Video scouting: an architecture and system for the integration of multimedia information in personal TV applications

Currently available personal video recorders find and store whole TV programs. Our system, Video Scouting, not only finds and stores programs; it automatically segments and indexes story segments from the programs according to viewers´ profiles. The extracted descriptions serve the viewers´ content information requests for program segment selection, e.g., play the three minute interview with Hillary Clinton. To achieve this, the system combines information from the audio, visual, and transcript domains in a probabilistic framework based on Bayesian networks. We describe the overall architecture, a system implementation, and discuss some experimental results