Redundancy filtering and fusion verification for video copy detection

详细信息    查看全文

• 作者：Shikui Wei (1) (2)
  Su Jiang (1) (2)
  Wenxian Jin (1) (2)
  Yao Zhao (1) (2)
  Rongrong Ni (1) (2)
  Zhenfeng Zhu (1) (2)
  
  1. Institute of Information Science ; Beijing Jiaotong University ; Beijing ; 100044 ; China
  2. Beijing Key Laboratory of Advanced Information Science and Network Technology ; Beijing ; 100044 ; China
  
• 关键词：Video copy detection ; Path verification ; Frame fusion ; Frame filtering ; HMM
• 刊名：Multimedia Systems
• 出版年：2015
• 出版时间：March 2015
• 年：2015
• 卷：21
• 期：2
• 页码：207-216
• 全文大小：1,892 KB
• 参考文献：1. Lowe, D.G.: Distinctive image features from scale-invariant keypoints. Int. J. Comput. Vis. 60(2), 91鈥?10 (2004) CrossRef
  2. Wu, C., Zhu, J., Zhang, J.: A content-based video copy detection method with randomly projected binary features. In: IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops, pp. 21鈥?6 (2012)
  3. Tian, Y., Jiang, M., Huang, T.: Video copy detection and localization with scalable cascading of complementary detectors and multi-scale sequence matching. IEEE MultiMedia 20(3), 72鈥?6 (2012)
  4. Uchida, Y., Takagi, K., Sakazawa, S.: Fast and accurate content-based video copy detection using bag-of-global visual features. In: IEEE International Conference on Acoustics Speech and Signal Processing, pp. 1029鈥?032 (2012)
  5. Jiang, M., Tian, Y., Huang, T.: Video copy detection using a soft cascade of multimodal features. IEEE Int. Conf. Multimedia Expo 2012, 374鈥?79 (2012)
  6. Ren, J., Chang, F., Wood, T., Zhang, J.R.: Efficient video copy detection via aligning video signature time series. In: Proceedings of the 2nd ACM International Conference on Multimedia Retrieval (HongKong). ACM New York, NY, USA (2012)
  7. Kim, C., Vasudev, B.: Spatiotemporal sequence matching for efficient video copy detection. IEEE Trans. Circuits Syst. Video Technol. 15(1), 127鈥?32 (2005) CrossRef
  8. Wei, S.K., Zhao, Y., Zhu, C., Xu, C., Zhu, Z.F.: Frame fusion for video copy detection. IEEE Trans. Circuits Syst. Video Technol. 21(1), 15鈥?8 (2011) CrossRef
  9. Wei, S.K., Zhao, Y., Zhu, Z.F., Liu, N.: Multimodal fusion for video search reranking. IEEE Trans. Knowl. Data Eng. 22(8), 1191鈥?199 (2010) CrossRef
  10. Chiu, C.Y., Chen, C.S., Chien, L.F.: A framework for handling spatiotemporal variations in video copy detection. IEEE Trans. Circuits Systems Video Technol. 18(3), 412鈥?17 (2008) CrossRef
  11. Douze, M., Jegou, H., Schmid, C.: An image-based approach to video copy detection with spatio-temporal post-filtering. IEEE Trans. Multimedia 12(4), 257鈥?66 (2010) CrossRef
  12. Douze, M., Jegou, H., Schmid, C., Perez, P.: Compact video description for copy detection with precise temporal alignment. In: European Conference on Computer Vision, pp. 522鈥?35 (2010)
  13. Shang, L., Yang, L., Wang, F., Chan, K.P., Hua, X.S.: Real-time large scale near-duplicate web video retrieval. In: ACM International Conference on Multimedia, pp. 531鈥?40 (2010)
  14. Liu, B., Li, Z., Yang, Y.C., Wang, M., Tian, X.M.: Real-time video copy-location detection in large-scale repositories. IEEE Multimedia 18(3), 22鈥?1 (2011) CrossRef
  15. Douze, A.D.M., Gaidon, A., Jegou, H., Marszatek, M., Schmid, C.: Inria-lear鈥檚 video copy detection system. In: Proc. TRECVID, Gaithersburg, USA (2008)
  16. Jegou, H., Douze, M., Schmid, C., Perez, P.: Aggregating Local Descriptors into a Compact Image Representation. In: IEEE Conference on Computer Vision and Pattern Recognition, pp. 3304鈥?311 (2010)
  17. Wei, S.K., Xu, D., Li, X.L., Zhao, Y.: Joint optimization toward effective and efficient image search. IEEE Trans. Cybern 43(6), 2216鈥?227 (2013)
  18. Wang, S.H., Huang, Q.M., Jiang, S.Q., Tian, Q.: S3MKL: scalable semi-supervised multiple kernel learning for real world image data mining. IEEE Trans. Multimedia 14(4), 1259鈥?274 (2012) CrossRef
  19. Wang, S.H., Huang, Q.M., Jiang, S.Q., Tian, Q.: Nearest-neighbor method using multiple neighborhood similarities for social media data mining. Neurocomputing 95(15), 105鈥?16 (2012) CrossRef
  20. Wang, M., Hua, X.S., Tang, J., Hong, R.: Beyond distance measurement: constructing neighborhood similarity for video annotation. IEEE Trans. Multimedia 11(3), 465鈥?76 (2009) CrossRef
  21. Jegou, H., Douze, M., Schmid, C.: Product quantization for nearest neighbor search. IEEE Trans. Pattern Anal. Mach. Intell. 33(1):17鈥?28 (2011)
  22. http://people.rennes.inria.fr/Herve.Jegou/software.html. Accessed 15 June 2014
  23. Wang, M., Hua, X.S., Hong, R., Tang, J., Qi, G.J., Song, Y.: Unified video annotation via multigraph learning. IEEE Trans. Circuits Systems Video Technol. 19(5), 733鈥?46 (2009) CrossRef
  24. Wang, S.H., Jiang S.Q., Huang, Q.M. and Tian Q.: Multi-feature metric learning with knowledge transfer among semantics and social tagging. IEEE International Conference on Computer Vision and Pattern Recognition (CVPR) (2012)
  25. Petersohn, C.: Fraunhofer HHI at TRECVID 2004: Shot Boundary Detection System. TREC Video Retrieval Evaluation Online Proceedings, TRECVID (2004)
  26. Jiang, S., Zhao, Y., Wei, S.K., Ni, R.R., Zhu, Z.F.: Frame filtering and path verification for improving video copy detection. International Conference on Internet Multimedia Computing and Service (2013)
  27. Barr, J., Bradley, B., Hannigan, B.: Using digital watermarks with image signatures to mitigate the threat of the copy attack. IEEE International Conference on Acoustics Speech and Signal Processing (2003)
  28. Smeaton, A.F., Over, P., Kraaij, W.: Evaluation campaigns and TRECVID. In: ACM International Workshop on Multimedia Information Retrieval, pp. 321鈥?30 (2006)
  
• 刊物类别：Computer Science
• 刊物主题：Multimedia Information Systems
  Computer Communication Networks
  Operating Systems
  Data Storage Representation
  Data Encryption
  Computer Graphics
  
• 出版者：Springer Berlin / Heidelberg
• ISSN：1432-1882

文摘

Recently, the frame fusion based video copy detection scheme provides a possibility to detect copies in a continuous query video stream. However, its computational complexity is high since a large amount of returned reference frames need to be handled by some reference clip reconstruction methods. In addition, dense frame sampling strategies generally used for improving copy localization precision not only further aggravate the computational efficiency but also lead to much more false alarms due to the content redundancy among frames. To alleviate the above problems, a new scheme is proposed for improving the performance of the frame fusion based video copy detection in both efficiency and effectiveness. In particular, the continuous similarity property among neighbor frames is learned for guiding the design of smart frame filtering method so as to greatly reduce the redundancy among frames. Then, two effective path verification schemes, which utilize cross-clip verification strategy, are studied for removing false alarms. The extensive experiments show that the proposed scheme remarkably improves the detection accuracy of the baseline frame fusion scheme and gives a comparable localization accuracy.