›› 2013, Vol. 28 ›› Issue (5): 788-796.doi: 10.1007/s11390-013-1377-6

Special Issue: Artificial Intelligence and Pattern Recognition; Computer Graphics and Multimedia; Data Management and Data Mining

• Special Section of CVM2013 • Previous Articles     Next Articles

A Novel Web Video Event Mining Framework with the Integration of Correlation and Co-Occurrence Information

Cheng-De Zhang1 (张承德), Xiao Wu1, * (吴晓), Member, ACM, IEEE Mei-Ling Shyu2, Senior Member, IEEE, and Qiang Peng1 (彭强), Member, ACM   

  1. 1 School of Information Science and Technology, Southwest Jiaotong University, Chengdu 610031, China;
    2 Department of Electrical and Computer Engineering, University of Miami, Coral Gables, FL 33146, U.S.A.
  • Received:2013-05-05 Revised:2013-08-10 Online:2013-09-05 Published:2013-09-05
  • Supported by:

    This work was supported by the National Natural Science Foundation of China under Grant Nos. 61373121, 61071184, 60972111, 61036008, the Research Funds for the Doctoral Program of Higher Education of China under Grant No. 20100184120009, the Program for Sichuan Provincial Science Fund for Distinguished Young Scholars under Grant Nos. 2012JQ0029, 13QNJJ0149, the Fundamental Research Funds for the Central Universities of China under Grant Nos. SWJTU09CX032, SWJTU10CX08, and the Program of China Scholarships Council under Grant No. 201207000050.

The massive web videos prompt an imperative demand on effciently grasping the major events. However, the distinct characteristics of web videos, such as the limited number of features, the noisy text information, and the unavoidable error in near-duplicate keyframes (NDKs) detection, make web video event mining a challenging task. In this paper, we propose a novel four-stage framework to improve the performance of web video event mining. Data preprocessing is the first stage. Multiple Correspondence Analysis (MCA) is then applied to explore the correlation between terms and classes, targeting for bridging the gap between NDKs and high-level semantic concepts. Next, co-occurrence information is used to detect the similarity between NDKs and classes using the NDK-within-video information. Finally, both of them are integrated for web video event mining through negative NDK pruning and positive NDK enhancement. Moreover, both NDKs and terms with relatively low frequencies are treated as useful information in our experiments. Experimental results on large-scale web videos from YouTube demonstrate that the proposed framework outperforms several existing mining methods and obtains good results for web video event mining.

[1] Zhang J, Fan X, Wang J et al. Keyword-propagation-based information enriching and noise removal for web news videos. In Proc. the 18th ACM International Conference on Knowledge Discovery and Data Mining, Aug. 2012, pp.561-569.

[2] Chen K Y, Luesukprasert L, Chou S et al. Hot topic extraction based on timeline analysis and multidimensional sentence modeling. IEEE Transactions on Knowledge and Data Engineering, 2007, 19(8): 1016-1025.

[3] Fung G P C , Yu J X, Liu H et al. Time-dependent event hierarchy construction. In Proc. the 13th Int. Conf. Knowledge Discovery and Data Mining, Aug. 2007, pp.300-309.

[4] Fung G P C, Yu J X, Yu P S et al. Parameter free bursty events detection in text streams. In Proc. the 31st Int. Conf. Very Large Data Bases, Aug. 2005, pp.181-192.

[5] He Q, Chang K, Lim E P. Analyzing feature trajectories for event detection. In Proc. the 30th ACM Int. Conf. Research and Develop. in Inform. Retrieval, Aug. 2007, pp.207-214.

[6] Wang X, Zhai C, Hu X et al. Mining correlated bursty topic patterns from coordinated text streams. In Proc. the 13th ACM International Conference on Knowledge Discovery and Data Mining, Aug. 2007, pp.784-793.

[7] Yao J, Cui B, Huang Y et al. Bursty event detection from collaborative tags. World Wide Web, 2012, 15(2): 171-195.

[8] Tan S, Tan H K, Ngo C W. Topical summarization of web videos by visual-text time-dependent alignment. In Proc. the ACM Int. Conf. Multimedia, Oct. 2010, pp.1095-1098.

[9] Wu X, Zhao W L, Ngo C W. Near-duplicate keyframe retrieval with visual keywords and semantic context. In Proc. the 6th ACM International Conference on Image and Video Retrieval, July 2007, pp.162-169.

[10] Ke Y, Sukthankar R, Huston L. Effcient near-duplicate detection and sub-image retrieval. In Proc. the ACM Int. Conf. Multimedia, 2004, Vol.4, pp.869-876.

[11] Ngo C W, Zhao W L, Jiang Y G. Fast tracking of nearduplicate keyframes in broadcast domain with transitivity propagation. In Proc. the 14th ACM International Conference on Multimedia, Oct. 2006, pp.845-854.

[12] Zhang D Q, Chang S F. Detecting image near-duplicate by stochastic attributed relational graph matching with learning. In Proc. the 12th ACM International Conference on Multimedia, Oct. 2004, pp.877-884.

[13] Wu X, Ngo C W, Hauptmann A G. Multimodal news story clustering with pairwise visual near-duplicate constraint. IEEE Transactions on Multimedia, 2008, 10(2): 188-199.

[14] Wu X, Ngo C W, Li Q. Threading and autodocumenting news videos: A promising solution to rapidly browse news topics. IEEE Signal Processing Magazine, 2006, 23(2): 59-68.

[15] Martinez-Gil J, Aldana-Montes J. KnoE: A web mining tool to validate previously discovered semantic correspondences. Journal of Computer Science and Technology, 2012, 27(6): 1222-1232.

[16] Lu B, Wang G R, Yuan Y. A novel approach towards large scale cross-media retrieval. Journal of Computer Science and Technology, 2012, 27(6): 1140-1149.

[17] Feng B L, Cao J, Bao X G et al. Graph-based multi-space semantic correlation propagation for video retrieval. The Visual Computer, 2011, 27(1): 21-34.

[18] Hsu W H, Chang S F. Topic tracking across broadcast news videos with visual duplicates and semantic concepts. In Proc. the 2006 IEEE International Conference on Image Processing, Oct. 2006, pp.141-144.

[19] Liu D T, Shyu M L, Chen C et al. Within and between shot information utilisation in video key frame extraction. Journal of Information & Knowledge Management, 2011, 10(3): 247-259.

[20] Meng T, Shyu M L. Leveraging concept association network for multimedia rare concept mining and retrieval. In Proc. the 2012 IEEE International Conference on Multimedia & Expo, July 2012, pp.860-865.

[21] Cao J, Ngo C W, Zhang Y D et al. Tracking web video topics: Discovery, visualization, and monitoring. IEEE Trans. Circuits and Systems for Video Technology, 2011, 21(12): 18351846.

[22] Duygulu P, Pan J Y, Forsyth D A. Towards autodocumentary: Tracking the evolution of news stories. In Proc. the 12th ACM Int. Conf. Multimedia, Oct. 2004, pp.820-827.

[23] Zhai Y, Shah M. Tracking news stories across different sources. In Proc. the 13th ACM International Conference on Multimedia, Nov. 2005, pp.2-10.

[24] Liu L, Sun L, Rui Y et al. Web video topic discovery and tracking via bipartite graph reinforcement model. In Proc. of the 17th ACM International Conference on World Wide Web, Apr. 2008, pp.1009-1018.

[25] Wu X, Lu Y J, Peng Q et al. Mining event structures from web videos. IEEE Multimedia, 2011, 18(1): 38-51.

[26] Hu S M, Chen T, Xu K et al. Internet visual media processing: A survey with graphics and vision applications. The Visual Computer, 2013, 29(5): 393-405.

[27] Parry M L, Legg P A, Chung D H et al. Hierarchical event selection for video storyboards with a case study on snooker video visualization. IEEE Transactions on Visualization and Computer Graphics, 2011, 17(12): 1747-1756.

[28] Lin L, Ravitz G, Shyu M L et al. Correlation-based video semantic concept detection using multiple correspondence analysis. In Proc. the 10th IEEE International Symposium on Multimedia, Dec. 2008, pp.316-321.

[29] Salkind N J. Encyclopedia of Measurement and Statistics. SAGA Publications, Inc., 2006.

[30] Kennedy L S, Naaman M. Generating diverse and representative image search results for landmarks. In Proc. the 17th ACM International Conference on World Wide Web, Apr. 2008, pp.297-306.

[31] Zhu Q S, Lin L, Shyu M L et al. Utilizing context information to enhance content-based image classification. International Journal of Multimedia Data Engineering and Management, 2011, 2(3): 34-51.

[32] Lin L, Chen C, Shyu M L et al. Weighted subspace filtering and ranking algorithms for video concept retrieval. IEEE Multimedia, 2011, 18(3): 32-43.

[33] Lowe D G. Distinctive image features from scale-invariant keypoints. International Journal of Computer Vision, 2004, 60(2): 91-110.

[34] Zhao W L, Wu X, Ngo C W. On the annotation of web videos by effcient near-duplicate search. IEEE Transactions on Multimedia, 2010, 12(5): 448-461.
No related articles found!
Full text



[1] Liu Mingye; Hong Enyu;. Some Covering Problems and Their Solutions in Automatic Logic Synthesis Systems[J]. , 1986, 1(2): 83 -92 .
[2] Chen Shihua;. On the Structure of (Weak) Inverses of an (Weakly) Invertible Finite Automaton[J]. , 1986, 1(3): 92 -100 .
[3] Gao Qingshi; Zhang Xiang; Yang Shufan; Chen Shuqing;. Vector Computer 757[J]. , 1986, 1(3): 1 -14 .
[4] Chen Zhaoxiong; Gao Qingshi;. A Substitution Based Model for the Implementation of PROLOG——The Design and Implementation of LPROLOG[J]. , 1986, 1(4): 17 -26 .
[5] Huang Heyan;. A Parallel Implementation Model of HPARLOG[J]. , 1986, 1(4): 27 -38 .
[6] Min Yinghua; Han Zhide;. A Built-in Test Pattern Generator[J]. , 1986, 1(4): 62 -74 .
[7] Tang Tonggao; Zhao Zhaokeng;. Stack Method in Program Semantics[J]. , 1987, 2(1): 51 -63 .
[8] Min Yinghua;. Easy Test Generation PLAs[J]. , 1987, 2(1): 72 -80 .
[9] Zhu Hong;. Some Mathematical Properties of the Functional Programming Language FP[J]. , 1987, 2(3): 202 -216 .
[10] Li Minghui;. CAD System of Microprogrammed Digital Systems[J]. , 1987, 2(3): 226 -235 .

ISSN 1000-9000(Print)

CN 11-2296/TP

Editorial Board
Author Guidelines
Journal of Computer Science and Technology
Institute of Computing Technology, Chinese Academy of Sciences
P.O. Box 2704, Beijing 100190 P.R. China
E-mail: jcst@ict.ac.cn
  Copyright ©2015 JCST, All Rights Reserved