Who's that actor?
Nevenka Dimitrova, Angel Janevski, Dongge Li, John L Zimmerman · 2003
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.