DIMACS Workshop on Video Mining November 4-6, 2002 DIMACS Center, Rutgers University, Piscataway, New Jersey Organizers: Azriel Rosenfeld, University of Maryland, ar@cfar.umd.edu Daniel DeMenthon, University of Maryland, daniel@cfar.umd.edu Dave Doermann, University of Maryland, doermann@cfar.umd.edu Presented under the auspices of the Special Focus on Data Analysis and Mining. Modern computer technology, together with the proliferation of broadcast channels and of video-based surveillance systems, has enabled us to produce vast amounts of both raw and processed video data. The potential uses of this data are many and varied. Monitoring and mining of the content of this already huge, rapidly growing mass of data calls for the development of major computational resources and the development of sophisticated video understanding techniques. The applications and potential applications of video mining include: - monitoring of (possibly remote) surveillance cameras in theft protection, fire protection, care of bedridden patients and young children - automatic recognition of suspicious people in large crowds - automatic checking to identify passengers entering an airplane, bus, or public building (to verify entry authorization) - automatic quality control in manufacturing processes - robotic vision - retrieval of archived video clips to illustrate a newsbreaking story - retrieval of suspicious activities in prerecorded video surveillance sequences - browsing of DVD and set-top box recordings - intelligent fast-forward techniques - detection of multi-lingual scene text to determine origin of broadcast - video search engines for web browsers - ranking of video clips by relevance in web query results - classification of videos into genres for search pruning - detection of crowd patterns for mob control - detection of traffic patterns for traffic understanding management There are some pervasive challenges here. A huge amount of data must be efficiently stored. Once stored, there must exist efficient retrieval algorithms. It must also be possible to retrieve different kinds of data stored in possibly different formats. Some of the applications will require real-time response and action based on an incoming data stream. The purpose of this workshop will be to survey available and potential technologies for video monitoring and mining (and in general methods of fast and efficient content-based analysis of video streams) and to identify promising directions for research in this challenging area. Specific topics to be covered will be analysis of camera motion and scene activity; temporal segmentation; content-based classification, indexing, and retrieval; representation, browsing, and visualization. We will also investigate related mining problems having to do with audio mining, seismic data mining, and cross-modality mining. Audio mining applications of interest include speech recognition; seismic data mining applications include identification of potential new sources of oil and gas and detection of earthquakes and/or nuclear tests. Cross-modality issues arise for example in problems involving identification from both video and speech. ***************************************************************** Workshop Program: (FINAL) Monday, November 4th 8:00 - 9:00 Registration and breakfast 9:00 - 9:05 Welcome and Greeting DIMACS representative 9:05 - 9:20 Introductory remarks Azriel Rosenfeld, University of Maryland, College Park 9:20 - 10:10 Spatiotemporal Representations from Image Sequences: From Illusions to Video Mining Yiannis Aloimonos, University of Maryland, College Park 10:10 - 10:30 Break 10:30 - 11:15 Video Indexing and Summarization using the Motion Activity Descriptor Ajay Divakaran, Mitsubishi Electric Research Laboratories 11:15 - 12:00 A Framework of Human Motion Tracking and Event Detection for Video Indexing and Mining Thomas Huang, University of Illinois at Urbana-Champaign 12:00 - 1:30 Lunch 1:30 - 2:15 Efficient Video Browsing using Multiple Synchronized Views Arnon Amir, IBM Almaden Research Center 2:15 - 3:00 Video Indexing, Summarization, and Adaptation Shih-Fu Chang, Columbia University 3:00 - 3:15 Break 3:15 - 4:00 Beyond Key Frames: The Physical Setting as a Video Mining Primitive John R. Kender, Columbia University 4:00 - 4:45 Content-based Video Retrieval Rainer Lienhart, Intel Laboratories Tuesday, November 5th 8:00 - 9:00 Registration and breakfast 9:00 - 9:45 Video Indexing and Retrieval using Spatio-Temporal Descriptions of Sequences Daniel DeMenthon, University of Maryland, College Park 9:45 - 10:30 Database Techniques and Video Data Management Arjen P. de Vries, CWI, The Netherlands 10:30 - 10:45 Break 10:45 - 11:30 Automatic Genre Classification of Video David Doermann, University of Maryland, College Park 11:30 - 12:15 Mining Images and Video B.S. Manjunath, University of California, Santa Barbara 12:15 - 1:30 Lunch 1:30 - 2:15 Knowledge-based Techniques for Content-based Video Retrieval Milan Petkovic, University of Twente 2:15 - 3:00 Video Categorization using Semantics and Semiotics Mubarak Shah, University of Central Florida 3:00 - 3:15 Break 3:15 - 4:00 Mixtures of Probability Experts for Audio Retrieval and Indexing Malcolm Slaney, IBM Almaden Research Center 4:00 - 4:40 Statistical Modeling and Retrieval of Video Content John R. Smith, IBM T.J. Watson Research Center Wednesday, November 6th 8:00 - 9:00 Registration and breakfast 9:00 - 9:45 Multimedia Story Segmentation Nevenka Dimitrova, Philips Research USA 9:45 - 10:30 Context-dependent Detection of Unpredictable Events in Videos Longin Jan Latecki, Temple University 10:30 - 10:45 Break 10:45 - 11:30 Statistical Methods for Real-time Video Surveillance Visvanathan Ramesh, Siemens Corporate Research 11:30 - 12:15 Bayesian Models of Video Structure for Segmentation and Content Characterization Nuno Vasconcelos, Compaq Research 12:15 - 1:30 Lunch 1:30 - 2:15 Movie Content Analysis and Abstraction via Multimodal Information C.-C. Jay Kuo, University of Southern California 2:15 - 3:00 Finding Information in a Digital Video Archive Alexander Hauptmann, Carnegie-Mellon University 3:00 - 3:15 Concluding Remarks **************************************************************** REGISTRATION FEES: Our funding agencies require that we charge a registration fee during the course of the workshop. Registration fees include participation in the workshop, all workshop materials, breakfast, lunch, breaks and any scheduled social events (if applicable). Fees are $40 per person per day for faculty, researchers and "other", and $5 per person per day for postdocs. The registration fee is waived for undergraduate students, graduate students, DIMACS postdocs and DIMACS long-term visitors who are in residence at DIMACS. Fees for employees of DIMACS partner institutions are waived. DIMACS partner institutions are: Rutgers University, Princeton University, AT&T Labs - Research, Bell Labs, NEC Research Institute and Telcordia Technologies. Fees for employees of DIMACS affiliate members Avaya Labs and Microsoft Research are also waived. Fees are not waived for IBM Watson Research Center employees (the terms of the IBM membership are different from the Avaya and Microsoft agreements). *************************************************************** For complete information on registration, travel and accommodations see: http://dimacs.rutgers.edu/Workshops/Video/