lab of Intelligent Information Processing, Institute of Computing Technology); Bingkun Bao (College of Telecommunications & Information Engineering, Nanjing U. of Posts and Telecommunications); Pamela Cosman (U. of California San Diego); Guorong Li (U. of Chinese Academy of Sciences); Qingming Huang (U. of Chinese Academy of Sciences)

13:45 *P2A-02 Explainable Video Action Reasoning via Prior Knowledge and State Transitions Tao Zhuo (National University of Singapore); Zhiyong Cheng (Shandong Artificial Intelligence Institute); Peng Zhang (Northwestern Polytechnical U.); Yongkang Wong (National U. of Singapore); Mohan Kankanhalli (National U. of Singapore)

14:00 P2A-03 Explainable Interaction-driven User Modeling over Knowledge Graph for Sequential Recommendation Xiaowen Huang (National Lab. of Pattern Recognition, Institute of Automation, Chinese Academy of Sciences); Quan Fang (National Lab. of Pattern Recognition, Institute of Automation, Chinese Academy of Sciences); Shengsheng Qian (National Lab. of Pattern Recognition, Institute of Automation, Chinese Academy of Sciences); Jitao Sang (Beijing Jiaotong U.); Yan Li (Kuaishou Technology); Changsheng Xu (National Lab. of Pattern Recognition, Institute of Automation, Chinese Academy of Sciences)

P2A-04 Learning Using Privileged Information for Food Recognition Lei Meng (National U. of Singapore); Long Chen (Zhejiang U.); Xun Yang (National U. of Singapore); Hanwang Zhang (Nanyang Technological U.); Dacheng Tao (The U. of Sydney); Chunyan Miao (Nanyang Technological U.); Tat-Seng Chua (National U. of Singapore)

P2A-05 Occluded Facial Expression Recognition Enhanced through Privileged Information Bowen Pan; Shangfei Wang; Bin Xia — (U. of Science and Technology of China)

P2A-06 Attention Transfer (ANT) Network for View-invariant Action Recognition Yanli Ji (U. of Electronic Science and Technology of China); Feixiang Xu (U. of Electronic Science and Technology of China); Yang Yang (U. of Electronic Science and Technology of China); Ning Xie (U. of Electronic Science and Technology of China); Heng Tao Shen (U. of Electronic Science and Technology of China); Tatsuya Harada (The U. of Tokyo)

P2A-07 Action Recognition with Bootstrapping based Long-range Temporal Context Attention Ziming Liu (Beijing Institute of Technology); Guangyu Gao (Beijing Institute of Technology); A. K. Qin (Swinburne U. of Technology); Tong Wu (Beijing Institute of Technology); Chi Harold Liu (Beijing Institute of Technology)

14:15 *P2A-08 Perceptual Visual Reasoning with Knowledge Propagation Guohao Li; Xin Wang; Wenwu Zhu — (Tsinghua U.)

14:30 *P2A-09 Knowledge-guided Pairwise Reconstruction Network for Weakly Supervised Referring Expression Grounding Xuejing Liu (VIPL, ICT, Chinese academy of science); Liang Li (Chinese Academy of Sciences); Shuhui Wang (VIPL, ICT, Chinese academy of science); Zheng-Jun Zha (U. of Science and Technology of China); Li Su (U. of Chinese Academy of Sciences); Qingming Huang (U. of Chinese Academy of Sciences)

14:45 P2A-10 Sparse Temporal Causal Convolution for Efficient Action Modeling Changmao Cheng (Fudan U. and Megvii Research Shanghai); Chi Zhang (Megvii); Yichen Wei (Megvii Research Shanghai); Yu-Gang Jiang (Fudan U. and Jilian Technology Group)

P2A-11 Optimized Skeleton-based Action Recognition via Sparsified Graph Regression Xiang Gao; Wei Hu; Jiaxiang Tang; Jiaying Liu; Zongming Guo — (Peking University)

P2A-12 Prediction-CGAN: Human Action Prediction with Conditional Generative Adversarial Networks Wanru Xu (Beijing Jiaotong U.); Jian Yu (Beijing Jiaotong U.); Zhenjiang Miao (Beijing Jiaotong U.); Lili Wan (Beijing Jiaotong U.); Qiang Ji (Rensselaer Polytechnic Institute)

P2A-13 Cross-Fiber Spatial-Temporal Co-enhanced Networks for Video Action Recognition Haoze Wu (U. of Science and Technology of China); Zheng-Jun Zha (U. of Science and Technology of China); Xin Wen (U. of Science and Technology of China); Zhenzhong Chen (Wuhan U.); Dong Liu (U. of Science and Technology of China); Xuejin Chen (U. of Science and Technology of China)

P2A-14 Long Short-Term Relation Networks for Video Action Detection Dong Li (U. of Science and Technology of China); Ting Yao (JD AI Research); Zhaofan Qiu (U. of Science and Technology of China); Houqiang Li (U. of Science and Technology of China); Tao Mei (JD AI Research)

  48/88

  

Session 2B: Adversarial Learning Session Chair: Pål Halvorsen, SimulaMet (Norway) Tuesday October 22 — Main Track — 13:30-15:00 — location Hermès 13:30 *P2B-01 Attacking Gait Recognition Systems via Silhouette Guided GANs

Meijuan Jia; Hongyu Yang; Di Huang; Yunhong Wang — (Beihang University) 13:45 *P2B-02 Mocycle-GAN: Unpaired Video-to-Video Translation

Yang Chen (U. of Science and Technology of China); Yingwei Pan (JD AI Research); Ting Yao (JD AI Research); Xinmei Tian (U. of Science and Technology of China); Tao Mei (JD AI Research)

14:00 P2B-03 STDGAN: ResBlock Based Generative Adversarial Nets Using Spectral Normalization and Two Different Discriminators Zhaoyu Zhang; Jun Yu — (University of Science and Technology of China)

P2B-04 Adversarial Colorization of Icons based on Contour and Color Conditions Tsai-Ho Sun; Chien-Hsun Lai; Sai-Keung Wong; Yu-Shuen Wang — (National Chiao Tung U.)

P2B-05 MetaAdvDet: Towards Robust Detection of Evolving Adversarial Attacks Chen Ma (Tsinghua U.); Chenxu Zhao (JD AI Research); Hailin Shi (JD AI Research); Li Chen (Tsinghua U.); Junhai Yong (Tsinghua U.); Dan Zeng (Shanghai U.)

P2B-06 Tell Me Where It is Still Blurry: Adversarial Blurred Region Mining and Refining Jen-Chun Lin (Yuan Ze U.); Wen-Li Wei (Institute of Information Science, Academia Sinica); Tyng-Luh Liu (Institute of Information Science, Academia Sinica); C.-C. Jay Kuo (U. of Southern California); Mark Liao (Institute of Information Science, Academia Sinica)

P2B-07 Joint-attention Discriminator for Accurate Super-resolution via Adversarial Training Rong Chen (School of Information Science and Engineering, Xiamen U.); Yuan Xie (East China Normal U.); Xiaotong Luo (School of Information Science and Engineering, Xiamen U.); Yanyun Qu (School of Information Science and Engineering, Xiamen U.); Cuihua Li (School of Information Science and Engineering, Xiamen U.)

14:15 *P2B-08 Adversarial Preference Learning with Pairwise Comparisons Zitai Wang (SKLOIS, Institute of Information Engineering, Chinese Academy of Sciences; SCS, U. of CAS); Qianqian Xu (Key Laboratory of Intelligent Information Processing, Institute of Computing Technology, Chinese Academy of Sciences); Ke Ma (SKLOIS, Institute of Information Engineering, Chinese Academy of Sciences; SCS, U. of CAS); Yangbangyan Jiang (SKLOIS, Institute of Information Engineering, Chinese Academy of Sciences; SCS, U. of CAS); Xiaochun Cao (SKLOIS, Institute of Information Engineering, Chinese Academy of Sciences; SCS, U. of CAS); Qingming Huang (School of Computer Science and Technology, U. of Chinese Academy of Sciences)

14:30 *P2B-09 Deep Adversarial Graph Attention Convolution Network for Text-Based Person Search Jiawei Liu; Zheng-Jun Zha; Richang Hong; Meng Wang; Yongdong Zhang — (University of Science and Technology of China)

14:45 P2B-10 BasketballGAN: Generating Basketball Play Simulation Through Sketching Hsin-Ying Hsieh (National Chiao Tung U.); Chieh-Yu Chen (NVIDIA Corporation); Yu-Shuen Wang (National Chiao Tung U.); Jung-Hong Chuang (National Chiao Tung U.)

P2B-11 Joint Adversarial Domain Adaptation Shuang Li (Beijing Institute of Technology); Chi Harold Liu (Beijing Institute of Technology); Binhui Xie (Beijing Institute of Technology); Limin Su (Beijing Institute of Technology); Zhengming Ding (Indiana U. - U. Indianapolis); Gao Huang (Tsinghua U.)

P2B-12 Adversarial Seeded Sequence Growing for Weakly-Supervised Temporal Action Localization Chengwei Zhang (Shanghai Jiao Tong U.); Yunlu Xu (Hikvision Research Institute); Zhanzhan Cheng (Hikvision Research Institute); Yi Niu (Hikvision Research Institute); Shiliang Pu (Hikvision Research Institute); Fei Wu (Zhejiang U.); Futai Zou (Shanghai Jiao Tong U.)

P2B-13 Cycle-consistent Conditional Adversarial Transfer Networks Jingjing Li (U. of Science and Technology of China); Erpeng Chen (U. of Science and Technology of China); Zhengming Ding (IUPUI); Lei Zhu (Shandong Normal U.); Ke Lu (University of Science and Technology of China); Zi Huang (The U. of Queensland)

P2B-14 GAN Flexible Lmser for Super-resolution Peiying Li; Shikui Tu; Lei Xu — (Shanghai Jiao Tong U.)

  49/88

  

Session 2C: Captioning & Video Analysis Session Chair: Ramesh Jain, University of California, Irvine (USA) Tuesday October 22 — Main Track — 13:30-15:00 — location Rhodes 9 13:30 *P2C-01 Aligning Linguistic Words and Visual Semantic Units for Image Captioning

Guo Longteng (Institute of Automation, Chinese Academy of Sciences); Jing Liu (NLPR of CASIA); Jinhui Tang (the School of Computer Science and Engineering, Nanjing University of Science and Technology); Jiangwei Li (Multimedia Department, Huawei Devices); Wei Luo (Multimedia Department, Huawei Devices); Hanqing Lu (Institute of Automation, Chinese Academy of Sciences)

13:45 *P2C-02 Hierarchical Global-Local Temporal Modeling for Video Captioning Yaosi Hu (Wuhan University); Zhenzhong Chen (Wuhan University); Zheng-Jun Zha (University of Science and Technology of China); Feng Wu (University of Science and Technology of China)

14:00 P2C-03 Attention-based Densely Connected LSTM for Video Captioning Yongqing Zhu; Shuqiang Jiang — (Institute of Computing Technology Chinese Academyof Sciences)

P2C-04 Critic-based Attention Network for Event-based Video Captioning Elaheh Barati (wayne state university); Xuewen Chen (AI-Ways)

P2C-05 Watch It Twice: Video Captioning with a Refocused Video Encoder Xiangxi Shi; Jianfei Cai; Shafiq Joty; Jiuxiang Gu —(Nanyang Technological University)

P2C-06 MvsGCN: A Novel Graph Convolutional Network for Multi-video Summarization Jiaxin Wu (Shenzhen university); Sheng-Hua Zhong (Shenzhen University); Yan Liu (The Hong Kong Polytechnic University, Hong Kong)

P2C-07 Stacked Memory Network for Video Summarization Junbo Wang (Institute of Automation Chinese Academy of Sciences); Wei Wang (Institute of Automation Chinese Academy of Sciences); Zhiyong Wang (The University of Sydney); Liang Wang (Institute of Automation Chinese Academy of Sciences); Dagan Feng (The University of Sydney); Tieniu Tan (Institute of Automation Chinese Academy of Sciences)

14:15 *P2C-08 Unpaired Cross-lingual Image Caption Generation with Self-Supervised Rewards Yuqing Song; Shizhe Chen; Yida Zhao; Qin Jin — (Renmin University of China)

14:30 *P2C-09 MUCH: Mutual Coupling Enhancement of Scene Recognition and Dense Captioning Xinhang Song (Institute ofomputing Technology, Chinese Academy of Sciences); Bohan Wang (ICT); Gongwei Chen (ICT); Shuqiang Jiang (ICTCAS)

14:45 P2C-10 Generative Reconstructive Hashing for Incomplete Video Analysis Jingyi Zhang (University of Electronic Science and Technology of China, UESTC); Zhen Wei (Institute of Information Engineering, the Chinese Academy of Sciences); Ionut Cosmin Duta (Inception Institute of Artificial Intelligence, United Arab Emirates); Fumin Shen (U. of Electronic Science and Technology of China, UESTC); Li Liu (Inception Institute of Artificial Intelligence, United Arab Emirates); Fan Zhu (Inception Institute of Artificial Intelligence, United Arab Emirates); Xing Xu (University of Electronic Science and Technology of China, UESTC); Ling Shao (Inception Institute of Artificial Intelligence, United Arab Emirates); Heng Tao Shen (University of Electronic Science and Technology of China, UESTC)

P2C-11 You Only Recognize Once: Towards Fast Video Text Spotting Zhanzhan Cheng (Zhejiang University); Jing Lu (Hikvision Research Institute); Yi Niu (Hikvision Research Institute); Shiliang Pu (Hikvision Research Institute); Fei Wu (Zhejiang University); Shuigeng Zhou (Fudan University)

P2C-12 Black-box Adversarial Attacks on Video Recognition Models Linxi Jiang (Fudan University); Xingjun Ma (The University of Melbourne); Shaoxiang Chen (Fudan University); James Bailey (The University of Melbourne); Yu-Gang Jiang (Fudan University and Jilian Technology Group)

P2C-13 Ranking Video Salient Object Detection Zheng Wang; Xinyu Yan; Yahong Han; Meijun Sun — (Tianjin University)

P2C-14 Video Retargeting: Trade-off between Content Preservation and Spatio-temporal Consistency Donghyeon Cho; Yunjae Jung); François Rameau; Dahun Kim; Sanghyun Woo; In So Kweon — (Korea Advanced Institute of Science and Technology, Republic of Korea)

  50/88

  

Session 2D: 3D Visual Processing Session Chair: Winston Hsu, National Taiwan University (Taiwan) Tuesday October 22 — Main Track — 13:30-15:00 — location Risso 6 13:30 *P2D-01 3D Point Cloud Geometry Compression on Deep Learning

Tianxin Huang; Yong Liu — (Zhejiang U.) 13:45 *P2D-02 Eye in the Sky: Drone-Based Object Tracking and 3D Localization

Haotian Zhang; Gaoang Wang; Zhichao Lei; Jenq-Neng Hwang — (U. of Washington) 14:00 P2D-03 Unsupervised Domain Adaptation for 3D Human Pose Estimation

Xiheng Zhang (Zhejiang U.); Yongkang Wong (National U. of Singapore); Mohan Kankanhalli (National U. of Singapore); Weidong Geng (Zhejiang U.)

P2D-04 DaNet: Decompose-and-aggregate Network for 3D Human Shape and Pose Estimation Hongwen Zhang (Institute of Automation, Chinese Academy of Sciences); Jie Cao (Institute of Automation, Chinese Academy of Sciences); Guo Lu (Shanghai Jiao Tong University); Wanli Ouyang (The University of Sydney); Zhenan Sun (Institute of Automation, Chinese Academy of Sciences)

P2D-05 3D Singing Head for Music VR: Learning External and Internal Articulatory Synchronicity from Lyric, Audio and Notes Jun Yu (U. of Science and Technology of China); Chang Wen Chen (The State U. of New York at Buffalo); Zengfu Wang (U. of Science and Technology of China)

P2D-06 Fine-grained Fitting Experience Prediction: A 3D-slicing Attention Approach Shan Huang (Tsinghua U.); Zhi Wang (Tsinghua U.); Laizhong Cui (Shenzhen U.); Yong Jiang (Tsinghua U.); Rui Gao (Epoque)

P2D-07 iDFusion: Globally Consistent Dense 3D Reconstruction from RGB-D and Inertial Measurements Dawei Zhong; Lei Han; Lu Fang — (Tsinghua-Berkeley Shenzhen Institute)

14:15 *P2D-08 MMJN: Multi-Modal Joint Networks for 3D Shape Recognition Weizhi Nie (Tianjin U.); Qi Liang (Tianjin U.); Anan Liu (Tianjin U.); Zhendong Mao (U. of Science and Technology of China); Yangyang Li (China Academy of Electronics and Information Technology)

14:30 *P2D-09 Monocular Visual Object 3D Localization in Road Scenes Yizhou Wang (U. of Washington); Yen-Ting Huang (Pervasive AI Research Labs); Jenq-Neng Hwang (U. of Washington)

14:45 P2D-10 Ground-Aware Point Cloud Semantic Segmentation for Autonomous Driving Jian Wu (U. of Science and Technology of China); Jianbo Jiao (U. of Oxford); Qingxiong Yang (MoonX.AI); Zheng-Jun Zha (U. of Science and Technology of China); Xuejin Chen (U. of Science and Technology of China)

P2D-11 SRINet: Learning Strictly Rotation-Invariant Representations for Point Cloud Classification and Segmentation Xiao Sun; Zhouhui Lian; Jianguo Xiao — (Peking U.)

P2D-12 L2G Auto-encoder: Understanding Point Clouds by Local-to-Global Reconstruction with Hierarchical Self-Attention Xinhai Liu (Tsinghua U.); Zhizhong Han (Tsinghua U.); Xin Wen (Tsinghua U.); Yu-Shen Liu (Tsinghua U.); Matthias Zwicker (U. of Maryland)

P2D-13 Self-supervised Representation Learning using 360° Data Junnan Li (National University of Singapore); Jianquan Liu (NEC Corporation); Yongkang Wong (National University of Singapore); Shoji Nishimura (NEC Corporation); Mohan Kankanhalli (National University of Singapore)

P2D-14 360-degree Video Gaze Behaviour: A Ground-Truth Data Set and a Classification Algorithm for Eye Movements Ioannis Agtzidis; Mikhail Startsev; Michael Dorr — (Technical U. of Munich)

  51/88

Demo Session 1 Tuesday October 22 — Main Track — 15:00-16:30 — location Galliéni 4

D1-01 BioTouchPass Demo: Handwritten Passwords for Touchscreen Biometrics Ruben Tolosana; Ruben Vera-Rodriguez; Julian Fierrez; Aythami Morales — (U. Autonoma de Madrid)

D1-02 Adapting Computer Vision Algorithms for Omnidirectional Video Hannes Fassold (Joanneum Research)

D1-03 Exquisitor: Breaking the Interaction Barrier for Exploration of 100 Million Images Hanna Ragnarsdóttir (Reykjavik U.); Þórhildur Þorleiksdóttir (Reykjavik U.); Omar Shahbaz Khan (IT U. of Copenhagen); Björn Þór Jónsson (IT U. of Copenhagen); Gylfi Þór Guðmundsson (Reykjavik U.); Jan Zahálka (Bohem.ai); Stevan Rudinac (U. of Amsterdam); Laurent Amsaleg (CNRS-IRISA); Marcel Worring (U. of Amsterdam)

D1-04 Documenting Physical Objects with Live Video and Object Detection Scott Carter; Laurent Denoue; Daniel Avrahami — (FX Palo Alto Laboratory)

D1-05 Split & Dual Screen Comparison of Classic vs Object-based Video Maarten Wijnants; Sven Coppers; Gustavo Rovelo; Peter Quax; Wim Lamotte — (Hasselt U.)

D1-06 CamaLeon: Smart Camera for Conferencing in the Wild Laurent Denoue; Scott Carter; Chelhwon Kim — (FX Palo Alto Laboratory)

D1-07 Personalized Video Summarization with Idiom Adaptation Yi Dong (Nanyang Technological U.); Chang Liu (Nanyang Technological U.); Zhiqi Shen (Nanyang Technological U.); Zhanning Gao (Alibaba Group); Pan Wang (Alibaba Group); Changgong Zhang (Alibaba Group); Peiran Ren (Alibaba Group); Xuansong Xie (Alibaba Group); Yu Han (Nanyang Technological U.)

D1-08 Tastalyzer: Audiovisual Exploration of Urban and Rural Variations in Music Taste Christine Bauer (Johannes Kepler U.); Markus Schedl (Johannes Kepler U.); Vera Angerer (Salzburg U. of Applied Sciences); Stefan Wegenkittl (Salzburg U. of Applied Sciences)

Demo Session 2 Tuesday October 22 — Main Track — 15:00-16:30 — location Galliéni 5 D2-01 Interactive Multi-Camera Soccer Video Analysis System

Yunjin Wu; Ziyuan Zhao ; Shengqiang Zhang; Lulu Yao; Yan Yang; Tom Z. J. Fu; Stefan Winkler — (U. of Illinois at Urbana-Champaign)

D2-02 Walker's Movie Map: Route View Synthesis Using Omni-directional Videos Naoki Sugimoto; Yuko Iinuma; Kiyoharu Aizawa — (U. of Tokyo)

D2-03 ACE: Art, Color, and Emotion Gjorgji Strezoski; Arumoy Shome; Riccardo Bianchi; Shruti Rao; Marcel Worring — (U. of Amsterdam)

D2-04 Development of an Acoustic AR Gamification System to Support Physical Exercise Takumi Kiriu (Kyoto Sangyo U.); Mohit Mittal (Kyoto Sangyo U.); Panote Siriaraya (Kyoto Institute of Technology); Yukiko Kawai (Kyoto Sangyo U. & Osaka U.); Shinsuke Nakajima (Kyoto Sangyo U.)

D2-05 Audio-Visual Variational Fusion for Multi-Person Tracking with Robots Xavier Alameda-Pineda; Soraya Arias; Yutong Ban; Guillaume Delorme; Laurent Girin; Radu Horaud; Xiaofei Li; Bastien Mourgue; Guillaume Sarrazin — (INRIA)

D2-06 BUDA.ART: A Multimodal Content Based Analysis and Retrieval System for Buddha Statues Benjamin Renoust; Matheus Oliveira Franca; Jacob Chan; Van Le; Ayaka Uesaka; Yuta Nakashima; Hajime Nagahara; Juereng Wang; Yutaka Fujioka — (Osaka U.)

D2-07 Fast Video Quality Enhancement Using GANs Leonardo Galteri; Lorenzo Seidenari; Marco Bertini; Tiberio Uricchio; Alberto Del Bimbo — (Universita' degli Studi di Firenze)

D2-08 Animating Your Life: Real-Time Video-to-Animation Translation Yang Chen (U. of Science and Technology of China); Yingwei Pan (JD AI Research); Ting Yao (JD AI Research); Xinmei Tian (U. of Science and Technology of China); Tao Mei (JD AI Research)

52/88

  

Poster Session 1 Session Chair: Zhengyu Zhao, Radboud University (Netherlands) Tuesday October 22 — Main Track — 15:00-16:30 — location Central Alley 15:00 Poster Session 1 — Period 1

During this period, the authors of the following contributions will be in front of their poster panel: ● posters for all papers in the Tuesday morning Sessions 1A, 1B, 1C, 1D ● posters for Best Papers

The authors of these papers will be standing in front of their poster board during this period. Posters will remain on display during the entire main conference.

15:45 Poster Session 1 — Period 2 During this period, the authors of the following contributions will be in front of their poster panel:

● posters for all papers in the Tuesday afternoon Sessions 2A, 2B, 2C, 2D The authors of these papers will be standing in front of their poster board during this period. Posters will remain on display during the entire main conference.

  53/88

  

Grand Challenge Posters Session Tuesday October 22 — 15:00-16:30 — location Central Alley

2019 iQIYI Celebrity Video Identification Challenge GC-01 ResidualDenseNetwork: A Simple Approach for Video Person Identification

Zixuan Huang; Yuan Chang; Weizhao Chen; Qiwei Shen; Jianxin Liao — (Beijing U. of Posts and Telecommunications)

GC-02 Make the Best of Face Clues in iQIYI Celebrity Video Identification Challenge 2019 Xi Fang; Ying Zou — (Shanghai Jiao Tong U.)

GC-03 DeepMEF: A Deep Model Ensemble Framework for Video Based Multi-modal Person Identification Chuanqi Dong; Zheng Gu; Zhonghao Huang; Wen Ji; Jing Huo; Yang Gao — (Nanjing U.)

GC-04 A Novel Deep Multi-modal Feature Fusion Method for Celebrity Video Identification Jianrong Chen; Li Yang; Yuanyuan Xu; Jing Huo; Yinghuan Shi; Yang Gao — (Nanjing U.)

GC-05 A Hierarchical Framework with Improved Loss for Large-scale Multi-modal Video Identification Shichuan Zhang; Zengming Tang; Hao Pan; Xinyu Wei; Jun Huang — (Shanghai Advanced Research Institute, Chinese Academy of Sciences)

GC-06 iQIYI Celebrity Video Identification Challenge Yuanliu Liu; Peipei Shi; Bo Peng; He Yan; Yong Zhou; Bing Han; Yi Zheng; Chao Lin; Jianbin Jiang; Yin Fan; Tingwei Gao; Ganwen Wang; Jian Liu; Xiangju Lu; Junhui Liu; Danming Xie — (iQiyi Inc.)

2019 Perfect Half Million Beauty Product Image Recognition Challenge

GC-07 Cross-domain Beauty Item Retrieval via Unsupervised Embedding Learning Zehang Lin (The Hong Kong Polytechnic U.); Haoran Xie (The Education U. of Hong Kong); Peipei Kang (Guangdong U. of Technology); Zhenguo Yang (Guangdong U. of Technology); Wenyin Liu (Guangdong U. of Technology); Qing Li (The Hong Kong Polytechnic U.)

GC-08 The Retrieval of the Beautiful: Self-Supervised Saliency Object Detection for Beauty Product Retrieval Jiawei Wang (CVTE); Shuai Zhu (CVTE); Jiao Xu (CVTE); Da Cao (Hunan U.)

GC-09 Beauty Product Retrieval Based on Regional Maximum Activation of Convolutions with Generalized Attention Jun Yu; Guochen Xie; Mengyan Li; Haonian Xie; Lingyun Yu — (U. of Science and Technology of China)

GC-10 Beauty Aware Network: An Unsupervised Method for Makeup Product Retrieval Yi Zhang; Linzi Qu; Lihuo He; Wen Lu; Xinbo Gao — (Xidian U.)

BioMedia

GC-11 ACM Multimedia BioMedia 2019 Grand Challenge Overview Steven Hicks (SimulaMet); Michael Riegler (SimulaMet); Pia Smedsrud (Augere Medical AS); Trine Haugen (OsloMet); Kristin Randheim Randel (Cancer Registry of Norway); Konstantin Pogorelov (Simula Research Laboratory); Håkon Kvale Stensland (Simula Research Laboratory); Duc-Tien Dang-Nguyen (U. of Bergen); Mathias Lux (U. of Klagenfurt); Andreas Petlund (Augere Medical AS); Thomas De Lange (U. of Oslo); Peter Thelin Schmidt (Karolinska Hospital); Pål Halvorsen (SimulaMet)

GC-12 Gastrointestinal Tract Diseases Detection with Deep Attention Neural Network Yuan Chang; Zixuan Huang; Weizhao Chen; Qiwei Shen — (Beijing U. of Posts and Telecommunications)

GC-13 Automatic Disease Detection and Report Generation for Gastrointestinal Tract Examination Philipp Harzig; Moritz Einfalt; Rainer Lienhart — (U. of Augsburg)

GC-14 Enhancing Endoscopic Image Classification with Symptom Localization and Data Augmentation Trung-Hieu Hoang (U. of Science, Vietnam National U.-Ho Chi Minh city); Hai-Dang Nguyen (EURECOM); Viet-Anh Nguyen (U. of Medicine and Pharmacy, Ho Chi Minh city); Thanh-An Nguyen(Japan Advanced Institute of Science and Technology); Vinh-Tiep Nguyen (U. of Science, HCM-VNU; John von Neumann Institute, VNU-HCM); Minh-Triet Tran (U. of Science, Vietnam National U. Ho Chi Minh city)

GC-15 Adaptive Ensemble:Solution to the Biomedia ACM MM Grand Challenge 2019

  54/88

  

Zhipeng Luo (DeepBlue Technology); Xiaowei Wang (DeepBlue Technology); Zhenyu Xu (DeepBlueTechnology); Xue Li (Microsoft); Jiadong Li (DeepBlue Technology)

GC-16 Biomedia ACM MM Grand Challenge 2019: Using Data Enhancement to Solve Sample Unbalance Wenhua Meng (ZhengZhou U.); Shan Zhang (Beijing union U.); Xudong Yao (Chinese Academy of Sciences); Xiaoshan Yang (Chinese Academy of Sciences); Changsheng Xu (Chinese Academy of Sciences)

Content-based video relevance prediction: Hulu

GC-17 BERT4SessRec: Content-Based Video Relevance Prediction with Bidirectional Encoder Representations from Transformer Xusong Chen (U. of Science and Technology of China); Dong Liu (U. of Science and Technology of China); Chenyi Lei (Ali Inc.); Rui Li (U. of Science and Technology of China); Zheng-Jun Zha (U. of Science and Technology of China); Zhiwei Xiong (U. of Science and Technology of China)

GC-18 Exploring Content-based Video Relevance for Video Click-Through Rate Prediction Xun Wang (Zhejiang Gongshang U.); Yali Du (U. of Technology); Leimin Zhang (Zhejiang Gongshang U.); Xirong Li (Renmin U. of China); Miao Zhang (Zhejiang U.); Jianfeng Dong (Zhejiang Gongshang U.)

GC-19 Content-Based Video Relevance Prediction with Multi-view Multi-level Deep Interest Network Zeyuan Chen; Kai Xu; Wei Zhang — (East China Normal U.)

GC-20 Cold-Start Representation Learning: A Recommendation Approach with Bert4Movie and Movie2vec Xinran Zhang (IBM); Xin Yuan (U. of Electronic Science and Technology of China); Yunwei Li (U. of Electronic Science and Technology of China); Yanru Zhang (U. of Electronic Science and Technology of China)

GC-21 Time-aware Session Embedding for Click-Through-Rate Prediction Qidi Xu (U. of Electronic Science and Technology of China); Haocheng Xu (U. of Electronic Science and Technology of China); Weilong Chen (U. of Electronic Science and Technology of China); Chaojun Han (U. of Electronic Science and Technology of China); Haoyang Li (SenseTime); Wenxin Tan (U. of Electronic Science and Technology of China); Fumin Shen (U. of Electronic Science and Technology of China); Heng Tao Shen (U. of Electronic Science and Technology of China)

GC-22 Overview of Content-based Click-Through Rate Prediction Challenge for Video Recommendation Peng Wang; Yunsheng Jiang; Chunxu Xu; Xiaohui Xie — (Hulu LLC.)

Live Video Streaming

GC-23 A Hybrid Control Scheme for Adaptive Live Streaming Huan Peng (Dept. of Information and Engineering, Communication U. of China); Yuan Zhang (Dept. of Information and Engineering, Communication U. of China); Yongbei Yang (Dept. of Information and Engineering, Communication U. of China); Jinyao Yan (New Media Institute, Communication U. of China)

GC-24 HD3: Distributed Dueling DQN with Discrete-Continuous Hybrid Action Spaces for Live Video Streaming Xiaolan Jiang (Dept. of Informatics, The Graduate U. for Advanced Studies); Yusheng Ji (Dept. of Informatics, The Graduate U. for Advanced Studies / National Institute of Informatics)

GC-25 Continuous Bitrate & Latency Control with Deep Reinforcement Learning for Live Video Streaming Ruying Hong; Qiwei Shen; Lei Zhang; Jing Wang — (Beijing U. of Posts and Telecommunications)

GC-26 BitLat: Bitrate-adaptivity and Latency-awareness Algorithm for Live Video Streaming Chen Wang; Jianfeng Guan; Tongtong Feng; Neng Zhang; Tengfei Cao — (Beijing U. of Posts and Telecommunications)

GC-27 Latency Aware Adaptive Video Streaming using Ensemble Deep Reinforcement Learning Yin Zhao; Qiwei Shen; Wei Li; Tong Xu; Weihua Niu; Siran Xu — (Beijing U. of Posts and Telecommunications; EBUPT Information Technology Company)

GC-28 The ACM Multimedia 2019 Live Video Streaming Grand Challenge Gang Yi (Tsinghua U.); Dan Yang (Beijing U. of Posts and Telecommunications); Abdelhak Bentaleb (National U. of Singapore); Weihua Li (PowerInfo); Yi Li (PowerInfo); Kai Zheng (HuaWei); Jiangchuan Liu (Simon Fraser U.); Wei Tsang Ooi (National U. of Singapore); Yong Cui (Tsinghua U.)

Relation Understanding in Videos

  55/88

  

GC-29 Video Visual Relation Detection via Multi-modal Feature Fusion Xu Sun; Tongwei Ren; Yuan Zi; Gangshan Wu — (Nanjing U.)

GC-30 Relation Understanding in Videos Sipeng Zheng; Xiangyu Chen; Qin Jin — (The Renmin U. of China)

GC-31 Relation Understanding in Videos: A Grand Challenge Overview Xindi Shang; Junbin Xiao; Donglin Di; Tat-Seng Chua — (National U. of Singapore)

SMP Challenge

GC-32 Feature Construction for Posts and Users Combined with LightGBM for Social Media Popularity Prediction Ziliang He (Guangdong U. of Technology); Zijian He (Xiamen U.); Jiahong Wu (Guangdong U. of Technology); Zhenguo Yang (Guangdong U. of Technology)

GC-33 Catboost-based Framework with Additional User Information for Social Media Popularity Prediction Peipei Kang (Guangdong U. of Technology); Zehang Lin (The Hong Kong Polytechnic U.); Shaohua Teng (Guangdong U. of Technology); Guipeng Zhang (Guangdong U. of Technology); Lingni Guo (Guangdong U. of Technology); Wei Zhang (Guangdong U. of Technology)

GC-34 Social Media Popularity Prediction: A Multiple Feature Fusion Approach with Deep Neural Networks Keyan Ding (City U. of Hong Kong); Ronggang Wang (Peking U.); Shiqi Wang (City U. of Hong Kong)

GC-35 Popularity Prediction of Social Media based on Multi-Modal Feature Mining Chih-Chung Hsu (Dept. of Management Information Systems, National Pingtung U. of Science and Technology); Li-Wei Kang (Dept. of Electrical Engineering, National Taiwan Normal U.); Chia-Yen Lee (Dept. of Electrical Engineering, National United U.); Jun-Yi Lee (Dept. of Management Information Systems, National Pingtung U. of Science and Technology); Zhong-Xuan Zhang (Dept. of Electrical Engineering, National United U.); Shao-Min Wu (Dept. of Management Information Systems, National Pingtung U. of Science and Technology)

GC-36 Social Media Popularity Prediction Based on Visual-Textual Features with XGBoost Junhong Chen; Dayong Liang; Zhanmo Zhu; Xiaojing Zhou; Zihan Ye; Xiuyun Mo — (Guangdong U. of Technology)

GC-37 SMP Challenge: An Overview of Social Media Prediction Challenge 2019 Bo Wu (Columbia U.); Wen-Huang Cheng (National Chiao Tung U.); Peiye Liu (Beijing U. of Posts and Telecommunications); Bei Liu (Microsoft); Zhaoyang Zeng (Sun Yat-sen U.); Jiebo Luo (U. of Rochester)

  56/88

  

ConfLab: Meet the Chairs! Speaker: Hayley Hung, Delft University of Technology Tuesday October 22 — 15:30-16:30 — location Rhodes 9 Are you interested in getting the most of ACM Multimedia 2019? Interested in learning more about how to leverage your network with the most influential members of the community? Interested in discussing new research ideas, starting new collaborations and making new scientific friendships? Then we invite you to participate in ConfLab: Meet the Chairs!, our very own conference living lab at ACM Multimedia 2019. This is a social gathering event where you get to meet the organisers of the Multimedia Conference and learn about the community values with leaders and peers. As part of the session, we will provide tips on how to leverage your network effectively. Participating in ConfLab:Meet the Chairs! involves donating your interaction data. This will be recorded by sensors and survey responses to create a large-scale shared community dataset that will allow us to analyze our networking patterns. To protect your privacy, your personal information is made available only to you and is anonymized by the research groups leading the experiments. We will also provide you with personal information about your data after the event. Are you a Diversity Diamond who interacts with researchers of a broad set of different research interests or a Focused Falcon, someone who interacts with researchers with just a few research interests? The science and technology behind ConfLab will be presented in depth at a tutorial on Friday 25 October. We encourage you to participate and join the debate. Come join us in helping to understand and shape the future of our community! This initiative is a collaborative venture of the Socially Perceptive Computing Lab led by Hayley Hung (Delft University of Technology, Netherlands) with close coordination and support from the ACM MM 2019 General Chairs.

  57/88

  

Best Paper Session Session Chair: Guillaume Gravier, CNRS-IRISA (France) Tuesday October 22 — Main Track — 16:30-18:00 — location Athéna

16:30 PB-01 Multi-modal Knowledge-aware Hierarchical Attention Network for Explainable Medical Question Answering Yingying Zhang (National Laboratory of Pattern Recognition, Institute of Automation, CAS;University of Chinese Academy of Sciences); Shengsheng Qian (National Laboratory of Pattern Recognition, Institute of Automation, CAS); Quan Fang (National Laboratory of Pattern Recognition, Institute of Automation, CAS); Changsheng Xu (National Laboratory of Pattern Recognition, Institute of Automation, CAS)

16:45 PB-02 Multimodal Dialog System: Generating Responses via Adaptive Decoders Liqiang Nie (Shandong University); Wenjie Wang (Shandong University); Richang Hong (Hefei University of Technology); Meng Wang (Hefei University of Technology); Qi Tian (Noah’s Ark Lab, Huawei)

17:00 PB-03 Audiovisual Zooming: What You See Is What You Hear Arun Asokan Nair (Johns Hopkins University, Snap Research); Austin Reiter (Snap Research); Changxi Zheng (Columbia University, Snap Research); Shree Nayar (Snap Research)

17:15 PB-04 Human-imperceptible Privacy Protection Against Machines Zhiqi Shen (National University of Singapore); Shaojing Fan (National University of Singapore); Yongkang Wong (National University of Singapore); Tiantsong Ng (InsiteAI, New Zealand); Mohan Kankanhalli (National University of Singapore)

17:30 PB-05 Flexible Online Multi-modal Hashing for Large-scale Multimedia Retrieval Xu Lu (Shandong Normal University); Lei Zhu (Shandong Normal University); Zhiyong Cheng (Shandong Artificial Intelligence Institute); Jingjing Li (University of Science and Technology of China); Xiushan Nie (Shandong University of Finance and Economics); Huaxiang Zhang (Shandong Normal University)

  58/88

  

ACM SIGMM Award for Outstanding Technical Contributions to Multimedia Computing, Communications and Applications

Speaker: Mubarak SHAH, University of Central Florida Session Chair: Alan Smeaton, Dublin City University (Ireland) Wednesday October 23 — 09:00-10:00 — location Athéna The 2019 winner of the prestigious ACM Special Interest Group on Multimedia (SIGMM) award for Outstanding Technical Contributions to Multimedia Computing, Communications and Applications is Professor Mubarak Shah. The award is given in recognition of his outstanding and pioneering and continued research contributions in the areas of multimedia content analysis and multimedia applications, for leadership in education, and for outstanding and continued service to the multimedia community.

  59/88

  

Session 3A: Multimodal QA & Content Generation Session Chair: Roger Zimmermann, National University of Singapore (Singapore) Wednesday October 23 — Main Track — 10:30-12:00 — location Athéna 10:30 *P3A-01 Hierarchical Graph Semantic Pooling Network for Multi-modal Community Question

Answer Matching Jun Hu (HeFei U. of Technology); Shengsheng Qian (Institute of Automation Chinese Academy of Sciences); Quan Fang (Institute of Automation Chinese Academy of Sciences); Changsheng Xu (Hefei U. of Technology, Institute of Automation Chinese Academy of Sciences)

10:45 *P3A-02 Learnable Aggregating Net with Divergent Loss for Video Question Answering Xiangpeng Li (U. of Electronic Science and Technology of China); Lianli Gao (U. of Electronic Science and Technology of China); Xuanhan Wang (U. of Electronic Science and Technology of China); Wu Liu (AI Research of JD.COM); Xing Xu (U. of Electronic Science and Technology of China); Jingkuan Song (U. of Electronic Science and Technology of China); Heng Tao Shen (U. of Electronic Science and Technology of China)

11:00 P3A-03 Multi-interaction Network with Object Relation for Video Question Answering Weike Jin (Zhejiang U.); Zhou Zhao (Zhejiang U.); Mao Gu (Zhejiang U.); Jun Yu (Hangzhou Dianzi U.); Jun Xiao (Zhejiang U.); Yueting Zhuang (Zhejiang U.)

P3A-04 CRA-Net: Composed Relation Attention Network for Visual Question Answering Liang Peng (U. of Electronic Science and Technology of China); Yang Yang (U. of Electronic Science and Technology of China); Zheng Wang (U. of Electronic Science and Technology of China); Xiao Wu (Southwest Jiaotong University); Zi Huang (The U. of Queensland)

P3A-05 Walking with MIND: Mental Imagery eNhanceD Embodied QA Juncheng Li; Siliang Tang; Fei Wu; Yueting Zhuang — (Zhejiang University)

P3A-06 Finding Images by Dialoguing with Image Lejian Ren (Chinese Academy of Sciences); Si Liu (Beihang U.); Han Huang (Beihang U.); Jizhong Han (Chinese Academy of Sciences); Shuicheng Yan (Qihoo/360); Bo Li (Beihang U.)

P3A-07 Exploiting Temporal Relationships in Video Moment Localization with Natural Language Songyang Zhang (U. of Rochester); Jinsong Su (Xiamen U.); Xin Jin (Huawei Technologies Co. Ltd.); Dandan Tu (Huawei Technologies Co. Ltd.); Jiebo Luo (U. of Rochester)

11:15 *P3A-08 Erasing-based Attention Learning for Visual Question Answering Fei Liu (National Lab of Pattern Recognition, Institute of Automation, Chinese Academy of Sciences); Jing Liu (National Lab of Pattern Recognition, Institute of Automation, Chinese Academy of Sciences); Richang Hong (School of Computer and Information, Hefei U. of Technology); Hanqing Lu (National Lab of Pattern Recognition, Institute of Automation, Chinese Academy of Sciences)

11:30 *P3A-09 Question-Aware Tube-Switch Network for Video Question Answering Tianhao Yang (U. of Science and Technology of China); Zheng-Jun Zha (U. of Science and Technology of China); Hongtao Xie (U. of Science and Technology of China); Meng Wang (Hefei University of U.); Hanwang Zhang (Nanyang Technological U.)

11:45 P3A-10 Cross-Modal Dual Learning for Sentence-to-Video Generation Yue Liu; Xin Wang; Yitian Yuan; Wenwu Zhu — (Tsinghua University)

P3A-11 Preserving Semantic and Temporal Consistency for Unpaired Video-to-Video Translation Kwanyong Park; Sanghyun Woo; Dahun Kim; Donghyeon Cho; In So Kweon — (Korea Advanced Institute of Science and Technology, Republic of Korea)

P3A-12 Referring Expression Comprehension with Semantic Visual Relationship and Word Mapping Chao Zhang (Samsung Research China, Beijing); Weiming Li (Samsung Research China, Beijing); Wanli Ouyang (The U. of Sydney); Qiang Wang (Samsung Research China, Beijing); Woo-Shik Kim (Samsung Advanced Institute of Technology, North Korea); Sunghoon Hong (Samsung Advanced Institute of Technology, North Korea)

P3A-13 SDIT: Scalable and Diverse Cross-domain Image Translation Yaxing Wang; Abel Gonzalez Garcia; Joost van de Weijer; Luis Herranz — (Computer Vision Center)

P3A-14 A Single-Shot Arbitrarily-Shaped Text Detector based on Context Attended Multi-Task Learning Pengfei Wang (Xidian University); Chengquan Zhang (Baidu Inc.); Fei Qi (Xidian University); Zuming Huang (Baidu Inc.); Mengyi En (Baidu Inc.); Junyu Han (Baidu Inc.); Jingtuo Liu (Baidu Inc.); Errui Ding (Baidu Inc.); Guangming Shi (Xidian University)

  60/88

  

Session 3B: Attention & Saliency Session Chair: Alan Hanjalic, Delft University of Technology (Netherlands) Wednesday October 23 — Main Track — 10:30-12:00 — location Hermès 10:30 *P3B-01 Aberrance-aware Gradient-sensitive Attentions for Scene Recognition with RGB-D

Videos Xinhang Song (Institute of Computing Technology, Chinese Academy of Sciences); Sixian Zhang (Institute of Computing Technology, Chinese Academy of Sciences); Yuyun Hua (BUAA); Shuqiang Jiang (Institute of Computing Technology, Chinese Academy of Sciences)

10:45 *P3B-02 An Attentional-LSTM for Improved Classification of Brain Activities Evoked by Images Shenghua Zhong; Ahmed Fares; Jianmin Jiang — (Shenzhen University)

11:00 P3B-03 Understanding the Teaching Styles by an Attention based Multi-task Cross-media Dimensional Modeling Suping Zhou (Tsinghua U.); Jia Jia (Tsinghua U.); Xiang Li (Tsinghua U.); Yufeng Yin (Tsinghua U.); Yang Yao (Tsinghua U.); Yin Zhang (Tsinghua U.); Zeyang Ye (Tsinghua U.); Kehua Lei (Tsinghua U.); Jialie Shen (Queen’s U. of Belfast)

P3B-04 Ingredient-Guided Cascaded Multi-Attention Network for Food Recognition Weiqing Min (Institute); Linhu Liu (Institute); Zhengdong Luo (Institute); Shuqiang Jiang (Institute)

P3B-05 Pedestrian Attribute Recognition via Hierarchical Multi-task Learning and Relationship Attention Lian Gao; Di Huang; Yuanfang Guo; Yunhong Wang — (Beihang U.)

P3B-06 Small and Dense Commodity Object Detection with Multi-Scale Receptive Field Attention Zhong Ji; Qiankun Kong; Haoran Wang; Yanwei Pang — (Tianjin U.)

P3B-07 What I See Is What You See: Joint Attention Learning for First and Third Person Video Co-analysis Huangyue Yu; Minjie Cai; Yunfei Liu; Feng Lu — (Beihang U.)

11:15 *P3B-08 Multi-Level Fusion based Class-aware Attention Model for Weakly Labeled Audio Tagging Yifang Yin (National U. of Singapore); Meng-Jiun Chiou (National U. of Singapore); Zhenguang Liu (Zhejiang Gongshang U.); Harsh Shrivastava (MIDAS Lab, IIITD); Rajiv Ratn Shah (IIIT-Delhi); Roger Zimmermann (National U. of Singapore)

11:30 *P3B-09 Fine-grained Cross-media Representation Learning with Deep Quantization Attention Network Meiyu Liang (Beijing U. of Posts and Telecommunications); Junping Du (Beijing U. of Posts and Telecommunications); Wu Liu (AI Research of JD.com); Zhe Xue (Beijing U. of Posts and Telecommunications); Yue Geng (Beijing U. of Posts and Telecommunications); Congxian Yang (Beijing U. of Posts and Telecommunications)

11:45 P3B-10 Impact of Saliency and Gaze Features on Visual Control: Gaze-Saliency Interest Estimator Souad Chaabouni; Frederic Precioso — (U. Côte d'Azur, CNRS, I3S)

P3B-11 A Unified Multiple Graph Learning and Convolutional Network Model for Co-saliency Estimation Bo Jiang (School of Computer Science and Technology, Anhui U.); Xingyue Jiang (Anhui U.); Ajian Zhou (Anhui U.); Jin Tang (Anhui U.); Bin Luo (Anhui U.)

P3B-12 SGDNet: An End-to-End Saliency-Guided Deep Neural Network for No-Reference Image Quality Assessment Sheng Yang (Nanyang Technological U.); Qiuping Jiang (Ningbo U.); Weisi Lin (Nanyang Technological U.); Yongtao Wang (Peking U.)

P3B-13 Co-saliency Detection Based on Hierarchical Consistency Bo Li; Sun Zhengxing; Quan Wang; Qian Li — (Department of Computer Science and Technology, Nanjing U.)

  61/88

  

Session 3C: Smart Applications Session Chair: Ichiro Ide, Nagoya University (Japan) Wednesday October 23 — Main Track — 10:30-12:00 — location Rhodes 9 10:30 *P3C-01 Inferring Mood Instability via Smartphone Sensing: A Multi-View Learning Approach

Xiao Zhang (Nanjing U.); Fuzhen Zhuang (Chinese Academy of Sciences); Wenzhong Li (Nanjing U.); Haochao Ying (Zhejiang U.); Hui Xiong (Rutgers U.); Sanglu Lu (Nanjing U.)

10:45 *P3C-02 Visual-Inertial State Estimation with Pre-integration Correction for Robust Mobile Augmented Reality Zikang Yuan (Huazhong U. of Science and Technology, School of Electronic Information and Communications); Dongfu Zhu (Huazhong U. of Science and Technology, School of Electronic Information and Communications); Cheng Chi (Huazhong U. of Science and Technology, School of Electronic Information and Communications); Jinhui Tang (Nanjing U. of Science and Technology, Dept. of Computer Science); Chunyuan Liao (HiScene Technology Ltd. Co); Xin Yang (Huazhong U. of Science and Technology, School of Electronic Information and Communications)

11:00 P3C-03 MMGCN: Multimodal Graph Convolution Network for Personalized Recommendation of Micro-video Yinwei Wei (Shandong U.); Xiang Wang (National U. of Singapore); Liqiang Nie (Shandong U.); Xiangnan He (U. of Science and Technology of China); Richang Hong (Hefei U. of Technology); Tat-Seng Chua (National U. of Singapore)

P3C-04 Personalized Hashtag Recommendation for Micro-videos Yinwei Wei (Shandong U.); Zhiyong Cheng (Shandong Artificial Intelligence Institute); Xuzheng Yu (Shandong U.); Zhou Zhao (Zhejiang U.); Lei Zhu (Shandong Normal U.); Liqiang Nie (Shandong U.)

P3C-05 Multimodal Classification of Urban Micro-Events Maarten Sukel; Stevan Rudinac; Marcel Worring — (U. of Amsterdam)

P3C-06 Routing Micro-videos via a Temporal Graph-guided Recommendation System Yongqi Li (Shandong U.); Meng Liu (Shandong U.); Jianhua Yin (Shandong U.); Chaoran Cui (Shandong U. of Finance and Economics); Xin-Shun Xu (Shandong U.); Liqiang Nie (Shandong U.)

P3C-07 Joint Rotation-Invariance Face Detection and Alignment with Angle-Sensitivity Cascaded Networks Bowen Yang; Chun Yang; Qi Liu; Xu-Cheng Yin — (Department of Computer Science and Technology, U. of Science and Technology Beijing)

11:15 *P3C-08 Close the Gap between Deep Learning and Mobile Intelligence by Incorporating Training in the Loop Cong Wang (Old Dominion U.); Yanru Xiao (Old Dominion U.); Xing Gao (U. of Memphis); Li Li (Chinese Academy of Sciences); Jun Wang (Futurewei Technologies)

11:30 *P3C-09 Towards Automatic Face-to-Face Translation Prajwal K R (Int. Institute of Information Technology, Hyderabad); Rudrabha Mukhopadhyay (Int. Institute of Information Technology, Hyderabad); Jerin Philip (Int. Institute of Information Technology, Hyderabad); Abhishek Jha (Int. Institute of Information Technology, Hyderabad); Vinay Namboodiri (Indian Institute of Technology, Kanpur); Jawahar C V (Int. Institute of Information Technology, Hyderabad)

11:45 P3C-10 See Through the Windshield from Surveillance Camera Images Daiqian Ma (Peking U.); Yan Bai (Peking U.); Renjie Wan (Nanyang Technological U.); Ce Wang (Peking U.); Boxin Shi (Peking U.); Lingyu Duan (Peking U.)

P3C-11 Exploring Background-bias for Anomaly Detection in Surveillance Videos) Kun Liu; Huadong Ma — (beijing U. of posts and telecommunications)

P3C-12 Editing Text in the Wild Liang Wu (Huazhong U. of Science and Technology); Chengquan Zhang (Baidu Inc.); Jiaming Liu (Baidu Inc.); Junyu Han (Baidu Inc.); Jingtuo Liu (Baidu Inc.); Errui Ding (Baidu Inc.); Xiang Bai (Huazhong U. of Science and Technology)

P3C-13 A Novel Two-stage Separable Deep Learning Framework for Practical Blind Watermarking Yang Liu; Mengxi Guo; Jian Zhang; Yuesheng Zhu; Xiaodong Xie — (Peking U.)

P3C-14 Towards a Perceptual Loss: Using a Neural Network Codec Approximation as a Loss for Generative Audio Models Ishwarya Ananthabhotla (Massachusetts Institute of Technology); Sebastian Ewert (Spotify); Joe Paradiso (Massachusetts Institute of Technology)

  62/88

  

Session 3D: Algorithms in Multimedia Session Chair: Xirong Li, Renmin University of China (China) Wednesday October 23 — Main Track — 10:30-12:00 — location Risso 6 10:30 *P3D-01 User Diverse Preference Modeling by Multimodal Attentive Metric Learning

Fan Liu (Shandong U.); Zhiyong Cheng (Shandong Artificial Intelligence Institute); Changchang Sun (Shandong U.); Yinglong Wang (Qilu U. of Technolog (Shandong Academy of Sciences)); Liqiang Nie (Shandong U.); Mohan Kankanhalli (National U. of Singapore)

10:45 *P3D-02 Deep Hashing by Discriminating Hard Examples Cheng Yan (Beihang U.); Guansong Pang (The U. of Adelaide); Xiao Bai (Beihang U.); Chunhua Shen (The U. of Adelaide); Jun Zhou (Griffith U.); Edwin Hancock (U. of York)

11:00 P3D-03 Supervised Discrete Hashing With Mutual Linear Regression Xingbo Liu (School of Computer Science and Technology, Shandong U.); Xiushan Nie (School of Computer Science and Technology, Shandong Jianzhu U.); Quan Zhou (School of Software, Shandong U.); Yilong Yin (School of Software, Shandong U.)

P3D-04 Robust Subspace Discovery by Block-diagonal Adaptive Locality-constrained Representation Zhao Zhang (Hefei U. of Technology); Jiahuan Ren (Soochow U.); Sheng Li (U. of Georgia); Richang Hong (Hefei U. of Technology); Zhengjun Zha (U. of Science and Technology of China); Meng Wang (Hefei U. of Technology)

P3D-05 Heterogeneous Domain Adaptation via Soft Transfer Network Yuan Yao (Harbin Institute of Technology); Yu Zhang (The Hong Kong U. of Science and Technology); Xutao Li (Harbin Institute of Technology); Yunming Ye (Harbin Institute of Technology)

P3D-06 Alleviating Feature Confusion for Generative Zero-shot Learning Jingjing Li (U. of Science and Technology of China); Mengmeng Jing (U. of Science and Technology of China); Ke Lu (U. of Science and Technology of China); Lei Zhu (Shandong Normal U.); Yang Yang (U. of Science and Technology of China); Zi Huang (The U. of Queensland)

P3D-07 Duet Robust Deep Subspace Clustering Yangbangyan Jiang (SKLOIS, Institute of Information Engineering, Chinese Academy of Sciences; SCS, U. of CAS); Qianqian Xu (Key Laboratory of Intelligent Information Processing, Institute of Computing Technology, Chinese Academy of Sciences); Zhiyong Yang (SKLOIS, Institute of Information Engineering, Chinese Academy of Sciences; SCS, U. of CAS); Xiaochun Cao (SKLOIS, Institute of Information Engineering, Chinese Academy of Sciences; SCS, U. of CAS); Qingming Huang (School of Computer Science and Technology, U. of Chinese Academy of Sciences)

11:15 *P3D-08 Watch, Reason and Code: Learning to Represent Videos Using Program Xuguang Duan (Tsinghua U.); Qi Wu (The U. of Adelaide); Chuang Gan (MIT-Watson AI Lab); Yiwei Zhang (Tsinghua U.); Wenbing Huang (Tencent AI Lab); Anton van den Hengel (The U. of Adelaide); Wenwu Zhu (Tsinghua U.)

11:30 *P3D-09 Super Resolution Using Dual Path Connections Bin-Cheng Yang (Nanjing U.)

11:45 P3D-10 Imbalance-aware Pairwise Constraint Propagation Hui Liu; Yuheng Jia; Junhui Hou; Qingfu Zhang — (City U. of Hong Kong)

P3D-11 Hybrid Image Enhancement With Progressive Laplacian Enhancing Unit Jie Huang; Zhiwei Xiong; Xueyang Fu; Dong Liu; Zhengjun Zha — (U. of Science and Technology of China)

P3D-12 Zero-Shot Restoration of Back-lit Images Using Deep Internal Learning Lin Zhang; Lijun Zhang; Xiao Liu; Ying Shen; Shaoming Zhang; Shengjie Zhao — (Tongji U.)

P3D-13 Kindling the Darkness: A Practical Low-light Image Enhancer Yonghua Zhang; Jiawan Zhang; Xiaojie Guo — (Tianjin U.)

P3D-14 TGG: Transferable Graph Generation for Zero-shot and Few-shot Learning Chenrui Zhang; Xiaoqing Lyu; Zhi Tang — (Peking U.)

  63/88

  

Doctoral Symposium Session Chair:

● Hervé Bredin, LIMSI, France ● Suzanne Little, Dublin City University, Ireland

Wednesday October 23 — 12:00-13:30 — location Galliéni 7 DS-01 Cross-modal Neural Sign Language Translation

Amanda Duarte (Universitat Politècnica de Catalunya) DS-02 On-Camera Digital Watermarking and its Application for Law Enforcement and Public

Safety Michael Kerr (Australian Criminal Intelligence Commission)

DS-03 On Quantizing the Mental Image of Concepts for Visual Semantic Analyses Marc Aurel Kastner (Nagoya University)

  64/88

  

Art Lunch Keynote — Inventing Narratives of the Anthropocene: Microclimate Machines and Arts & Sciences Installations

Speaker: Jean-Marc Chomaz, CNRS Session Chair: Martha Larson, Radboud University and TU Delft (Netherlands) Wednesday October 23 — 13:00-13:30 — location Central Space Since the creation of the Laboratoire d'Hydrodynamique (LadHyX) of the CNRS and the École Polytechnique, I have been involved as a researcher and artist in "arts & sciences" projects in all disciplines (circus, theatre, design, contemporary art, music, etc.). My approach tries to give direct access to an imaginary using scientific language and concepts not to demonstrate, but to make sense. The works I have created alone or jointly with other artists such as Ana Rewakowicz and Camille Duprat, Anaïs Tondeur, Aniara Rodado, the duets Evelina Domnitch Dmitry Gelfand, HeHe, or within the Labofactory collective founded with Laurent Karst and François-Eudes Chanfrault, are not intended to show or demonstrate scientific phenomena, to provide formal evidence or to reveal established facts. Rather, they suggest a different point of view, a destabilizing transgression, an uncomfortable comparison, a bodily experience, a metaphor for physics that would use the scientific imagination to reinvent our perception of the world and question the truth in its relativity and in all its fragility. These shared adventures have led me to realize that my intention is closely linked to deeper meaning and commitment. The human species, which, on a geological scale, should have remained an ephemeral and marginal event, is confronted with a deadly threat directly linked to its own action and its casual use, without verbalization and questioning, of science and technology. The fascination that science exerts on everyone's mind, starting with scientists themselves, remains extremely powerful, as evidenced by media coverage of the likely observation of the Higgs Boson or the black hole in the centre of the giant Messier 87 galaxy. Science therefore does not need to be re-invested but to be reinvested by humans, in order to allow new stories to emerge in thought and speech and to constitute a modern "song of gesture", entirely devoted to sustainable actions on a global scale and to the emergence of ethical paths of thought, generally accepted. Scientists are beginning to understand that science and the scientific approach itself may be powerless to solve or even grasp the reality and meaning of, for example, climate change or the new frontiers that today's questions of life and consciousness represent. Much of my scientific research and work combining art and science focuses on the question of climate change, and more specifically on how to predict, analyse and understand the scope, in the current state of knowledge, of the notion of the anthropocene; the controversial use of this term, which alone serves as a manifesto, calls into question the impact and ethics of mankind and requires a commitment both individually and collectively to define and build a new pact, an updated and shared new deal. Such global problems and challenges are beyond the realm of science alone, which is designed to divide a complex and sensitive problem into several small isolated systems, until it reaches a stage where the issue can be the subject of a laboratory experiment, computer study or modeling in a scientist's brain. Science was never designed to rebuild the fragile and complex system as a whole. We need a different protocol, another approach and a new analytical framework to address the challenges posed by the multiple, complex and transdisciplinary phenomena embedded in the concept of the anthropocene. Art and science encompass all the performances and narratives necessary for this confrontation, question our beliefs and observations, but also the nature, legitimacy and ethics of our scientific practice without the usual restrictions imposed on critical thinking by an almost sacred and therefore impossible to question protocol of proof. Once this judicious common vision has been constructed through art, scientific narratives and narratives resulting from the association of science with art, it should permeate all the actions of all individuals and communities and, secondarily, undoubtedly contribute to defining and attributing to science a more reasonable path to follow, or at the very least to bring back to it the possibility of critical thinking.

  65/88

  

Session 4A: Cross-Modal Retrieval Session Chair: Jialie Shen, Queen's University, Belfast (United Kingdom) Wednesday October 23 — Main Track — 13:30-15:00 — location Athéna 13:30 *P4A-01 Dual-level Embedding Alignment Network for 2D Image-Based 3D Object Retrieval

He-Yu Zhou; An-An Liu; Wei-Zhi Nie — (School of Electronic and Information Engineering,Tianjin U.)

13:45 *P4A-02 TC-Net for iSBIR: Triplet Classification Network for Instance-level Sketch Based Image Retrieval Hangyu Lin (School of Data Science, Fudan U.); Peng Lu (Department of Physics, Fudan U.); Yanwei Fu (School of Data Science, Fudan U.); Shaogang Gong (Queen Mary U. of London); Xiangyang Xue (Fudan U.); Yu-Gang Jiang (Fudan U. and Jilian Technology Group)

14:00 P4A-03 Learning Local Similarity with Spatial Relations for Object Retrieval Zhenfang Chen (The U. of Hong Kong); Zhanghui Kuang (Sensetime); Wei Zhang (SenseTime Group Limited); Kwan-Yee Kenenth Wong (The U. of Hong Kong)

P4A-04 Learning Disentangled Representation for Cross-Modal Retrieval with Deep Mutual Information Estimation Weikuo Guo (Dalian U. of Technology); Huaibo Huang (CASIA, Beijing); Xiangwei Kong (Zhejiang U.); Ran He (CASIA, Beijing)

P4A-05 Separated Variational Hashing Networks for Cross-Modal Retrieval Peng Hu (Sichuan U.); Xu Wang (Sichuan U.); Liangli Zhen (Institute of High Performance Computing, Agency for Science, Technology and Research); Dezhong Peng (Sichuan U.; Chengdu Sobey Digital Technology Co., Ltd.; Shenzhen Cyberspace Laboratory, China.)

P4A-06 Semi-supervised Deep Quantization for Cross-modal Search Xin Wang (Tsinghua U.); Wenwu Zhu (Tsinghua U.); Chenghao Liu (Singapore Management U.)

P4A-07 A New Benchmark and Approach for Fine-grained Cross-media Retrieval Xiangteng He; Yuxin Peng; Liu Xie — (Peking U.)

14:15 *P4A-08 Video-Based Cross-Modal Recipe Retrieval Da Cao (Hunan U.); Zhiwang Yu (Hunan U.); Hanling Zhang (Hunan U.); Jiansheng Fang (CVTE Research); Liqiang Nie (Shandong U.); Qi Tian (Noah’s Ark Lab, Huawei)

14:30 *P4A-09 A Two-step Cross-modal Hashing by Exploiting Label Correlations and Preserving Similarity in Both Steps Zhen-Duo Chen; Yongxin Wang; Hui-Qiong Li; Xin Luo; Liqiang Nie; Xin-Shun Xu — (Shandong U.)

14:45 P4A-10 Cross-Modal Image-Text Retrieval with Semantic Consistency Hui Chen (School of Software, Tsinghua U., Beijing); Guiguang Ding (School of Software, Tsinghua U., Beijing); Zijia Lin (Microsoft Research, Beijing); Sicheng Zhao (Department of Electrical Engineering and Computer Sciences, U. of California Berkeley); Jungong Han (School of Computing & Communications, Lancaster U.)

P4A-11 Annotation Efficient Cross-Modal Retrieval with Adversarial Attentive Alignment Po-Yao Huang (Carnegie Mellon U.); Guoliang Kang (U. of Technology, Sydney); Wenhe Liu (Carnegie Mellon U.); Xiaojun Chang (Monash U.); Alexander G. Hauptmann (Carnegie Mellon U.)

P4A-12 Towards Optimal CNN Descriptors for Large-Scale Image Retrieval Yinzheng Gu; Chuanpeng Li; Yu-Gang Jiang — (Jilian Technology Group)

P4A-13 A Framework for Effective Known-item Search in Video Jakub Lokoc (Charles U. in Prague); Tomáš Souček (Charles U. in Prague); Gregor Kovalcik (Charles U., Faculty of Mathematics and Physics); Jaroslav Moravec (Charles U. in Prague); Premysl Cech (Charles U. in Prague)

P4A-14 W2VV++: Fully Deep Learning for Ad-hoc Video Search Xirong Li (Renmin U. of China); Chaoxi Xu (Renmin U. of China); Gang Yang (renmin U. of China); Zhineng Chen (Institute of Automation, Chinese Academy of Sciences); Jianfeng Dong (Zhejiang U.)

  66/88

  

Session 4B: Visual Analysis & Applications Session Chair: Wen-Huang Cheng, National Chiao Tung University (Taiwan) Wednesday October 23 — Main Track — 13:30-15:00 — location Hermès 13:30 *P4B-01 Gradual Network for Single Image De-raining

Weijiang Yu (Sun Yat-sen U.); Zhe Huang (U. of Wisconsin-Madison); Litong Feng (Sensetime Group Limited); Wei Zhang (SenseTime Group Limited); Nong Xiao (Sun Yat-sen U.)

13:45 *P4B-02 AnoPCN: Video Anomaly Detection via Deep Predictive Coding Network Muchao Ye (South China U. of Technology); Xiaojiang Peng (Shenzhen Institutes of Advanced Technology, Chinese Academy of Sciences); Weihao Gan (SenseTime Group Limited); Wei Wu (SenseTime Group Limited); Yu Qiao (Shenzhen Institutes of Advanced Technology, Chinese Academy of Sciences)

14:00 P4B-03 DTDN: Dual-task De-raining Network Zheng Wang; Jianwu Li Ge Song — (School of Computer Science and Technology, Beijing Institute of Technology)

P4B-04 IntersectGAN: Learning Domain Intersection for Generating Images with Multiple Attributes Zehui Yao; Boyan Zhang; Zhiyong Wang; Wanli Ouyang; Dong Xu; Dagan Feng — (The U. of Sydney)

P4B-05 Weakly Supervised Fine-grained Image Classification via Correlation-guided Discriminative Learning Zhihui Wang (Dalian U. of Technology); Shijie Wang (Dalian U. of Technology); Pengbo Zhang (Dalian U. of Technology); Haojie Li (Dalian U. of Technology); Wei Zhong (Dalian U. of Technology); Jianjun Li (Hangzhou Dianzi U.)

P4B-06 Single-shot Semantic Image Inpainting with Densely Connected Generative Networks Ling Shen (Hefei U. of Technology); Richang Hong (Hefei U. of Technology); Haoran Zhang (Hefei U. of Technology); Hanwang Zhang (Nanyang Technological U.); Meng Wang (Hefei U. of Technology)

P4B-07 GAIN: Gradient Augmented Inpainting Network for Irregular Holes Jianfu Zhang (Shanghai Jiao Tong U.); Li Niu (Shanghai Jiao Tong U.); Dexin Yang (Shanghai Jiao Tong U.); Liwei Kang (Shanghai Jiao Tong U.); Yaoyi Li (Shanghai Jiao Tong U.); Weijie Zhao (Versa-AI); Liqing Zhang (Shanghai Jiao Tong U.)

14:15 *P4B-08 Single Image Deraining via Recurrent Hierarchy Enhancement Network Youzhao Yang; Hong Lu — (Fudan U.)

14:30 *P4B-09 DADNet: Dilated-Attention-Deformable ConvNet for Crowd Counting Dan Guo (Hefei U. of Technology); Kun Li (Hefei U. of Technology); Zheng-Jun Zha (U. of Science and Technology of China); Meng Wang (Hefei U. of Technology)

14:45 P4B-10 Deep Spatial Pyramid Features Collaborative Reconstruction for Partial Person Re-identification Zan Gao (Qilu U. of Technology (Shandong Academy of Sciences)); Li-Shuai Gao (Tianjin U. of Technology); Hua Zhang (Tianjin U. of Technology); Zhi-Yong Cheng (Qilu U. of Technology (Shandong Academy of Sciences)); Ri-Chang Hong (Hefei U. of Technology)

P4B-11 DoT-GNN: Domain-Transferred Graph Neural Network for Group Re-identification Ziling Huang (National Tsinghua U.); Zheng Wang (National Institute of Informatics); Wei Hu (Peking U.); Chia-Wen Lin (National Tsinghua U.); Shin'Ichi Satoh (National Institute of Informatics, The U. of Tokyo)

P4B-12 Improving the Learning of Multi-column Convolutional Neural Network for Crowd Counting Zhi-Qi Cheng (Southwest Jiaotong U.); Jun-Xiu Li (Southwest Jiaotong U.); Qi Dai (Microsoft); Xiao Wu (Southwest Jiaotong U.); Jun-Yan He (Southwest Jiaotong U.); Alexander Hauptmann (Carnegie Mellon U.)

P4B-13 Crowd Counting via Multi-layer Regression Xin Tan (Nanjing U.); Chun Tao (Nanjing Tech v); Tongwei Ren (Nanjing U.); Jinhui Tang (Nanjing University of Science and Technology); Gangshan Wu (Nanjing U.)

P4B-14 Gesture-to-Gesture Translation in the Wild via Category-Independent Conditional Maps Yahui Liu (University of Trento); Marco De Nadai (University of Trento); Gloria Zen (University of Trento); Nicu Sebe (University of Trento); Bruno Lepri (Fondazione Bruno Kessler)

  67/88

  

Session 4C: Social Computing & Image Processing Session Chair: Ewa Kijak, Univ Rennes-IRISA (France) Wednesday October 23 — Main Track — 13:30-15:00 — location Rhodes 9 13:30 *P4C-01 Seeking Micro-influencers for Brand Promotion

Tian Gan (Shandong University); Shaokun Wang (Shandong University); Meng Liu (Shandong University); Xumeng Song (Shandong University); Yiyang Yao (Northwestern Polytechnical University); Liqiang Nie (Shandong University)

13:45 *P4C-02 Multi-modal Knowledge-aware Event Memory Network for Social Media Rumor Detection Huaiwen Zhang; Quan Fang; Shengsheng Qian; Changsheng Xu — (National Laboratory of Pattern Recognition, Institute of Automation, Chinese Academy of Sciences)

14:00 P4C-03 User-Aware Folk Popularity Rank: User-Popularity-Based Tag Recommendation That Can Enhance Social Popularity Xueting Wang; Yiwei Zhang; Toshihiko Yamasaki — (The University of Tokyo)

P4C-04 Intrinsic Image Popularity Assessment Keyan Ding (City University of Hong Kong); Kede Ma (New York University); Shiqi Wang (City University of Hong Kong)

P4C-05 Vision-based Price Suggestion for Online Second-hand Items Liang Han; Zhaozheng Yin; Zhurong Xia; Li Guo; Mingqian Tang; Rong Jin — (Alibaba Group)

P4C-06 Instance of Interest Detection Fan Yu; Haonan Wang; Tongwei Ren; Jinhui Tang; Gangshan Wu — (Nanjing University)

P4C-07 On Learning Disentangled Representation for Acoustic Event Detection Lijian Gao (Jiangsu University); Qirong Mao (Jiangsu University); Ming Dong (Wayne State University); Yu Jing (Wayne State University); Ratna Chinnam (Wayne State University)

14:15 *P4C-08 MOC: Measuring the Originality of Courseware in Online Education Systems Jiawei Wang (CVTE Research); Jiansheng Fang (CVTE Research); Jiao Xu (CVTE Research); Shifeng Huang (CVTE Research); Da Cao (Hunan University); Ming Yang (CVTE Research)

14:30 *P4C-09 Audiovisual Transformer Architectures for Large-Scale Classification and Synchronization of Weakly Labeled Audio Events Wim Boes; Hugo Van Hamme — (Katholieke Universiteit Leuven)

14:45 P4C-10 Progressive Retinex: Mutually Reinforced Illumination-Noise Perception Network for Low-Light Image Enhancement Yang Wang (University of Science and Technology of China); Yang Cao (University of Science and Technology of China); Zheng-Jun Zha (University of Science and Technology of China); Jing Zhang (University Technology, Sydney); Zhiwei Xiong (University of Science and Technology of China); Wei Zhang (Shandong University); Feng Wu (University of Science and Technology of China)

P4C-11 Lightweight Image Super-Resolution with Information Multi-distillation Network Zheng Hui; Xinbo Gao; Yunchu Yang; Xiumei Wang — (Xidian University)

P4C-12 Deep Fusion Network for Image Completion Xin Hong (Institute of Computing Technology, Chinese Academy of Sciences); Pengfei Xiong (Megvii Technology); Renhe Ji (Megvii Technology); Haoqiang Fan (Megvii Technology)

P4C-13 Predicting Future Instance Segmentation with Contextual Pyramid ConvLSTMs Jiangxin Sun (Sun Yat-sen University); Jiafeng Xie (Sun Yat-sen University); Zihang Lin (Sun Yat-sen University); Jian-Fang Hu (Sun Yat-sen University); Wei-Shi Zheng (Sun Yat-sen University); Jianhuang Lai (Sun Yat-sen University); Wenjun Zeng (Microsoft)

P4C-14 Cycle In Cycle Generative Adversarial Networks for Keypoint-Guided Image Generation Hao Tang (University of Trento); Dan Xu (University of Oxford, United Kingdom); Gaowen Liu (Texas State University); Wei Wang (Ecole Polytechnique Fédérale de Lausanne); Yan Yan (Texas State University); Nicu Sebe (University of Trento)

  68/88

  

Session 4D: Embedding & Network Learning Session Chair: Xavier Alameda-Pineda, Inria (France) Wednesday October 23 — Main Track — 13:30-15:00 — location Risso 6 13:30 *P4D-01 Diachronic Cross-modal Embeddings

David Semedo; João Magalhaes — (U. NOVA de Lisboa) 13:45 *P4D-02 Domain-Specific Embedding Network for Zero-Shot Recognition

Shaobo Min (USTC); Hantao Yao (nlpr); Hongtao Xie (USTC); Zheng-Jun Zha (USTC); Yongdong Zhang (USTC)

14:00 P4D-03 Adaptive Semantic-Visual Tree for Hierarchical Embeddings Shuo Yang (Harbin Institute of Technology); Wei Yu (JD AI Research); Ying Zheng (Harbin Institute of Technology); Hongxun Yao (Harbin Institute of Technology); Tao Mei (JD AI Research)

P4D-04 Defending Against Adversarial Examples via Soft Decision Trees Embedding Yingying Hua (Chinese Academy of Sciences); Shiming Ge (Chinese Academy of Sciences); Xindi Gao (Chinese Academy of Sciences); Xin Jin (Beijing Electronic Science and Techinology Institute); Dan Zeng (Shanghai University)

P4D-05 Adaptive Feature Fusion via Graph Neural Network for Person Re-identification Yaoyu Li (Institute of Automation, Chinese Academy of Sciences; U. of Chinese Academy of Sciences); Hantao Yao (Institute of Automation, Chinese Academy of Sciences (CASIA)); Lingyu Duan (Peking U.); Hanxing Yao (Llvision Technology); Changsheng Xu (Institute of Automation, Chinese Academy of Sciences)

P4D-06 Learning Semantics-aware Distance Map with Semantics Layering Network for Amodal Instance Segmentation Ziheng Zhang; Anpei Chen; Ling Xie; Jingyi Yu; Shenghua Gao — (ShanghaiTech U.)

P4D-07 Open Set Deep Learning with a Bayesian Nonparametric Generative Model Xulun Ye; Jieyu Zhao — (Ningbo U.)

14:15 *P4D-08 Collaborative Preference Embedding against Sparse Labels Shilong Bao (SKLOIS, Institute of Information Engineering, Chinese Academy of Sciences; SCS, U. of CAS); Qianqian Xu (Key Laboratory of Intelligent Information Processing, Institute of Computing Technology, Chinese Academy of Sciences); Ke Ma (SKLOIS, Institute of Information Engineering, Chinese Academy of Sciences; SCS, U. of CAS); Zhiyong Yang (SKLOIS, Institute of Information Engineering, Chinese Academy of Sciences; SCS, U. of CAS); Xiaochun Cao (SKLOIS, Institute of Information Engineering, Chinese Academy of Sciences; SCS, U. of CAS); Qingming Huang (School of Computer Science and Technology, University of Chinese Academy of Sciences)

14:30 *P4D-09 Learning Fragment Self-Attention Embeddings for Image-Text Matching Yiling Wu (Institute of Computing Technology, U. of Chinese Academy of Sciences); Shuhui Wang (Institute of Computing Technology); Guoli Song (U. of Chinese Academy of Sciences); Qingming Huang (U. of Chinese Academy of Sciences)

14:45 P4D-10 Fast Non-Local Neural Networks with Spectral Residual Learning Lu Chi (Peking U.); Guiyu Tian (Peking U.); Yadong Mu (Peking U.); Lingxi Xie (Huawei); Qi Tian (Noah’s Ark Lab, Huawei)

P4D-11 Data Priming Network for Automatic Check-Out Congcong Li (U. of Chinese Academy of Sciences); Dawei Du (U. at Albany, State U. of New York); Libo Zhang (Institute of Software, Chinese Academy of Sciences); Tiejian Luo (U. of Chinese Academy of Sciences); Yanjun Wu (Institute of Software, Chinese Academy of Sciences); Qi Tian (Noah's Ark Lab, Huawei); Longyin Wen (JD Digits); Siwei Lyu (U. at Albany, State U. of New York)

P4D-12 Monocular Depth Estimation as Regression of Classification using Piled Residual Networks Wen Su (Faculty of Mechanical Engineering and Automation, Zhejiang Sci-Tech U.); Haifeng Zhang (U. of Science and Technology of China); Jia Li (U. of Science and Technology of China); Wenzhen Yang (Faculty of Mechanical Engineering and Automation, Zhejiang Sci-Tech U.); Zengfu Wang (U. of Science and Technology of China)

P4D-13 GroundNet: Monocular Ground Plane Normal Estimation with Geometric Consistency Yunze Man (Zhejiang U.); Xinshuo Weng (Carnegie Mellon U.); Xi Li (Zhejiang U.); Kris Kitani (Carnegie Mellon U.)

P4D-14 WealthAdapt: A General Network Adaptation Framework for Small Data Tasks Bingyan Liu; Yao Guo; Xiangqun Chen — (Peking University)

  69/88

  

Demo Session 3 Wednesday October 23 — Main Track — 15:00-16:30 — location Galliéni 4

D3-01 Market2Dish: A Health-aware Food Recommendation System Hao Jiang; Wenjie Wang; Meng Liu; Liqiang Nie; Ling-Yu Duan; Changsheng Xu — (Shandong U.)

D3-02 Remote VR Gaming on Mobile Devices Mikko Pitkänen; Marko Viitanen; Alexandre Mercat; Jarno Vanne — (Tampere University)

D3-03 Ultrasound-Based Silent Speech Interface using Sequential Convolutional Auto-encoder Kele Xu (National U. of Defense Technology); Yuxiang Wu (National U. of Defense Technology); Zhifeng Gao (Microsoft Research Asia)

D3-04 Interactive Exploration of Journalistic Video Footage through Multimodal Semantic Matching Sarah Ibrahimi (U. of Amsterdam); Shuo Chen (U. of Amsterdam); Devanshu Arya (U. of Amsterdam); Arthur Câmara (Delft U. of Technology); Yunlu Chen (U. of Amsterdam); Tanja Crijns (RTL Nederland); Maurits van der Goes (RTL Nederland); Thomas Mensink (Google Research); Emiel van Miltenburg (Tilburg U.); Daan Odijk (RTL Nederland); William Thong (U. of Amsterdam); Jiaojiao Zhao (U. of Amsterdam); Pascal Mettes (U. of Amsterdam)

D3-05 NeuronUnityIntegration2.0. A Unity Based Application for Motion Capture and Gesture Recognition Federico Becattini; Andrea Ferracani; Filippo Principi; Marioemanuele Ghianni; Alberto Del Bimbo — (Universita' degli Studi di Firenze)

D3-06 Real-Time Visual Navigation in Huge Image Sets Using Similarity Graphs Kai Uwe Barthel; Nico Hezel; Konstantin Schall; Klaus Jung — (HTW Berlin)

D3-07 A Real-Time Demo for Acoustic Event Classification in Ambient Assisted Living Contexts Arunodhayan Sampathkumar; Danny Kowerko; Rene Erler — (Chemnitz University of Technology)

D3-08 User-Adaptive Editing for 360 Degree Video Streaming with Deep Reinforcement Learning Lucile Sassatelli; Marco Winckler; Thomas Fisichella; Ramon Aparicio — (Université Cote d’Azur)

Demo Session 4 Wednesday October 23 — Main Track — 15:00-16:30 — location Galliéni 5 D4-01 OtonoVR: Arbitrarily Angled Audio-Visual VR Experience Using Selective Synthesis Sound

Field Technique Toshiharu Horiuchi; Sumaru Niida; Yasuhiro Takishima — (KDDI Research)

D4-02 Active Learning of Identity Agnostic Roles for Character Grounding in Videos Jiang Gao (Samsung Research)

D4-03 Ramen as You Like: Sketch-based Food Image Generation and Editing Jaehyeong Cho; Wataru Shimoda; Keiji Yanai — (The University of Electro-Communications)

D4-04 DeepPhysio: Monitored Physiotherapeutic Exercise in the Comfort of your Own Home Gianmarco Sanesi; Andrew Bagdanov; Marco Bertini; Alberto Del Bimbo — (Universita' degli Studi di Firenze)

D4-05 Using 3D Bookmarks for Desktop and Mobile DASH-3D Clients Thomas Forgione (U. of Toulouse); Axel Carlier (U. of Toulouse); Géraldine Morin (U. of Toulouse); Wei Tsang Ooi (National U. of Singapore); Vincent Charvillat (U. of Toulouse)

D4-06 Automatic Fashion Knowledge Extraction from Social Media Yunshan Ma; Lizi Liao; Tat-Seng Chua — (National University of Singapore)

D4-07 A Cooking Support System by Extracting Difficult Scenes for Cooking Operations from Recipe Short Videos Takuya Yonezawa (Kwansei Gakuin U.); Yuanyuan Wang (Yamaguchi U.); Yukiko Kawai (Kyoto Sangyo U. & Osaka U.); Kazutoshi Sumiya (Kwansei Gakuin U.)

D4-08 AI Coach: Deep Human Pose Estimation and Analysis for Personalized Athletic Training Assistance Jianbo Wang (Zhejiang U.); Kai Qiu (Microsoft); Houwen Peng (Microsoft); Jianlong Fu (Microsoft); Jianke Zhu (Zhejiang U.)

D4-09 Mind Band: Crossmedia AI Music Composing Platform Zhaolin Qiu; Yufan Ren; Canchen Li; Hongfu Liu; Yifan Huang; Yiheng Yang; Songruoyao Wu; Hanjia Zheng; Juntao Ji; Jianjia Yu; Kejun Zhang — (Zhejiang U.)

  70/88

  

Poster Session 2 Session Chair: Zhuoran Liu, Radboud University (Netherlands) Wednesday October 23 — Main Track — 15:00-16:30 — location Central Alley

15:00 Poster Session 2 — Period 1

During this period, the authors of the following contributions will be in front of their poster panel:

● Wednesday Sessions 3A, 3B, 3C, 3D, 4A, 4B, 4C, 4D ● posters for the Brave New Ideas papers ● posters for the Doctoral Symposium

The authors of these papers will be standing in front of their poster board during this period. Posters will remain on display during the entire main conference.

15:45 Poster Session 2 — Period 2

During this period, the authors of the following contributions will be in front of their poster panel:

● posters for all papers in the Thursday Sessions 5A, 5B, 5C, 5D ● posters for the Brave New Ideas papers ● posters for the Doctoral Symposium

The authors of these papers will be standing in front of their poster board during this period. Posters will remain on display during the entire main conference.

Reproducibility Posters Session Wednesday October 23 — 15:00-16:30 — location Central Alley

R-01 Using Mr. MAPP for Lower Limb Phantom Pain Management Kanchan Bahirat (The U. of Texas at Dallas); Yu-Yen Chung (The U. of Texas at Dallas); Thiru Annaswamy (VA North Texas Health Care System); Gargi Raval (VA North Texas Health Care System); Kevin Desai (The U. of Texas at Dallas); Balakrishnan Prabhakaran (The U. of Texas at Dallas); Michael Riegler (Simula Metropolitan Center for Digital Engineering)

R-02 Reproducible Experiments on Adaptive Discriminative Region Discovery for Scene Recognition Zhengyu Zhao (Radboud U.); Zhuoran Liu (Radboud U.); Martha Larson (Radboud U. and TU Delft); Naoko Nitta (Osaka University); Ahmet Iscen (Google Research)

R-03 On Reproducing Semi-dense Depth Map Reconstruction using Deep Convolutional Neural Networks with Perceptual Loss Ilya Makarov (National Research U. Higher School of Economics, Samsung-PDMI Joint AI Center); Dmitrii Maslov (National Research U. Higher School of Economics); Vladimir Aliev (National Research U. Higher School of Economics); Olga Gerasimova (National Research U. Higher School of Economics); Alisa Korinevskaya (National Research U. Higher School of Economics); Ujjwal Sharma (U. of Amsterdam); Haoliang Wang (Adobe research)

R-04 Companion Paper for "MiniView Layout for Bandwidth-Efficient 360-Degree Video" Mengbai Xiao (The Ohio State U.); Shuoqian Wang (SUNY Binghamton); Chao Zhou (SUNY Binghamton); Li Liu (George Mason U.); Zhenhua Li (Tsinghua U.); Yao Liu (SUNY Binghamton); Songqing Chen (George Mason U.); Lucile Sassatelli (U. Côte d'Azur, CNRS, I3S); Gwendal Simon (IMT Atlantique)

  71/88

  

Panel 1: Challenges for Multimedia/Multimodal Research in the Next Decade The multimedia and multimodal community is witnessing explosive transformations in the current era. These are evident in the huge growth of conferences, opportunities in both industry and research, and the emerging applications with major societal impact. With the unprecedented deployment of multimedia devices, processes, and systems, the role of multimedia research has become even more important than ever, influencing our abilities and prospects in advancing state-of-the-art technologies and solving real-world problems underlying various challenges facing the society and the nation in areas like global communication, security, environmental sustainability, health care, education, etc. To respond to these challenges and further advance the frontiers of the field of multimedia, this panel will discuss some key challenges and visions that may guide future research in the next ten years. The following 9 challenges which cut across-cutting many aspects of multimedia research will provide the starting point for the panel discussions:

● Multimodal Theory, Fusion, Representation and Alignment. ● Personalization. ● Knowledge Discovery and Reasoning. ● Transparency & Explicability, Interpretation and Visualization. ● Creation of High-quality Relevant Multimodal Datasets. ● Scalable Learning and Infrastructure. ● Data Privacy. ● Validity, Authenticity and Authoritativeness.

Moderator: Alexander Hauptmann, Carnegie Mellon University Speakers:

● Hayley Hung, Delft University of Technology ● Alberto Del Bimbo, University of Florence ● Heng Ji, University of Illinois at Urbana Champaign ● Cathal Gurrin, Dublin City University ● Klara Nahrstedt, University of Illinois at Urbana Champaign

Wednesday October 23 — 15:30-16:30 — location Rhodes 9

  72/88

  

Rising Star + Best Thesis Session Chairs:

● Marcel Worring, University of Amsterdam (Netherlands) ● Alan Smeaton, Dublin City University (Ireland)

Wednesday October 23 — Main Track — 16:30-18:00 — location Athéna

16:30 Rising Star Ting Yao (JD AI Research) is the recipient of the SIGMM 2019 Rising Star award.

He will present "Deep Video Understanding: Action Recognition and Language Generation".

With the proliferation of mobile devices and tremendous increase in Internet bandwidth, video data is being generated and spreading explosively. Such trend encourages the development of the recent advances in deep neural networks, which could facilitate a broad range of video understanding scenarios. This talk will summarize our innovative methodologies and insights on the challenges of recognizing actions in videos and describing a video with a natural-language utterance. Moreover, the talk will also discuss the reflection on what is likely to be the next set of developments in video understanding and what is likely to be the next big leap.

17:00 Best Thesis Abdelhak Bentaleb (National University of Singapore) is the recipient of the 2019 SIGMM Best Thesis award.

He will present "Enabling Optimizations of Video Delivery in HTTP Adaptive Streaming".

In shared network environments, providing a satisfactory viewer Quality-of-Experience (QoE) for multiple concurrent video players is an arduous task and becomes very critical. Despite a plethora of solutions towards better QoE, existing works have been designed for specific environments and have shown good performance under certain circumstances. Nonetheless, most of them have not succeeded in achieving an acceptable viewer QoE level required by today's applications. The key focus of this dissertation is to bridge the long-standing gap between the optimization of the viewers' QoE, video players' competition for the available bandwidth, and their growing bandwidth demand, with respect to group fairness and network conditions in the existing best-effort network infrastructure. To achieve this objective, this dissertation goes one step beyond existing client-driven solutions, by providing the design, implementation, and evaluation of a novel suite of Adaptive BitRate (ABR) related solutions where the goal is to avoid HAS scalability issues (quality instability, QoE unfairness, and network resource underutilization/oversubscription) while maximizing the viewers' QoE in a fair and efficient way.

  73/88

  

Thursday Keynote — EU Data Protection Law: An ally for scientific reproducibility?

Speaker: Mireille Hildebrandt, Vrije Universiteit, Brussels Session Chair: Benoit Huet, EURECOM (France) Thursday October 24 — 09:00-10:00 — location Athéna This keynote will introduce some of the key concepts of European data protection law, and clarify how and why this is not equivalent with privacy law. Next, I will explain why and how EU data protection law could enhance the methodological integrity of machine learning applications, also in the domain of multimedia. The question is, first, how the General Data Protection Regulation (GDPR) applies to inferences captured from multimedia data. This raises a number of questions. Does it matter whether such data has been made public by the person it relates to? Does processing personal data always require consent? What counts as valid consent? What if the inferences are mere statistics? What does the prohibition of processing ‘sensitive data’ (ethnicity, health) mean for multimedia analytics? This keynote will provide a crash course in the underlying ‘logic’ of the GDPR, with a focus on what is relevant for inferences based on multimedia content and metadata. I will uncover the purpose limitation principle as the guiding rationale of EU data protection law, protecting individuals against incorrect, unfair or unwarranted targeting. In the second part of the keynote I will explain how the purpose limitation principle relates to machine learning research design, requiring keen attention to specific aspects of methodological integrity. These may concern p-hacking, data dredging, or cherry picking performance metrics, and connect with the reproducibility crisis in machine learning that is on the verge of destroying the reliability of ML applications.

  74/88

Brave New Ideas Session Chair: Yiannis Kompatsiaris CERTH (Greece) Thursday October 24 — 10:30-12:00 — location Athéna

10:30 BNI-01 Neural Storyboard Artist: Visualizing Stories with Coherent Image Sequences Shizhe Chen (Renmin University of China); Bei Liu (Microsoft Research Asia); Jianlong Fu (Microsoft Research Asia); Ruihua Song (Microsoft XiaoIce); Qin Jin (Renmin University of China); Pingping Lin (Microsoft XiaoIce); Xiaoyu Qi (Microsoft XiaoIce); Chunting Wang (Beijing Film Academy); Jin Zhou (Beijing Film Academy)

10:20 BNI-02 HyperLearn: A Distributed Approach for Representation Learning in Datasets With Many Modalities Devanshu Arya (University of Amsterdam); Stevan Rudinac (University of Amsterdam); Marcel Worring (University of Amsterdam)

11:14 BNI-03 Moment-to-Moment Detection of Internal Thought during Video Viewing from Eye Vergence Behavior Michael Xuelin Huang (Max Planck Institute of Informatics); Jiajia Li (Τhe Hong Kong Polytechnic University); Grace Ngai (Τhe Hong Kong Polytechnic University); Hong Va Leong (The Hong Kong Polytechnic University); Andreas Bulling (University of Stuttgart)

11:36 BNI-04 Learning Subjective Attributes of Images from Auxiliary Sources Francesco Gelli (National University of Singapore); Tiberio Uricchio (Università degli Studi di Firenze); Xiangnan He (University of Science and Technology of China); Alberto Del Bimbo (Università degli Studi di Firenze); Tat-Seng Chua (National University of Singapore)

Sisters and Ambassadors: Conferences beyond ACM MM Session Chair: Gerald Friedland, University of California Berkeley (United States) Thursday October 24 — 10:30-12:00 — location Rhodes 9

This session provides a window on what is happening at other conferences of the SIGMM, as well as related conferences in other fields.

10:30 Diversification within SIGMM Alan Smeaton (Dublin City University)

10:40 MMSys’19 and MMSys’20 Wei Tsang Ooi (NUS); Cise Midoglu (Simula)

10:50 ACM International Conference on Multimedia Retrieval Abdulmotaleb El Saddik (University of Ottawa)

11:00 ● The recent trend on Fairness, Accountability and TransparencyXavier Alameda-Pineda (Inria)

● Age and gender bias in pedestrian detection algorithmsMartim Brandao (University of Oxford)

11:30 ● Multimedia meets CHISusanne Boll (University of Oldenburg)

● PicMe: Interactive Visual Guidance for Taking Requested PhotoComposition Minju Kim (Korea Advanced Institute of Science & Technology)

75/88

Open Source Software Competition Session Chair: Klaus Schoeffmann, Klagenfurt University (Austria) Thursday October 24 — 10:30-12:00 — location Risso 6

10:30 OS-01 daBNN: A Super Fast Inference Framework for Binary Neural Networks on ARM devices Jianhao Zhang (JD AI Research); Yingwei Pan (JD AI Research); Ting Yao (JD AI Research); He Zhao (JD AI Research); Tao Mei (JD AI Research)

10:45 OS-02 The VIA Annotation Software for Images, Audio and Video Abhishek Dutta (University of Oxford); Andrew Zisserman (University of Oxford)

11:00 OS-03 Shooter Localization Using Social Media Videos Junwei Liang (Carnegie Mellon University); Jay Aronson (Carnegie Mellon University); Alexander Hauptmann (Carnegie Mellon University)

11:15 OS-04 A Modern C++ Parallel Task Programming Library Chun-Xun Lin (University of Illinois at Urbana-Champaign); Tsung-Wei Huang (University of Illinois at Urbana-Champaign); Guannan Guo (University of Illinois at Urbana-Champaign); Martin Wong (University of Illinois at Urbana-Champaign)

11:30 OS-05 Docker-Based Evaluation Framework for Video Streaming QoE in Broadband Networks Cise Midoglu (Simula Research Laboratory); Anatoliy Zabrovskiy (Alpen-Adria-Universität Klagenfurt); Ozgu Alay (Simula Metropolitan Center for Digital Engineering); Daniel Hoelbling-Inzko (Bitmovin Inc); Carsten Griwodz (University of Oslo); Christian Timmerer (Alpen-Adria-Universität Klagenfurt)

11:45 OS-06 OpenVSLAM: A Versatile Visual SLAM Framework Shinya Sumikura (Nagoya University); Mikiya Shibuya (Nagoya University); Ken Sakurada (National Institute of Advanced Industrial Science and Technology (AIST))

Lunch break: SIGMM Business Meeting The meeting is open to all, where reports on SIGMM-sponsored conferences, workshops and other events are presented and activities planned for the future are presented and discussed.

Thursday October 24 — 12:00-13:30 — location Central Space

76/88

  

Session 5A: Summaries & Generation Session Chair: João Magalhaes, Universidade NOVA de Lisboa (Portugal) Thursday October 24 — Main Track — 13:30-15:00 — location Athéna 13:30 *P5A-01 Unsupervised Video Summarization with Attentive Conditional Generative

Adversarial Networks Xufeng He (Shanghai Jiao Tong U.); Yang Hua (Queen's U. Belfast); Tao Song (Shanghai Jiao Tong U.); Zongpu Zhang (Shanghai Jiao Tong U.); Zhengui Xue (Shanghai Jiao Tong U.); Ruhui Ma (Shanghai Jiao Tong U.); Neil Robertson (Queen's University Belfast); Haibing Guan (Shanghai Jiao Tong U.)

13:45 *P5A-02 Generating 1 Minute Summaries of Day Long Egocentric Videos Anuj Rathore (IIIT Hyderabad); Pravin Nagar (IIIT Delhi); Jawahar C.V. (IIIT Hyderabad); Chetan Arora (IIT Delhi)

14:00 *P5A-03 Informative Visual Storytelling with Cross-modal Rules Jiacheng Li; Haizhou Shi; Siliang Tang; Fei Wu; Yueting Zhuang — (Zhejiang University)

14:15 *P5A-04 LinesToFacePhoto: Face Photo Generation From Lines With Conditional Self-Attention Generative Adversarial Networks Yuhang Li; Xuejin Chen; Zheng-Jun Zha; Feng Wu — (U. of Science and Technology of China)

14:30 *P5A-05 Sentence Specified Dynamic Video Thumbnail Generation Yitian Yuan (Tsinghua-Berkeley Shenzhen Institute, Tsinghua U.); Lin Ma (Tencent AI Lab); Wenwu Zhu (Tsinghua U.)

14:45 *P5A-06 Curiosity-driven Reinforcement Learning for Diverse Visual Paragraph Generation Yadan Luo (The U. of Queensland); Zi Huang (The U. of Queensland); Zheng Zhang (The U. of Queensland); Ziwei Wang (The U. of Queensland); Jingjing Li (U. of Science and Technology of China); Yang Yang (U. of Science and Technology of China)

Session 5B: Quality of Experience & Interaction Session Chair: Lorenzo Seidenari, University of Florence (Italy) Thursday October 24 — Main Track — 13:30-15:00 — location Hermès 13:30 *P5B-01 Quality Assessment of In-the-Wild Videos

Dingquan Li (Peking U.); Tingting Jiang (Peking U.); Ming Jiang (Peking U.) Jia Li (Beihang U.); Kaiwen Yu (Beihang U.); Yifan Zhao (Beihang U.); Yu Zhang (Beihang U.); Long Xu (Chinese Academy of Sciences)

13:45 *P5B-02 Cross-Reference Stitching Quality Assessment for 360° Omnidirectional Images Jia Li (Beihang U.); Kaiwen Yu (Beihang U.); Yifan Zhao (Beihang U.); Yu Zhang (Beihang U.); Long Xu (Chinese Academy of Sciences)

14:00 *P5B-03 Generalized Playback Bar for Interactive Branched Video Eric Lindskog; Jesper Wrang; Madeleine Bäckström; Linn Hallonqvist; Niklas Carlsson — (Linkoping U.)

14:15 *P5B-04 360° Mulsemedia: A Way to Improve Subjective QoE in 360° Videos Alexandra Covaci (U. of Kent); Ramona Trestian (Middlesex U.); Estevao B Saleme (IFES); Ioan-Sorin Comsa (Brunel U.); Gebremariam Mesfin Assres (Addis Ababa U.); Celso Santos (U. Federal do Espírito Santo); Gheorghita Ghinea (Brunel U.)

14:30 *P5B-05 ViProVoQ: Towards a Vocabulary for Video Quality Assessment in the Context of Creative Video Production Simon Wedel (Ilmenau U. of Technology); Michael Koppetz (Arnold & Richter Cine Technik GmbH); Janto Skowronek (Ilmenau U. of Technology); Alexander Raake (Ilmenau U. of Technology)

14:45 *P5B-06 DeepQuantizedCS: Quantized Compressive Video Recovery using Deep Convolutional Networks Saurabh Kumar; Yagnesh Badiyani; Subhasis Chaudhuri — (IIT Bombay)

 

77/88

  

Session 5C: Transport & Delivery Session Chair: Yong Cui, Tsinghua University (China) Thursday October 24 — Main Track — 13:30-15:00 — location Rhodes 9 13:30 *P5C-01 Towards 6DoF HTTP Adaptive Streaming Through Point Cloud Compression

Jeroen van der Hooft (Ghent U.); Tim Wauters (Ghent U.); Filip De Turck (Ghent U.); Christian Timmerer (Alpen-Adria-Universität Klagenfurt); Hermann Hellwagner (Alpen-Adria-Universität Klagenfurt)

13:45 *P5C-02 Lossy Intermediate Deep Learning Feature Compression and Evaluation Zhuo Chen (Nanyang Technological U.); Kui Fan (Peking U.); Shiqi Wang (City U. of Hong Kong); Lingyu Duan (Peking U.); Weisi Lin (Nanyang Technological U.); Alex Kot (Nanyang Technological U.)

14:00 *P5C-03 Band and Quality Selection for Efficient Transmission of Hyperspectral Images Mohammad Amin Arab; Kiana Calagari; Mohamed Hefeeda — (Simon Fraser U.)

14:15 *P5C-04 PiTree: Practical Implementation of ABR Algorithms Using Decision Trees Zili Meng (Tsinghua U.); Jing Chen (Tsinghua U.); Yaning Guo (Tsinghua U.); Chen Sun (Tsinghua U.); Hongxin Hu (Clemson U.); Mingwei Xu (Tsinghua U.)

14:30 *P5C-05 AdaCompress: Adaptive Compression for Online Computer Vision Services Hongshan Li; Yu Guo; Zhi Wang; Shutao Xia; Wenwu Zhu — (Tsinghua U.)

14:45 *P5C-06 Talking Video Heads Maarten Wijnants (Hasselt U. tUL); Sven Coppers (Hasselt U. tUL); Gustavo Rovelo (Hasselt U. tUL); Peter Quax (Hasselt U. tUL Flanders Make); Wim Lamotte (Hasselt U. tUL)

Session 5D: Art & Culture Session Chair: Jia Jia, Tsinghua University (China) Thursday October 24 — Main Track — 13:30-15:00 — location Risso 6

13:30 *P5D-01 Recognizing the Style of Visual Arts via Adaptive Cross-layer Correlation Liyi Chen; Jufeng Yang — (Nankai University)

13:45 *P5D-02 Melody Slot Machine: A Controllable Holographic Virtual Performer Masatoshi Hamanaka (RIKEN)

14:00 *P5D-03 Generating Captions for Images of Ancient Artworks Shurong Sheng; Marie-Francine Moens — (Katholieke Universiteit Leuven)

14:15 *P5D-04 GP-GAN: Towards Realistic High-Resolution Image Blending Huikai Wu (CASIA); Shuai Zheng (U. of Oxford); Junge Zhang (CASIA); Kaiqi Huang (CASIA)

14:30 *P5D-05 Progressive Image Inpainting with Full-Resolution Residual Network Zongyu Guo; Zhibo Chen; Tao Yu; Jiale Chen; Sen Liu — (University of Science and Technology of China)

14:45 *P5D-06 Facial Image-to-Video Translation by a Hidden Affine Transformation Guangyao Shen (Tsinghua U.); Wenbing Huang (Tencent AI Lab); Chuang Gan (MIT-Watson AI Lab); Mingkui Tan (South China U. of Technology); Junzhou Huang (Tencent AI Lab); Wenwu Zhu (Tsinghua U.); Boqing Gong (Tencent AI Lab)

  78/88

  

Panel 2: Legal and Ethical Challenges in Multimedia Research Multimedia research has now moved beyond laboratory experiments and is rapidly being deployed in real-life applications including advertisements, social interaction, search, security, automated driving, and healthcare. Hence, the developed algorithms now have a direct impact on the individuals using the abovementioned services and the society as a whole. While there is a huge potential to benefit the society using such technologies, there is also an urgent need to identify the checks and balances to ensure that the impact of such technologies is ethical and positive. This panel will bring together an array of experts who have experience collecting large-scale datasets, building multimedia algorithms, and deploying them in practical applications, as well as, a lawyer whose eyes have been on the fundamental rights at stake. They will lead a discussion on the ethics and lawfulness of dataset creation, licensing, privacy of individuals represented in the datasets, algorithmic transparency, algorithmic bias, explainability, and the implications of application deployment. Through an interactive process engaging the audience, the panel hopes to: increase the awareness of such concepts in the multimedia research community; initiate a discussion on community guidelines all for setting the future direction of conducting multimedia research in a lawful and ethical manner. Moderator: Vivek Singh, Rutgers University Panelists:

● Susanne Boll, University of Oldenburg ● David A. Shamma, FXPAL ● Mireille Hildebrandt, Vrije Universiteit Brussels ● Elisabeth André, Augsburg University

Thursday October 24 — 15:30-16:30 — location Athéna

Grand Challenge During this session, each Grand Challenge will present a short overview, followed by presentations of the Grand Challenge Finalists. The winners will be announced at the end of the session. The Grand Challenge posters were presented on Tuesday (15:00—16:30). Thursday October 24 — 16:30-18:00 — location Athéna

  79/88

  

Workshop 7: MMSports — Multimedia Content Analysis in Sports

Abstract: The second ACM International Workshop on Multimedia Content Analysis in Sports (ACM MMSports’19) is held in Nice, France on October 25th, 2019 co-located with the ACM International Conference on Multimedia 2019 (ACM Multimedia 2019). The goal of this workshop is to bring together researchers and practitioners from academia and industry to address challenges and report progress in mining, analyzing, understanding and visualizing the multimedia/multimodal data in sports. The combination of sports and modern technology offers a novel and intriguing field of research with promising approaches for visual broadcast augmentation, understanding, statistical analysis and evaluation, and sensor fusion. There is a lack of research communities focusing on the fusion of multiple modalities. We are helping to close this research gap with this workshop series on multimedia content analysis in sports.

Organizers:

● Rainer Lienhart, University of Augsburg ● Hideo Saito, Keio University ● Thomas Moeslund, Aalborg University

Friday October 25 — Full day workshop — 09:00-17:30 — location Risso 6

09:00 Video-based Analysis of Soccer Matches Maximilian T. Fischer, Daniel A. Keim and Manuel Stein (University of Konstanz) 09:23 Retrieval of Similar Scenes Based on Multimodal Distance Metric Learning in Soccer

Videos Tomoki Haruyama, Sho Takahashi, Takahiro Ogawa and Miki Haseyama (Hokkaido University) 09:50 A Deep Architecture for Multimodal Summarization of Soccer Games Melissa Sanabria, Sherly, Frédéric Precioso and Thomas Menguy (Université Côte d’Azur,

CNRS, I3S) 10:13 "Does 4-4-2 exist?" - An Analytics Approach to Understand and Classify Football Team

Formations in Single Match Situations Eric Müller-Budack, Jonas Theiner, Robert Rein and Ralph Ewerth (Leibniz Information Centre

for Science and Technology (TIB)) 10:30 Refreshments (Central Space) 11:00 Keynote: Image-based Motion Capture and Analysis Systems for Movement and Behavior

Analysis Philipp Russ (Simi Reality Motion Systems) 11:45 Combining Qualitative and Quantitative Analysis in Football with SportSense Philipp Seidenschwarz, Adalsteinn Jonsson, Fabian Rauschenbach, Martin Rumo, Lukas Probst

and Heiko Schuldt (University of Basel) 12:08 Frame-level Event Detection in Athletics Videos with Pose-based Convolutional Sequence

Networks Moritz Einfalt, Charles Dampeyrou, Dan Zecha and Rainer Lienhart (University of Augsburg) 12:30 Lunch (Central Space) 14:00 Real-time CNN-based Segmentation Architecture for Ball Detection in a Single View Setup Gabriel Van Zandycke and Christophe de Vleeschouwer (Catholic U of Louvain) 14:23 Prediction of Future Shot Direction Using Pose and Position of Tennis Player Tomohiro Shimizu, Ryo Hachiuma, Hideo Saito, Takashi Yoshikawa and Chonho Lee (Keio

University) 14:45 Tracking Jockeys in a Cluttered Environment with Group Dynamics Mohammad Hedayati, Michael Cree and Jonathan Scott (University of Waikato) 15:08 Empirical Analysis of Pacing in Road Cycling Dietmar Saupe, Alexander Artiga Gonzalez, Ramona Burger and Chris Abbiss (University of

Konstanz) 15:30 Refreshments (Central Space) 16:00 Running Event Visualization Using Videos from Multiple Cameras

  80/88

  

Yeshwanth Napolean, Priadi Teguh Wibowo and Jan van Gemert (Delft University of Technology)16:23 Detection of Tennis Events from Acoustic Data Aaron Baughman, Eduardo Morales, Gary Reiss, Nancy Greco, Stephen Hammer and Shiqiang

Wang (IBM) 16:45 Spectator Excitement Detection in Small-scale Sports Events Kazuhiro Abe, Chikara Nakamura, Yosuke Otsubo, Tetsuya Koike and Naoto Yokoya (Nikon

Corporation) 17:08 Flexible Automatic Football Filming and Summarization Francesco Turchini, Lorenzo Seidenari, Leonardo Galteri, Andrea Ferracani, Giuseppe Becchi

and Alberto Del Bimbo (University of Florence)

  81/88

  

Workshop 8: FAT/MM — Fairness, Accountability, and Transparency in MultiMedia

Abstract: The series of FAT* events aim at bringing together researchers and practitioners interested in fairness, accountability, and transparency of computational methods. The FAT/MM workshop focuses on addressing these issues in the Multimedia field. Multimedia computing technologies operate today at an unprecedented scale, with a growing community of scientists interested in multimedia models, tools and applications. Such continued growth has great implications not only for the scientific community, but also for the society as a whole. Typical risks of large-scale computational models include model bias and algorithmic discrimination. These risks become particularly prominent in the multimedia field, which historically has been focusing on user-centered technologies. To ensure a healthy and constructive development of the best multimedia technologies, this workshop offers a space to discuss how to develop fair, unbiased, representative, and transparent multimedia models, bringing together researchers from different areas to present computational solutions to these issues.

Organizers:

● Xavier Alameda-Pineda, Inria ● Elisa Celis, Yale University ● Shih-Fu Chang, Columbia University ● Miriam Redi, Wikimedia Foundation ● Nicu Sebe, Huawei Ireland/University of Trento

Friday October 25 — Half day workshop — 09:00-12:30 — location Galliéni 4

09:00 Invited talk: Deep Learning for Video Retrieval by Natural Language Xirong Li, Renmin University of China 09:45 Oral #1: Learning Facial Recognition Biases through VAE Latent Representations Meghana Rao, Diego Celis, Stanford University 10:00 Oral #2: QoE-fair Resource Allocation for DASH Video Delivery Systems Luca de Cicco, Politecnico di Bari 10:15 Invited Oral: Bias, Discrimination and Fairness Issues in Robotics Martim Brandao, Oxford University 10:30 Refreshments (Central Space) 11:00 Invited talk: Fairness in Algorithmic and Crowd-Generated Descriptions of People Images Jahna Otterbacher, Open University of Cyprus 11:40 Oral #3: Social Multimedia, Diversity, and Global South Cities: A Double Blind Side Thanh-Trung Phan, IDIAP Research Institute 11:55 Oral #4: A Software Defined Network Based Research on Fairness in Multimedia Ahmed O Basil, University of Northampton 12:10 Oral #5: Toward Fairness in Face Matching Algorithms Vivek K. K Singh, Rutgers University

  82/88

  

Workshop 9: MULEA — Multimodal Understanding and Learning for Embodied Applications

Abstract: The First International Workshop on Multimodal Understanding and Learning for Embodied Applications is held in Nice, France, in conjunction with ACM Multimedia 2019. Embodied applications require the learning and knowledge discovery process involving an agent, the environment, and actions, as well as the understanding and grounding of multiple modalities of input signals. Being one of the frontiers in AI research, it covers many of the applications in AI, such as robotics, autonomous driving, multimodal chatbots, or simulated games. The Workshop brings an exciting program with invited speeches, original research papers, and lively discussions on this new and exciting research area.

Organizers:

● Jiang (John) Gao, Samsung Research America ● Jia-Yu (Tim) Pan, Google, Inc, Mountain View

Friday October 25 — Full day workshop — 09:00-17:30 — location Galliéni 5

09:00 Workshop opening and welcome Jiang Gao and Jia-Yu Pan (Samsung Research America, Google Inc.) 09:15 Keynote: Connecting Language and Vision: From Captioning towards Embodied Learning Subhashini Venugopalan (Google, Inc.) 10:10 Geometry-aware Relational Exemplar Attention for Dense Captioning Tzu-Jui Julius Wang, Hamed Rezazadegan Tavakoli, Mats Sjöberg, Jorma Laaksonen (Aalto

University, Nokia Technologies, CSC – IT Center for Science Ltd.) 10:30 Refreshments (Central Space) 11:00 Deep Reinforcement Learning Visual-text Attention for Multimodal Video Classification Mengyi Liu and Zhu Liu (Alibaba Group) 11:20 Keynote: On the Multisensory Nature of Objects and Language: A Robotics Perspective Jivko Sinapov (Tufts University) 12:15 Poster Blitz Session (4 posters, 3 minutes each) and Setup 12:30 Lunch (Central Space) 14:00 Keynote: Learning to Navigate Piotr Mirowski (DeepMind) 14:55 Visually Grounded Language Learning for Robot Navigation Emre Unal, Ozan Arkan Can, Yucel Yemez (Koc University) 15:15 Clustering Optimization for Abnormality Detection in Semi-autonomous Systems Hafsa Iqbal, Damian Campo, Mohamad Baydoun, Lucio Marcenaro, David Martin Gomez, Carlo

Regazzoni (University of Genova and University of Madrid) 15:35 Refreshments (Central Space) 16:00 Wrap up, next steps and closing Jiang Gao and Jia-Yu Pan (Samsung Research America, Google Inc.) 16:15 Poster Session continues

  83/88

  

Workshop 10: MAHCI — Multimedia for Accessible Human Computer Interfaces

Abstract: Multimedia technology plays a fundamental role to increase usability, and accessibility of computer interfaces in developing advanced human-computer interaction devices. The 2nd workshop on Multimedia for Accessible Human Computer Interface (MAHCI) continues to provide a forum to both multimedia and HCI researchers to discuss the accessible human computer interface design, development, and evaluation with state-of-the-art multimedia technology. It also enables multimedia community to expand its interaction with the HCI industry and broaden the scope of deploying multimedia technology in practical applications. The workshop features 6 papers which cover a number of novel applications and new methodologies in a half day program.

Organizers:

● Xueliang Liu, Hefei University of Technology ● Troy McDaniel, Arizona State University ● Rui Min, Google

Friday October 25 — Half day workshop — 14:00-17:30 — location Galliéni 4

14:00 Welcome and Introduction by the organizer Xueliang Liu (Hefei University of Technology), Rui Min (Google), Troy McDaniel (Arizona State

University,USA) 14:10 Meeting the Digital Twin: Multimedia Convergence for Citizens’ Well-being Abdulmotaleb El Saddik (University of Ottawa) 15:10 HaptWrap: Augmenting Non-visual Travel via Visual-to-tactile Mapping of Objects in

Motion Bryan Duarte (Arizona State University); Troy L. McDaniel (Arizona State University); Abhik

Chowdhury (Arizona State University); Sana Gill (Arizona State University); Panchanathan Sethuraman (Arizona State University)

15:30 Refreshments (Central Space) 16:00 Emotion Recognition with Simulated Phosphene Vision Caroline J.M. Bollen (Radboud University); Richard van Wezel (Radboud University); Marcel van

Gerven (Radboud University); Yağmur Güçlütürk (Radboud University) 16:15 Continuous Sign Language Recognition Based on Pseudo-supervised Learning Xiankun Pei (Hefei University of Technology); Dan Guo (Hefei University of Technology); Ye

Zhao (Hefei University of Technology) 16:30 Gaze Detection and Prediction Using Data from Infrared Cameras Yingxuan Zhu (Futurewei Technologies) 16:45 Semantic Enhanced Encoder-decoder Network (SEN) for Video Captioning YuLing Gui (Hefei University of Technology); Dan Guo (Hefei University of Technology); Ye Zhao

(Hefei University of Technology) 17:00 A Refreshable Tactile Display Effectively Supports Cognitive Mapping Followed by

Orientation and Mobility Tasks Luca Brayda (Fondazione Istituto Italiano di Tecnologia); Fabrizio Leo (Fondazione Istituto

Italiano di Tecnologia); Caterina Baccelliere (Fondazione Istituto Italiano di Tecnologia); Claudia Vigini (Istituto Chiossone onlus); Elena Cocchi (Istituto Chiossone onlus)

  84/88

  

Tutorial 5: Reproducibility and Experimental Design for Machine Learning on Audio and Multimedia Data Abstract: This tutorial provides an actionable perspective on the experimental design for machine learning experiments on multimedia data. The tutorial consists of lectures and hands-on exercises. The lectures provide a theoretical introduction to machine learning design and signal processing. The thought framework presented is derived from the traditional experimental sciences which require published results to be self-contained with regards to reproducibility. In the practical exercises, we will work on calculating and measuring quantities like capacity or generalization ratio for different machine learners and data sets and discuss how these quantities relate to reproducible experimental design. Please bring paper, pencil, and a laptop. The tutorial is based on a UC Berkeley graduate class Speaker: Gerald Friedland, University of California, Berkeley & Lawrence Livermore National Lab Friday October 25 — Half day workshop — 09:00-12:30 — location Rhodes 9

Tutorial 6: Principle to Program: Neural Fashion Recommendation with Multimodal Input Abstract: Outfit recommendation automatically pairs user-specified reference clothing with the most suitable complement from online shops. Aesthetic combination is a criterion for matching such fashion items. Fashion style tells a lot about one's personality and emerges from how people assemble clothing outfit from seemingly disjoint items into a cohesive concept. Experts share fashion tips showcasing their compositions to public where each item has both an image and textual metadata though. Also, retrieving products from online shopping catalogs in response to such real-world image query is essential for outfit recommendation. We cover style and compatibility in fashion recommendation - building on metric and deep learning approaches introduced elsewhere. We present in addition visual signals more broadly (e.g., cross-scenario retrieval, attribute classification) and combine text input (e.g., interpretable embedding) as well. Each section concludes walking through programs executed on Jupyter workstation using real-world datasets. We would like to offer opportunity to execute code fragments from the original authors of a few of the papers covered in our session. If you are interested in taking advantage of this opportunity, please bring your laptop. Speakers:

● Muthusamy Chelliah, Flipkart ● Soma Biswas, Indian Institute of Science ● Lucky Dhakad, Data Scientist, Flipkart Internet Pvt. Ltd

Friday October 25 — Half day tutorial — 09:00-12:30 — location Galliéni 1&2

  85/88

Tutorial 7: Multimodal Data Collection for Social Interaction Analysis In-the-Wild

Abstract: The benefits of exploiting multi-modality in the analysis of human-human social behaviour has been demonstrated widely in the community. An important aspect of this problem is the collection of data-sets that provide a rich and realistic representation of how people actually socialize with each other in real life. These subtle coordination patterns are influenced by individual beliefs, goals, and desires related to what an individual stands to lose or gain in the activities they perform in their everyday life. These conditions cannot be easily replicated in a lab setting and require a radical re-thinking of both how and what to collect. This tutorial provides a guide on how to create such multi-modal multi-sensor data sets when considering the entire experimental design and data collection process. It will also include a debriefing for the ConfLab experiment run at the conference to encourage a community discussion on issues of privacy and data sharing and ethical practices.

Speakers: ● Hayley Hung, Delft University of Technology● Chirag Raman, Delft University of Technology● Ekin Gedik, Delft University of Technology● Stephanie Tan, Delft University of Technology● Jose Vargas-Quiros, Delft University of Technology

Friday October 25 — Half day tutorial — 14:00-17:30 — location Rhodes 9

Tutorial 8: Medical Multimedia Systems and Applications

Abstract: Over the last decade we could observe an increasing need from clinicians for help from the multimedia community. The reason for this is the fact that more and more videos and images are stored in the hospital information system for post-operative usage. Although the storage itself is quite challenging due to the massive amount of data, even more serious problems arise when surgery videos should be used for purposes such as teaching and training, retrospective analysis, visual analytics, as well as diagnostic decision support. In this tutorial we will give a broad overview of the medical multimedia field, inclusive of its requirements and characteristics, discuss existing work of medical video/image analysis and outline open challenges and opportunities. We will cover several medical fields, such as laparoscopy gynecology, cholecystectomy, colonoscopy, and ophthalmology.

Speakers: ● Michael Riegler, Simula Metropolitan Center for Digital Engineering● Pål Halvorsen, SimulaMet● Klaus Schoeffmann, Klagenfurt University

Friday October 25 — Half day workshop — 14:00-17:30 — location Galliéni 1&2

86/88

Banquet, Wednesday Oct 23, 19:30

Hyatt Regency Nice Palais de la Méditerranée 13 Promenade des Anglais, Nice,

87/88