Author/Authors :
Li, Jianmin Tsinghua University - Department of Computer Science and Technology, Tsinghua National Laboratory for Information Science and Technology (TNList), State Key Laboratory of Intelligent Technology and Systems, China , Liang, Yingyu Tsinghua University - Department of Computer Science and Technology, Tsinghua National Laboratory for Information Science and Technology (TNList), State Key Laboratory of Intelligent Technology and Systems, China , Zhang, Bo Tsinghua University - Department of Computer Science and Technology, Tsinghua National Laboratory for Information Science and Technology (TNList), State Key Laboratory of Intelligent Technology and Systems, China
Abstract :
Content-based video copy detection is an active research field due to the need for copyright protection and business intellectual property protection. This paper gives a probabilistic spatiotemporal fusion approach for video copy detection. This approach directly estimates the location of the copy segment with a probabilistic graphical model. The spatial and temporal consistency of the video copy is embedded in the local probability function. An effective local descriptor and a two-level descriptor pairing method are used to build a video copy detection system to evaluate the approach. Tests show that it outperforms the popular voting algorithm and the probabilistic fusion framework based on the Hidden Markov Model, improving F-score (F1) by 8%.
