Résumé |
The Movie structure extraction is essential to automatic and content-based organization, retrieval and browsing of movie. However, while many robust shot segmentation algorithms have been developed, it is still difficult to extract structures from a film. In this paper, we present a novel film segmentation scheme, in which low-level and semantic features from audio and image are integrated in movie structure extraction. We show by experiment on 8 films that semantic features bring important information for structure extraction, |