This paper introduces an approach to generate video clips starting from an annotated commentary. The novelty of the approach lies in the use of rhetorical structure of the accompanying audio commentary in planning the video. The basic notions of cinematography are briefly introduced together with the Rhetorical Relation Theory to model the structure of a discourse. Then, the architecture of a video engine to automatically build video clips from the audio commentary annotated with respect to rhetorical relations is described. Finally, an application for a multimedia mobile guide in a museum is described.
展开▼
