Prof. Shih-Fu Chang Research Activities:

My research areas include multi-modal content analysis, video recognition, multimedia information retrieval, multi-dimensional video adaptation, and media forensics. Our approaches to many problems involve novel formulation and applications of techniques culled from signal processing, statistical pattern recognition, computer vision, and related fields such as information retrieval and networking. 

I have been advocating a new research framework called content-based media processing, in which we explore the synergy between automatic content analysis and innovative applications throughout the content chain. Examples include content-based indexing/summarization, content adaptive video transcoding, and content signature based authentication. As proof of concept, my group has demonstrated several well known systems for web image search, live video highlight generation and streaming, spatio-temporal video object search, and semi-fragile image authentication.

My group has actively participated in Columbia's ADVENT University-Industry Research Consortium, Columbia's Persiaval Digital Library project, NIST TRECVID video retrieval evaluation event, and the development of MPEG-7 and MPEG-21 standards.

For more information of our projects, please visit the web site of Digital Video and Multimedia Lab.