Multilevel video representation with application to keyframe extraction
RIS ID
54420
Abstract
Content-based video analysis calls for efficient video representation. In this paper, a novel multi-level representation of video is proposed based on the principle components derived from low-level visual features. It can characterize the video content from the coarse level to the fine level according to its intrinsic structure. This representation form provides a flexible scheme for video content analysis such as summarization, classification, and retrieval. A newly proposed subspace method, kernel based PCA, is explored to achieve this conveniently. The application in keyframe extraction is investigated to demonstrate the benefits of this representation.
Publication Details
Yu, X., Wang, L., Tian, Q. & Xue, P. (2004). Multilevel video representation with application to keyframe extraction. 10th International Conference on Multimedia Modelling (MMM) (pp. 117-123). Australia: IEEE.