Video Copy-Detection and Localization with a Scalable Cascading Framework

For video copy detection, no single audio-visual feature, or single detector based on several features, can work well for all transformations. This article proposes a novel video copy-detection and localization approach with scalable cascading of complementary detectors and multiscale sequence matching. In this cascade framework, a soft-threshold learning algorithm is utilized to estimate the optimal decision thresholds for detectors, and a multiscale sequence matching method is employed to precisely locate copies using a 2D Hough transform and multigranularities similarity evaluation. Excellent performance on the TRECVID-CBCD 2011 benchmark dataset shows the effectiveness and efficiency of the proposed approach.