First ACM International Workshop on Video Surveillance in conjunction with 11th ACM International Conference on Multimedia November 2-8, 2003, Berkeley, CA, USA WEB: http://www.mmdb.ece.ucsb.edu/~echang/acmmm-iwvs03.htm Workshop Date: November 7, 2003 With the proliferation of inexpensive cameras and the deployment of high-speed, wired/wireless networks, it has become economically and technically feasible to employ multiple cameras for security surveillance. In a surveillance system, video signals are generated by multiple cameras with or without spatially and temporally overlapping coverage. These signals need to be transmitted, processed, fused, stored, indexed, and then summarized as semantic events to allow efficient and effective queries and mining by security personnel and law enforcement officers. This workshop will bring together researchers, developers and practitioners from academia and industry to discuss various issues involved in developing a large-scale video surveillance system: e.g., from low-level feature extraction to high-level object and motion description, from camera control to networks to storage and indexing, and from theory to practice. The workshop will cover a variety of research issues on video surveillance. It will focus on the underlying theory, methods, systems, and applications. The topics will include, but are not limited to, the following: WORKSHOP TOPICS Video Content Analysis o Multi-Camera Calibration o Motion Detection and Tracking o Face Detection and Recognition in Unconstrained Environments o Object Recognition o Multi-camera/-sensor Fusion Video Event Modeling and Mining o 2D/3D Multi-level Scene/Patten Representations o Machine Learning Techniques for Event Mining o Spatio-temporal Data Mining o Threat Assessment Video Indexing and Storage o Spatio-temporal Data Indexing o Archival/Retrieval of Video Data o Query Paradigms and Languages o Mobile Architectures Surveillance Applications o Military Applications o Civilian Applications WORKSHOP STRUCTURE AND ATTENDANCE The one-day workshop will open with a special session consisting of three to four papers that will introduce and overview the research area. Presentations will then be organized into several sessions corresponding roughly to the categories identified above. The workshop will conclude with a round-table discussion on future research directions. The accepted papers will be available electronically from the workshop website, and also as printed workshop notes (published by ACM Multimedia). A special issue of ACM Multimedia journal or IEEE Transaction on Multimedia (under discussion) will publish selected papers. WORKSHOP CO-CHAIRS Edward Chang, UC, Santa Barbara Yuan-Fang Wang, UC, Santa Barbara PROGRAM COMMITTEE J. K. Aggarwal, University of Texas Shih-Fu Chang, Columbia University Nevenka Dimitrova, Philips Research Yihong Gong, NEC Research Ajay Divakaran, Mitsubishi Research Forouzan Golshan, Arizon State University Ioannis Kakadiaris, University of Houston Rainer Lienhart, Intel Research Chen Li, UC, Irvine Chung-Sheng Li IBM T.J. Watson Research Richard Muntz, UCLA N. Nandhukamar, Triveni Digital Youngchoon Park, MP7TV Thomas Plagemann, Univ of Oslo, Norway Stan Sclaroff, Boston University Cyrus Shahabi, USC Prashant Shenoy, Univ of Massachusetts, Amherst John Smith, IBM T.J. Watson Research Mohan Trivedi, UC, San Diego Hong-Jiang Zhang, Microsoft Research, China IMPORTANT DATES July 15, 2003: Submissions Due August 18, 2003: Acceptance Notice August 31, 2003: Camera Ready SUBMISSION Authors are invited to submit papers on the outlined topics or on other related issues. Submissions should not exceed 8 pages, and should conform to the ACM style sheet. Electronic submissions, in PDF format, are required and should be sent to Prof. Edward Chang at echang@ece.ucsb.edu. Sponsors: ACM SIGMM, UC Discovery Program (pending)