VIDEO RETRIEVAL VIA LEARNING COLLABORATIVE SEMANTIC DISTANCE

Abstract

Graph-based semi-supervised learning approaches have been proven effective and efficient in solving the problem of the inefficiency of labeled data in many real-world application areas, such as video annotation. However, the pairwise similarity metric, a significant factor of existing approaches, has not been fully investigated. That is, these graph-based semi-supervised approaches estimate the pairwise similarity between samples mainly according to the spatial property of video data. On the other hand, temporal property, an essential characteristic of video data, is not embedded into the pairwise similarity measure. Accordingly, a novel framework for video annotation, called Joint Spatio-Temporal Correlation Learning (JSTCL), is proposed in this paper. This framework is characterized by simultaneously taking into account the spatial and temporal property of video data to achieve more accurate pairwise similarity values. We apply the proposed framework to video annotation and report superior performance compared to key existing approaches over the benchmark TRECVID data set.