A Multi-modal Clustering Method for Web Videos

Abstract

The prevalence of video sharing websites brings the explosion of web videos and poses a tough challenge to the web video clustering for their indexing. This paper proposes a flexible multi-modal clustering method for web videos. This method achieves web video representation and similarity measurement by integrating the extracted visual features, semantic features and text features of videos to describe a web video more accurately. With the multi-modal combined similarity as input, the affinity propagation algorithm is employed for the clustering procedure. The clustering method is evaluated by experiments conducted on web video dataset and has a better performance than existing methods. © Springer-Verlag Berlin Heidelberg 2013.