Toward emergent representations for video

Advanced systems for finding, using, sharing, and remixing video require high-level representations of video content. A number of researchers have taken top-down, analytic approaches to the specification of representation structures for video. The resulting schemes, while showing the potential of high-level representations for aiding the retrieval and resequencing of video, have generally proved too complex for mainstream use. In this paper, we propose a bottom-up, emergent approach to developing video representation structures by examining retrieval requests and annotations made by a community of video remixers. Our initial research has found a useful degree of convergence between user-generated indexing terms and query terms, with the salient exception of descriptions of characters' corporeal characteristics. Categories and Subject Descriptors

• Type: Conference
• Year: 2005
• Where: MM
• Authors: Ryan Shaw, Marc Davis
• Keywords: MM 2005, Representation Structures, Video, Video Representation Structures