Supervised video summarization by content-based video segment selection

In this paper, we formulate the video summarization problem as the one of automatic video segment selection based on one-class classification. We introduce a novel variant of the One-Class Support Vector Machine classifier that exploits subclass information in its optimization problem, in order to jointly minimize the data dispersion within each subclass and determine the optimal decision function. We evaluate the proposed approach in Hollywood movies, where the performance of the proposed SOC-SVM algorithm is compared with that of the OC-SVM.