With the availability of production tools and distribution infrastructures, digital video content and applications are becoming prevalent. Researchers have been actively developing technologies for video indexing and summarization, in order to facilitate efficient management, exchange, and consumption of digital videos.

This tutorial will include two parts: (1) surveys of promising technologies and (2) discussion of potential applications. The survey component will include descriptions of the building blocks of a video indexing system, including

• shot detection and shot-based visualization interfaces, including difference based approaches, statistical approaches, and approaches handling special effects, flash, motion etc.
• video object extraction and indexing, including (semi-)automatic object extraction, feature extraction, and object retrieval techniques
• audio-video scene segmentation, including clustering based approaches, memory-based approaches, multimedia fusion, and approaches using domain-specific syntactic rules
• video summarization and skimming, including spatial summaries, temporal summaries, and time-compression skimming using domain-specific syntax
• event detection and classification, including learning-based event classification (e.g., HMM, Bayesian Networks), and joint visual-textual-audio classification

The application component will include case studies demonstrating the impact and challenges of the above technologies. Specifically, we will review applications in sports, medicine, news, presentation, and web-based search engines. Brief discussion will be given to explain the relationships of the technologies and the newly completed MPEG-7 standard.

Shih-Fu Chang is currently a Professor at the Department of Electrical Engineering of Columbia University. He leads Columbia University's ADVENT industry-university consortium and the Digital Video/Multimedia research group (www.ee.columbia.edu/dvmm), conducting research in multimedia indexing, adaptive coding, streaming, and authentication. Several systems developed by his group have been widely used, including VideoQ, WebSEEk for image/video searching, WebClip for networked video editing, and Sari for online image authentication watermarking.

In addition to developing new theories and algorithms, he is also interested in applying video technology to various domains, such as a medical video digital library funded by the DLI-2 initiative, a Digital News project, and a live sports video filtering project.

Prof. Chang has been a general co-chair of ACM Multimedia Conference 2000, an associate editor of several journals, and a consultant in several new media companies. He is a Distinguished Lecturer in IEEE Society of Circuits and Systems from 2001-2002. His group has actively participated in the development of MPEG-7.

He has been awarded a Navy ONR Young Investigator Award, a Faculty Development Award from IBM, a CAREER Award from National Science Foundation, and three Best Paper Awards from IEEE, ACM, and SPIE in the areas of multimedia manipulation and retrieval.