Omni-face detection for video/image content description
MULTIMEDIA '00 Proceedings of the 2000 ACM workshops on Multimedia
Classification of general audio data for content-based retrieval
Pattern Recognition Letters - Special issue on image/video indexing and retrieval
Exploring the Web with reconnaissance agents
Communications of the ACM
Project Aura: Toward Distraction-Free Pervasive Computing
IEEE Pervasive Computing
Multimedia content processing through cross-modal association
MULTIMEDIA '03 Proceedings of the eleventh ACM international conference on Multimedia
Discrimination of media moments and media intervals: sticker-based watch-and-comment annotation
Multimedia Tools and Applications
Hi-index | 0.00 |
We present a content augmentation application that enhances the primary video watching experience by providing related supplemental information. Our goal is to explore the value of cross-referencing related content among different media such as TV and Web. The cross-referencing is based on metadata, which is automatically extracted from the content. Metadata extraction can make a great difference for personalized user experience. In addition, annotations that provide title, genre, description, and cast can be greatly enriched with detailed information at the subprogram level, i.e. at the clip and scene level. We developed a system called InfoSip that performs person identification and scene annotation based on actor presence. The system links this information with actors' filmographies and biographies and produces an enriched viewing experience.