Local Behaviours Labelling for Content Based Video Copy Detection

This paper presents an approach for indexing a large set of videos by considering the dynamic behavior of local visual features along the sequences. The proposed concept is based on the extraction and the local description of interest points and further on the estimation of their trajectories along the video sequence. Analyzing the low-level description obtained allows to highlight trends of behavior and then to assign a label. Such an indexing approach of the video content has several interesting properties: the low-level descriptors provide a rich and compact description, while labels of behavior provide a generic semantic description of the video content, relevant for video content retrieval. We demonstrate the effectiveness of this approach for content-based copy detection (CBCD) on large collections of videos (several hundred hours of videos)