The DVMM Lab at Columbia University is dedicated to research of new theories, algorithms, and systems for multimedia content analysis, search, communication, and forensics, with a primary focus on digital video. It hosts faculty, students, and visiting researchers, conducting research as well as development of multimedia technologies, testbeds, and standards.

Our current research activities focus on five areas:

• multimedia search and retrieval
• pervasive media and mobile communication
• machine learning and object recognition
• media security and forensics
• multimedia standard, testbed, and benchmarking

We have applied research to several domains, with close collaboration with colleagues in medicine, journalism, education, as well as industry. Some highlight systems include automatic indexing and summarization for sports, news, and echocardiogram medical videos. In several projects, we are exploring novel use of techniques from statistical pattern recognition and multimedia signal processing in order to extract patterns, semantics, and knowledge from media content collection.

We advocate a new paradigm called content-based media engineering, in which we emphasize exploration of synergy between automatic content analysis and new functionalities in various stages of the content chain. Among such efforts, one project focuses on automatic prediction of optimal video transcoding operations based on classification of content categories and associated resource-utility relations. Another project aims at invariant feature extraction in supporting intelligent authentication that is able to distinguish acceptable manipulations from malicious content alterations.

For problems or questions regarding this web site contact The Web Master.
Last updated: June 12, 2003.