VECTaR2011

Effective correlation of multiple independent data sources is critical for multi-camera visual surveillance. Video data from a distributed camera network can often be huge and widely disparate in nature, with meaningful object associations often being not only previously unknown, but also highly context dependent and sparse. In this talk, I describe a holistic approach to multi-source object association among disjoint camera views, known as the problem of re-identification. The model utilises three distinct components: (1) the use of relative ranking to replace the more conventional metric distance matching method for comparing data from two different sources; (2) learning spatio-temporal activity profiles to reduce the search space for discovering meaningful associations between camera views; and (3) the use of interactive data mining to quickly and effectively guide the system to discover useful and/or previously unknown associations. The system is extensively evaluated against the UK Home Office i-LIDS multi-camera dataset. The results show that the combination of these three components permits the system to operate more quickly and effectively with a significantly higher success rate over previous techniques.

Bio:

Shaogang Gong is Professor of Visual Computation at Queen Mary University of London, a Fellow of the Institution of Electrical Engineers and a Fellow of the British Computer Society. He received his D.Phil in computer vision from Keble College, Oxford University in 1989. He has published over 250 papers in computer vision and machine learning, and two books "Visual Analysis of Behaviour: From Pixels to Semantics" (2011), and "Dynamic Vision: From Images to Face Recognition" (2000). His work focuses on behaviour recognition, video semantic content analysis, object detection and tracking, face and expression analysis, gesture and action recognition.

Dr. Ivan Laptev, INRIA France

URL: http://www.irisa.fr/vista/Equipe/People/Ivan.Laptev.html

Registration: the paper code for registration is: 'WS18-yy' (yy is the number of your paper ID in the VECTaR workshop). (updated on 27/09/2011).

The conference ID for using the pdf-xepress is 'iccv2011x'. The camera-ready submission deadline is extended to 14/09/2011. (updated on 12/09/2011).

Call for Papers

With the vast development of Internet capacity and speed, as well as wide adoptation of media technologies in people's daily life, it is highly demanding to efficiently process or organize video events rapidly emerged from the Internet (e.g., YouTube), wider surveillance networks, mobile devices, smart cameras, etc. The human visual perception system could, without difficulty, interpret and recognize thousands of events in videos, despite high level of video object clutters, different types of scene context, variability of motion scales, appearance changes, occlusions and object interactions. For a computer vision system, it has been very challenging to achieve automatic video event understanding for decades. Broadly speaking, those challenges include robust detection of events under motion clutters, event interpretation under complex scenes, multi-level semantic event inference, putting events in context and multiple cameras, event inference from object interactions, etc.

In recent years, steady progress has been made towards better models for video event categorization and recognition, e.g., from modeling events with bag of spatial temporal features to discovering event context, from detecting events using a single camera to inferring events through a distributed camera network, and from low-level event feature extraction and description to high-level semantic event classification and recognition. However, the current progress in video event analysis is still far more from its promise. It is still very difficult to retrieve or categorise a specific video segment based on their content in a real multimedia system or in surveillance applications. The existing techniques are usually tested on simplified scenarios, such as the KTH dataset, and real-life applications are much more challenging and require special attention. To advance the progress further, we must adapt recent or existing approaches to find new solutions for intelligent video event understanding.

The goal of this workshop is to provide a forum for recent research advances in the area of video event categorisation, tagging and retrieval. The workshop seeks original high-quality submissions from leading researchers and practitioners in academia as well as industry, dealing with theories, applications and databases of visual event recognition. Real-life applications in the context of multimedia metadata, i.e. event analysis and recognition on videos from the Internet, surveillance cameras, and mobile devices, etc., will be the theme of this year's workshop. Topics include the following, but not limited to:

Motion interpretation and grouping
Human Action representation and recognition
Abnormal event detection
Contextual event inference
Event recognition among a distributed camera network
Multi-modal event recognition
Spatial temporal features for event categorization
Hierarchical event recognition
Probabilistic graph models for event reasoning
Machine learning for event recognition
Global/local event descriptors
Metadata construction for event recognition
Bottom up and top down approaches for event recognition
Event-based video segmentation and summarization
Video event database gathering and annotation
Efficient indexing and concepts modeling for video event retrieval
Semantic-based video event retrieval
On-line video event tagging
Evaluation methodologies for event-based systems
Event-based applications (security, sports, news, etc.)

Important Dates

Submission Deadline ~~July 11th, 2011~~ Extended to July 18th, 2011
Notification of Acceptance ~~August 22nd, 2011~~ Extended to August 26th, 2011
Camera-Ready Submission ~~September 10th, 2011~~ Extended September 14th, 2011
Workshop November 13th, 2011

General Chairs

Prof. Tieniu Tan, Chinese Academy of Sciences, China
Prof. Thomas S. Huang, University of Illinois at Urbana-Champaign, USA

Program Chairs

Prof. Liang Wang, Chinese Academy of Sciences, China
Dr. Jianguo Zhang, University of Dundee, UK
Dr. Ling Shao, The University of Sheffield, UK

Tentative Program Commitee

Rama Chellappa , University of Maryland, USA
Chekuri S. Choudary, RNET Technologies, Dayton, OH, USA
James W. Davis , Ohio State University, USA
Ling-Yu Duan , Peking University, China
Tim Ellis , Kingston University, UK
James Ferryman , University of Reading, UK
GianLuca Foresti , University of Udine, Italy
Shaogang Gong , Queen Mary University London, UK
Jungong Han , Centrum Wiskunde & Informatica, The Netherlands
kaiqi Hang , Chinese Academy of Sciences, China
Winston Hsu , National Taiwan University
Ran He, Chinese Academy of Sciences
Yu-Gang Jiang , Columbia University, USA
Graeme A. Jones , Kingston University, UK
Ivan Laptev , INRIA, France
Jianmin Li , Tsinghua University, China
Xuelong Li , Chinese Academy of Sciences, China
Zhu Li , Hong Kong Polytechnic University, China
Marcin Marszalek , Unviersity of Oxford, UK
Tao Mei , Microsoft Research Asia
Paul Miller , Queen's University Belfast, UK
Ram Nevatia , University of Southern California, USA
Yanwei Pang , Tianjin University, China
Federico Pernici , Università di Firenze, Italy
Carlo Regazzoni , University of Genoa, Italy
Shin'ichi Satoh , National Institute of Informatics, Japan
Dan Schonfeld , University of Illinois at Chicago, USA
Ling Shao , The University of Sheffield, UK
Yan Song , University of Science and Technology of China
Peter Sturm , INRIA, France
Dacheng Tao , Sydney University of Technology, Australia
Xin-Jing Wang , Microsoft Research Asia
Quan Wang, Ericsson R&D Division, USA
Tao Xiang , Queen Mary University London, UK
Dong Xu , Nanyang Technological University, Singapore
Hongbin Zha , Peking University, China
Zhang Zhang, Chinese Academy of Sciences
Jianguo Zhang , University of Dundee, UK
Lei Zhang , Microsoft Research Asia
Liang Wang , Chinese Academy of Sciences, China
Pingkun Yan , Chinese Academy of Sciences, China
Yuan Yuan , Chinese Academy of Sciences, China

Submission

When submitting manuscripts to this workshop, the authors acknowledge that manuscripts substantially similar in content have NOT been submitted to another conference, workshop, or journal. However, dual submission to the ICCV 2011 main conference and VECTaR'11 is allowed.
The format of a paper submission is the same as the ICCV main conference. Please follow instructions on the ICCV 2011 website http://www.iccv2011.org/paper-submission.
For the paper submission, please go to the Submission Website (https://cmt.research.microsoft.com/VECTAR2011/)
! Note: To get a paper ID, please register an initial submission first through the submission website.

Review

Each submission will be reviewed by at least three reviewers from program committee members and external reviewers for originality, significance, clarity, soundness, relevance and technical contents. Accepted papers will be published together with the proceedings of ICCV 2011 (included in the main conference DVD and in IEEE Xplore). High-quality papers will be invited to submit a special issue of a good computer vision journal after the conference.

Contacts

Prof. Liang Wang, wangliang@nlpr.ia.ac.cn
Dr. Jianguo Zhang, jgzhang@computing.dundee.ac.uk
Dr. Ling Shao,ling.shao@sheffield.ac.uk