Multimedia Information Extraction Roadmap

Alexander Hauptmann

The broad challenge is to exploit multi-lingual, multimedia information from both web and TV video to allow broader understanding of different ideological, social, and cultural perspectives in different sources, for a wide variety of applications. This will involve the judicious analysis of the text and video features using a variety of machine learning and language analysis methods, as well as understanding of the video editing structure, as well as the context in which the media appears. The currently most plausible way to attack this is to develop thousands of automatically detectable semantic concepts in the video or images as a core vocabulary for highly accurate video analysis applications.

Submitted: Sep 8, 2008