CALL FOR PAPERS SECOND WORKSHOP ON STATISTICAL METHODS IN VIDEO PROCESSING in conjunction with European Conference on Computer Vision Prague, Czech Republic, May 16, 2004 Workshop web-site: http://www.scr.siemens.com/smvp04/ SCOPE In recent years a variety of advanced statistical methods became standard tools for processing visual information. Our current understanding of the performance of these techniques when applied to long video sequences is, however, rather limited. There are at least two reasons for this. First, the theoretical performance bounds are most often computed with limiting assumptions, which are not valid in practice. Second, robust vision systems require not only superior analysis to handle outliers and model selection, but also strategies to adapt to the non-stationary behavior of the input. This workshop focuses on recent progress in the application of modern statistics to solve computer vision tasks that use non-stationary video data. For such sequences, the underlying models and parameters of the algorithms have to be often adapted or reinitialized in time, according to higher-level strategies. Examples are sequences containing sudden or gradual changes in the input data statistics, such as: a walking/running/turning person; empty/crowded train stations; arrival of a train/metro; turning on/off (either abruptly or gradually) the light source(s); transition from day to night; changing the environment from indoor to outdoor; video signal captured from a vehicle entering a tunnel; weather changing from clear sky to rain/snow; dynamic occlusions; time-varying patterns (medical perfusion), summer/winter surveillance, etc. The workshop aims at bringing together researchers with various backgrounds, interested in building robust vision algorithms that can accommodate changes in the input statistics. Areas of interest include, but are not limited to: o Robust Statistical Techniques o Tracking and Motion Analysis o Stereo and Structure from Motion o 2D & 3D Scene Analysis o Fluid Motion Analysis o Dynamic Background Modeling o Dynamic Texture Analysis o Vision-based Driver Assistance o Video Segmentation and Indexing o Gesture Recognition o Spatio-Temporal Feature Selection o Applications in Medical Image Analysis o Applications in Meteorological Imagery o Biometrics and Surveillance This event is a sequel of the 1st Workshop on Statistical Methods in Video Processing, organized in conjunction with the 7th European Conference in Computer Vision, 2002. BEST STUDENT PAPER PRIZE Siemens Corporate Research will sponsor a prize awarded to the best student paper. IMPORTANT DATES Submission deadline: February 1, 2004 Author notification: March 15, 2004 Workshop: May 16, 2004 PAPER SUBMISSION AND REVIEW The submission is electronic, pdf file. The paper should be in English, no longer than 12 pages in Springer LNCS format (same format as ECCV 2004). The review is double blind, please do not identify the author(s) in the submission. The workshop proceedings will be published in the Springer Lecture Notes in Computer Science (LNCS). The following link should be used for paper submission: http://www.ds.eng.monash.edu.au/smvp/submission/submission_smvp2.html ORGANIZING COMMITTEE Dorin Comaniciu, Siemens Corporate Research, USA Kenichi Kanatani, Okayama University, Japan Rudolf Mester, Goethe-Universitaet, Germany David Suter, Monash University, Australia PROGRAM COMMITTEE Bir Bhanu, University of California, USA Patrick Bouthemy, IRISA / INRIA, France Mike Brooks, University of Adelaide, Australia Yaron Caspi, Weizmann Institute of Science, Israel Rama Chellappa, University of Maryland, USA Andrew Fitzgibbon, Oxford University, United Kingdom Radu Horaud, INRIA, France Naoyuki Ichimura, AIST / Columbia University, Japan Michael Isard, Microsoft Research, USA Bogdan Matei, Sarnoff Corporation, USA Takashi Matsuyama, Kyoto University, Japan Visvanathan Ramesh, Siemens Corporate Research, USA Harpreet Sawhney, Sarnoff Corporation, USA Stuart Schwartz, Princeton University, USA Mubarak Shah, University of Central Florida, USA Nobutaka Shimada, Osaka University, Japan Zhengyou Zhang, Microsoft Research, USA Ying Zhu, Siemens Corporate Research, USA