TOWARD THE AUTOMATED EDITING OF THEME-ORIENTED VIDEO SEQUENCES

This article considers the automated generation of humorous video sequ ences from arbitrary video material. We present a simplified model of the editing process. We then outline our approach to narrativity and v isual humor, discuss the problems of context and shot order in video, and consider influences on the editing process. We describe the role o f themes and semantic fields in the generation of content-oriented vid eo scenes. We then present the architecture of AUTEUR, an experimental system that embodies mechanisms to interpret, manipulate, and generat e video. An example of a humorous video sequence generated by AUTEUR i s described.