CIVR 2005: Image and Video Retrieval pp 71-81 | Cite as
EMD-Based Video Clip Retrieval by Many-to-Many Matching
Abstract
This paper presents a new approach for video clip retrieval based onEarth Mover’s Distance (EMD). Instead of imposing one-to-one matching constraint as in [11, 14], our approach allows many-to-many matching methodology and is capable of tolerating errors due to video partitioning and various video editing effects. We formulate clip-based retrieval as a graph matching problem in two stages. In the first stage, to allow the matching between a query and a long video, an online clip segmentation algorithm is employed to rapidly locate candidate clips for similarity measure. In the second stage, a weighted graph is constructed to model the similarity between two clips. EMD is proposed to compute the minimum cost of the weighted graph as the similarity between two clips. Experimental results show that the proposed approach is better than some existing methods in term of ranking capability.
Keywords
Video Clip Weighted Graph Optimal Match Video Database Approximate MatchPreview
Unable to display preview. Download preview PDF.
References
- 1.Cheung, S.C., Zakhor, A.: Efficient Video Similarity Measurement with Video Signature. IEEE Trans. on Circuits and Systems for Video Technology 13(1) (January 2003)Google Scholar
- 2.Cheung, S.C., Zakhor, A.: Fast Similarity Search and Clustering of Video Sequences on the World-Wide-Web. IEEE Trans. on Multimedia (2004)Google Scholar
- 3.Hoad, T.C., Zobel, J.: Fast Video Matching with Signature Alignment. In: ACM Int. Workshop on Multimedia Information Retrieval, pp. 262–268 (2003)Google Scholar
- 4.Kashino, K., Kurozumi, T., Murase, H.: A Quick Search Method for Audio and Video Signals based on Histogram Pruning. IEEE Trans. on Multimedia 5(3) (September 2003)Google Scholar
- 5.Naphade, M.R., Yeung, M.M., Yeo, B.L.: A Novel Scheme for Fast and Efficient Video Sequence Matching Using Compact Signatures. In: SPIE: Storage and Retrieval for Media Databases, pp. 564–572 (2000)Google Scholar
- 6.Yuan, J., Duan, L.-Y., Tian, Q., Xu, C.: Fast and Robust Short Video Clip Search Using an Index Structure. In: ACM Int. Workshop on Multimedia Information Retrieval (October 2004)Google Scholar
- 7.Chen, L., Chua, T.S.: A Match and Tiling Approach to Content-based Video Retrieval. In: Int. Conf. on Multimedia and Expo, pp. 417–420 (2001)Google Scholar
- 8.Dimitrova, N., Abdel-Mottaled, M.: Content-based Video Retrieval by Example Video Clip. In: SPIE: Storage and Retrieval of Image and Video Databases VI, vol. 3022, pp. 184–196 (1998)Google Scholar
- 9.Jain, A.K., Vailaya, A., Xiong, W.: Query by Video Clip. Multimedia System 7, 369–384 (1999)CrossRefGoogle Scholar
- 10.Lienhart, R., Effelsberg, W.: A Systematic Method to Compare and Retrieve Video Sequences. Multimedia Tools and applications 10(1) (January 2000)Google Scholar
- 11.Liu, X., Zhuang, Y., Pan, Y.: A New Approach to Retrieve Video by Example Video Clip. In: ACM Multimedia Conf. (1999)Google Scholar
- 12.Wu, Y., Zhuang, Y., Pan, Y.: Content-based Video Similarity Model. In: ACM Multimedia Conf. (2000)Google Scholar
- 13.Tan, Y.P., Kulkarni, S.R., Ramadge, P.J.: A Framework for Measuring Video Similarity and Its Application to Video Query by Example. In: Int. Conf. on Image Processing, vol. 2, pp. 106–110 (1999)Google Scholar
- 14.Peng, Y., Ngo, C.W.: Clip-based Similarity Measure for Hierarchical Video Retrieval. In: ACM Int. Workshop on Multimedia Information Retrieval (October 2004)Google Scholar
- 15.Ngo, C.W., Pong, T.C., Chin, R.T.: Video Partitioning by Temporal Slices Coherency. IEEE Trans. on Circuits and Systems for Video Technology 11(8), 941–953 (2001)CrossRefGoogle Scholar
- 16.Ngo, C.W., Pong, T.C., Zhang, H.J.: Motion-based Video Representation for Scene Change Detection. Int. Journal of Computer Vision 50(2) (November 2002)Google Scholar
- 17.Rubner, Y., Tomasi, C., Guibas, L.: The Earth Mover’s Distance as a Metric for Image Retrieval. Int. Journal of Computer Vision 40(2), 99–121 (2000)MATHCrossRefGoogle Scholar
- 18.MPEG video group. Description of Core Experiments for MPEG-7 Color/Texture Descriptors, ISO/MPEGJTC1/SC29/WG11 MPEG98/M2819 (July 1999)Google Scholar