The Second Workshop on Human Identification in Multimedia (HIM'17)

Abstract

Human Identities are an important information source in many high-level multimedia analysis tasks such as video summarization, semantic retrieval, interaction indexing, and scene understanding. The aim of this workshop is to bring together researchers in computer vision and multimedia to share ideas and propose solutions on how to address the many open issues in human identification, and present new datasets that introduce new challenges in the field. Human identification in multimedia is one relatively new problem in multimedia analysis and, recently, it has attracted the attention of many researchers in the field. Human Identification is significant to many multimedia related applications such as video surveillance, video search, human-computer interaction, and video summarization. Recent advances in feature representations, modeling, and inference techniques have led to a significant progress in the field. The proposed workshop aims to explore recent progress in human identification with multimedia data by taking stock of the past five years of work in this field and evaluating different algorithms. The proposed workshop will help the community to understand the challenges and opportunities of human identification in multimedia techniques for the next few years.


Topics

Topics of interest include, but are not limited to:
1.    Recognition on age, gender, ethnicity, hair color, etc.
2.    Soft biometric feature extraction
3.    Soft biometric feature evaluation
4.    Soft biometric feature reduction and classification
5.    Soft biometric system
6.    Studying the reliability of soft biometric characteristics
7.    Soft biometric information capture system
8.    Databases for evaluating methods on soft biometric
9.    Soft biometric security classification
10. Novel soft biometric traits
11. Fusion of primary and soft biometric information


Committee

Key Organizers


Yongxin Ge, Chongqing University, China
Xin Feng, Chongqing University of Technology, China
Xiuzhuang Zhou, Capital Normal University, China
Li Geng,The City University of New York

PC Members


Mohammad Elhoseiny, Facebook AI Lab, US
Mingchen Gao, National Institutes of Health, China
Shenghua Gao, ShanghaiTech University, China
Guodong Guo, West Virginia University, US
Junlin Hu, Nanyang Technological University, Singapore
Bo Liu, Rutgers University, US
Weitao Li, Hefei University of Technology, China
Zechao Li, Nanjing University of Science and Technology, China
Xiaoyan Luo, Beihang university, China
Xiaoming Liu, Michigan State University, US

Chuanxian Ren, Sun Yat-sen University, China
Chaoqun Weng, Nanyang Technological University, Singapore
Lu Wang, Osaka University, Japan
Xiang Yu, NEC Laboratories America Media Analytics Lab, US
Yang Yu, Facebook, US
Jianyu Yang, Soochow University, China
Jianwei Yang, Virginia Tech, US
Qijun Zhao, Sichuan University, China
Kunlei Zhang, Wayne State University, US
Yang Xiao, Huazhong University of Science and Technology, China

Duration

Half-day workshop (e.g. 8:35am~12:00pm)

7 oral presentations. Each oral presentation will be given 20 minutes including Q&A time.

1 Invited Talk, 30 minutes(if funds are available).

Submission

Paper Submission and Review
Site：TBA


The format of any submitted paper should follow the one for WACV2017.
This workshop will select one best paper.

Paper submission deadline: TBA
Reviewing period: TBA
Decision notification: TBA
Camera ready: TBA
Workshop day: April 30, 2017

For the papers which have ever been submitted to WACV but been rejected, the authors are encouraged to submit their WACV comments by printing their WACV comments from the CMT system as PDF file and submitting this PDF file as supplementary file along with their submission to the workshop.

Schedule

Half Day

08:35
 Opening Remarks
08:40
 Invited Talk
09:10
 Paper 1
09:30
 Paper 2
09:50
 Paper 3
10:10
 Coffee Break
10:30
 Paper 4
10:50
 Paper 5
11:10
 Paper 6
11:30
 Pager 7
11:50
 Conclusions & Future Work
12:00
 Lunch


CV of organizers

Yongxin Ge, Ph.D. (Contact Person)

· Chongqing University, China
· Address: No. 174 Shazhengjie, Shapingba, Chongqing, China, 430044
· Email: yongxinge@cqu.edu.cn
· Biography:
Yongxin Ge is currently an Associate Professor at the School of Software Engineering, Chongqing University, China. He received the B. Eng. degree in information and computing science, the M.S. degree in operations research and control theory and the Ph.D. degree in computer science and technology from the Chongqing University, Chongqing, China, in 2003, 2006 and 2011, respectively. From Sep. 2008 to Sep. 2009, he was an exchange PhD student in the department of Computer Science, University of Alberta, Canada, under the support of the China Scholarship Council. His research interests include image processing, pattern recognition and computer vision. He has published over 20 technical papers in international journals and conferences. He was a co-organizer of Special Session on “Video Analysis and Understanding”, SPIE International Conference on Visual Communication and Image Processing (VCIP), 2015.

 

Xin Feng, Ph.D

· Chongqing University of Technology, China
· Address: No. 69,Hongguang Ave., Banan,Chongqing, China, 400054
· Email: xfeng@cqut.edu.cn
· Biography:
Xin Feng is an Associate Professor at Department of Computer Science and Engineering in Chongqing University of Technology, Chongqing, China. She is currently making a two-year postdoc study at the Dept. of Electrical & Computer Engineering of New York University Tandon School of Engineering, New York, USA, under the support of the China Scholarship Council. She received the B.E. degree in computing science and technology, and the Ph.D. degree in computer application from Chongqing University, Chongqing, China, in 2004, 2011, respectively. From Sep. 2007 to Sep. 2008, she was a postgraduate exchange student in Dept. of Electrical & Computer Engineering of New York University Polytechnic School of Engineering, New York, USA. Her research interests include computer vision, video/image processing, with a particular emphasis in image/video representation and scene understanding. She has published 20 technical papers in international journals and conferences. She was a co-organizer of special session on International Conference on Visual Communication and Image Processing (VCIP), 2015.

 

Xiuzhuang Zhou, Ph.D.

· Capital Normal University, China
· Address: No.105, West Ring North Road, Haidian District Beijing, China, 100048
· Email: xiuzhuang.zhou@cnu.edu.cn
· Biography:
Xiuzhuang Zhou is currently an associate professor in College of Information Engineering, Capital Normal University, Beijing, China. He received B.S. degree from Department of Atmosphere Physics, Chengdu University of Information Technology, Chengdu, China, in 1996. He received M.E. degree and Ph.D. degree from School of Computer Science, Beijing Institute of Technology, Beijing, China, in 2005 and 2011, respectively. His research interests include computer vision, pattern recognition, and machine learning. He has published more than 40 scientific papers in peer-reviewed journals and conferences including some top venues such as the IEEE Transactions on Pattern Analysis and Machine Intelligence, IEEE Transactions on Image Processing, IEEE Transactions on Information Forensics and Security, CVPR and ACM MM. He is an Associate Editor of the Neurocomputing.

 

Li Geng, Ph.D.

· The City University of New York
· Address: 186 Jay Street,Brooklyn, New York, USA, 11201
· Email: LGeng@citytech.cuny.edu
· Biography:
Li Geng is currently an assistant professor in Department of Electrical Engineering & Telecommunication Technology at New York City College of Technology of the City University of New York. She received her B. Eng. degree in Telecommunication Engineering from Huazhong University of Science and Technology, Wuhan, China, in 2009. She received her Ph.D. degree in Electrical Engineering from Stony Brook University, New York, USA, in 2015. She has published around 10 scientific papers in peer-reviewed journals and conferences. Her research interests are in the area of statistical signal and image processing, signal detection and estimation, pattern recognition, as well as their applications to a wide area such as indoor localization and tracking with wearable sensor devices in health care systems and robotics.

Contact

Yongxin Ge


Chongqing University, China

yongxinge@cqu.edu.cn