COLLOQUIUM
Department of Computer Science and Engineering
University of South Carolina
 
Summarization and Semantic Compression of Videos

Tiecheng Liu

Department of Computer Science
Columbia University

Date: March 3, 2003 (Monday)
Time: 3:30-4:30PM
Place: Swearingen 1A03 (Faculty Lounge)

Abstract

Video summarization is the process of capturing the essential
semantics of original videos with drastically reduced data
requirements.  Video summarization has important applications in many
areas, such as indexing, browsing, and query of digital video
libraries, dynamic summaries of TV programs, etc.  My research
provides a new approach for both off-line and on-line video
summarization.  This approach has advantages over previous methods in
temporal complexity and scalability, and it allows users to browse and
search video content easily.  I also provide a new video compression
technique, semantic compression, for instructional videos.  Unlike
traditional signal-level video compression, semantic video compression
is based on analysis and understanding of video content.  I show the
results of my approach on video summarization and demonstrate a system
for semantic video compression.

Tiecheng Liu is currently a Ph.D. candidate in the Department of
Computer Science at Columbia University.  He expects to receive the
Ph.D. degree in May 2003.  Tiecheng Liu received the B.S.  degree in
Mathematics from Shandong University in 1996 and the Master's degree
in Electrical Engineering from the Chinese Academy of Sciences in
1999.  He worked as a research intern at Siemens Corporate Research in
2000 and 2001.  His research interests include Computer Vision, Image
and Video Processing, and Artificial Intelligence.  He is a student
member of the IEEE.