Hierarchical Video Summarization Based on Video Structure and Highlight

Abstract

Abstract. Video summarization is a significant scheme to organize massive video data, and implement a meaningful rapid navigation of video. In this paper, we propose a hierarchical video summarization approach based on video structure and highlight. We extract video structure unit, and measure the unit (frame, shot and scene) importance rank based on visual and audio attention models. According to the unit importance rank, the skim ratio and key frame ratio are assigned to the different video units. Thus we achieve a hierarchical video summary. Experimental results show the excellent performance of the approach.

Videotrees: Improving video surrogate presentation using hierarchy

“…Such a summary can provide its viewer with a "fast forward" skim through the original, while taking a lot less time to watch. By selecting the most salient segments of a video and placing those in sequence, a movie-trailer-like result can be obtained [13].…”

A Survey on Visual Content-Based Video Indexing and Retrieval

“…For instance, Taskiran et al [185] cluster key frames extracted from shots using color, edge, and texture features and present them in a hierarchical fashion using a similarity pyramid. Geng et al [187] propose a hierarchical video summarization algorithm based on video structure and highlights. In the algorithm, video structure units (frame, shot, and scene) are ranked using visual and audio attention models.…”