Semantic-aware automatic video editing

One of the challenges of multimedia applications is to provide user-tailored access to information encoded in different media. Particularly, previous research has not yet fully explored how to automatically compose different video segments according to a communicative goal. We propose a rhetoric-based method to support the selection and automatic editing of user-requested content from video footage. The method is applied to the domain of video documentaries to create biased sequences about a user selected subject.