Advertisement

Multimedia Systems

, Volume 22, Issue 1, pp 115–125 | Cite as

Online web video topic detection and tracking with semi-supervised learning

  • Guorong LiEmail author
  • Shuqiang Jiang
  • Weigang ZhangEmail author
  • Junbiao Pang
  • Qingming HuangEmail author
Special Issue Paper

Abstract

With the pervasiveness of online social media and rapid growth of web data, a large amount of multi-media data is available online. However, how to organize them for facilitating users’ experience and government supervision remains a problem yet to be seriously investigated. Topic detection and tracking, which has been a hot research topic for decades, could cluster web videos into different topics according to their semantic content. However, how to online discover topic and track them from web videos and images has not been fully discussed. In this paper, we formulate topic detection and tracking as an online tracking, detection and learning problem. First, by learning from historical data including labeled data and plenty of unlabeled data using semi-supervised multi-class multi-feature method, we obtain a topic tracker which could also discover novel topics from the new stream data. Second, when new data arrives, an online updating method is developed to make topic tracker adaptable to the evolution of the stream data. We conduct experiments on public dataset to evaluate the performance of the proposed method and the results demonstrate its effectiveness for topic detection and tracking.

Keywords

Topic detection and tracking Web video Multi-feature fusion Semi-supervised learning 

Notes

Acknowledgments

This work was supported by China Postdoctoral Science Foundation: 2012M520436, in part by National Basic Research Program of China (973 Program): 2012CB316400, National Natural Science Foundation of China: 61303153, 61025011, 61332016, 61322212, 61202234 and 61202322, Present Foundation of UCAS.

References

  1. 1.
    Xie, L., Natsev, A., Kender, J.R., Hill, M., Smith, J.R.: Visual memes in social media: tracking real-world news in youtube videos. In: Proceedings of the 19th ACM International Conference on Multimedia, MM ’11, pp. 53–62 (2011)Google Scholar
  2. 2.
    Allan, J., Carbonell, J., Doddington, G., Yamron, J., Yang, Y.: Topic detection and tracking pilot study final report (1998)Google Scholar
  3. 3.
    Chen, K., Luesukprasert, L., Chou, S.: Hot topic extraction based on timeline analysis and multi-dimensional sentence modeling. IEEE Trans. Knowl. Data Eng. 19(8), 1016–1025 (2007)CrossRefGoogle Scholar
  4. 4.
    Sun, A.X., Hu, M.: Query-guided event detection from news and blog streams. IEEE Trans. Syst. Man Cybern. 41(5), 834–839 (2011)CrossRefGoogle Scholar
  5. 5.
    Zhai, Y., Shah, M.: Tracking news stories across different sources. In: Proceedings of the 20th ACM International Conference on Multimedia, MM ’05, pp. 2–10. ACM (2005)Google Scholar
  6. 6.
    Wu, Z.L., Li, C.h.: Topic detection in online discussion using non-negative matrix factorization. In: Proceedings of the 2007 IEEE/WIC/ACM International Conferences on Web Intelligence and Intelligent Agent Technology-Workshops, WI-IATW ’07, pp. 272–275 (2007)Google Scholar
  7. 7.
    Kasiviswanathan, S.P., Melville, P., Banerjee, A., Sindhwani, V.: Emerging topic detection using dictionary learning. In: Proceedings of the 20th ACM International Conference on Information and Knowledge Management, CIKM ’11, pp. 745–754. ACM (2011)Google Scholar
  8. 8.
    Aiello, L.M., Petkos, G., Corney, D., Papadopoulos, S., Skraba, R., Goker, A., Kompatsiaris, Y., Jaimes, A.: Sensing trending topics in twitter. IEEE Trans. Multimed. 33(4), 410–419 (2013)Google Scholar
  9. 9.
    Kim, D., Kim, D., Hwang, E., Rho, S.: Twittertrends: a spatio-temporal trend detection and related keywords recommendation scheme. Multimed. Syst. 1–14 (2013)Google Scholar
  10. 10.
    Yeh, Y.R., Chung, Y.Y., Wang, Y.F.: A novel multiple kernel learning framework for heterogeneous feature fusion and variable selection. IEEE Trans. Multimed. 14(3), 563–574 (2012)CrossRefGoogle Scholar
  11. 11.
    Li, H.J., Wang, X.H., Tang, J.H., Zhao, C.X.: Combining global and local matching of multiple features fro precise item image retrieval. Multimed. Syst. 19, 37–49 (2013)CrossRefGoogle Scholar
  12. 12.
    Ma, Z.G., Yang, Y., Xu, Z.W., Yan, S.C., Sebe, N., Hauptmann, A.G.: Complex event detection via multi-source video attributes. In: Proceedings of IEEE Conference on Computer Vision and Pattern Recognition, CVPR (2013)Google Scholar
  13. 13.
    Xu, Z.W., Yang, Y., Tsang, I., Sebe, N., Hauptmann, A.G.: Feature weighting via optimal thresholding for video analysis. In: Proceedings of Intenational Conference on Computer Vision, ICCV (2013)Google Scholar
  14. 14.
    Bao, B.K., Min, W., Sang, J., Xu, C.: Multimedia news digger on emerging topics from social streams. In: Proceedings of the 20th ACM International Conference on Multimedia, MM ’12, pp. 1357–1358 (2012)Google Scholar
  15. 15.
    Liu, K., Xu, J., Zhang, L., Ding, Z., Li, M.: Discovering hot topics from geo-tagged video. Neurocomputing 105, 90–99 (2013)CrossRefGoogle Scholar
  16. 16.
    Shao, J., Ma, S., Lu, W., Zhuang, Y.: A unified framework for web video topic discovery and visualization. Pattern Recognit. Lett. 33(4), 410–419 (2012)CrossRefGoogle Scholar
  17. 17.
    Hong, R., Tang, J., Tan, H., Ngo, C., Yan, S., Chua, T.: Beyond search: event driven summarization for web videos. ACM Trans. Multimed. Comput. Commun. Appl. 33(4), 410–419 (2011)Google Scholar
  18. 18.
    Cao, J., Ngo, C.W., Zhang, Y.D., Li, J.T.: Tracking web video topics: discovery, visualization, and monitoring. IEEE Trans. Circuits Syst. Video Technol. 21(12), 1835–1846 (2011)CrossRefGoogle Scholar
  19. 19.
    Chen, T., Liu, C., Huang, Q.: An effective multi-clue fusion approach for web video topic detection. In: Proceedings of the 20th ACM International Conference on Multimedia, MM ’12, pp. 781–784 (2012)Google Scholar
  20. 20.
    Yang, Y., Song, J., Huang, Z., Ma, Z., Sebe, N., Hauptmann, A.: Multi-feature fusion via hierarchical regression for multimedia analysis. IEEE Trans. Multimed. 15(3), 572–581 (2013)CrossRefGoogle Scholar
  21. 21.
    McDonald, K., Smeaton, A.F.: A comparison of score, rank and probability-based fusion methods for video shot retrieval. In: Proceedings of the 4th International Conference on Image and Video Retrieval, CIVR’05, pp. 61–70 (2005)Google Scholar
  22. 22.
    Fu, Z., Ip, H.H.S., Lu, H., Lu, Z.: Multi-modal constraint propagation for heterogeneous image clustering. In: Candan, K.S., Panchanathan, S., Prabhakaran, B., Sundaram, H., Chi Feng, W., Sebe, N. (eds.) ACM Multimedia, pp. 143–152. ACM (2011)Google Scholar
  23. 23.
    Zhang, Y., Li, G., Chu, L., Wang, S., Zhang, W., Huang, Q.: Cross-media topic detection: a multi-modality fusion framework. In: Proceedings of the International Conference on Multimedia (2013)Google Scholar
  24. 24.
    Adams, W.H., Iyengar, G., Naphade, M.R., Neti, C., Nock, H.J., Smith, J.R.: Semantic indexing of multimedia content using visual, audio and text cues. EURASIP J. Appl. Signal Process. 2, 170–185 (2003)CrossRefGoogle Scholar
  25. 25.
    Papandreou, G., Katsamanis, A., Pitsikalis, V., Maragos, P.: Adaptive multimodal fusion by uncertainty compensation with application to audiovisual speech recognition. IEEE Trans. Audio Speech Lang. Process. 17(3), 423–435 (2009)CrossRefGoogle Scholar
  26. 26.
    Poh, N., Bengio, S.: How do correlation and variance of base-experts affect fusion in biometric authentication tasks? IEEE Trans. Signal Process. 53(11), 4384–4396 (2005)CrossRefMathSciNetGoogle Scholar
  27. 27.
    Ding, C., He, X.: K-means clustering via principal component analysis. In: Proceedings of the Twenty-first International Conference on Machine learning, ICML ’04, pp. 29–36 (2004)Google Scholar
  28. 28.
    Xue, Z., Jiang, S., Li, G., Huang, Q., Zhang, W.: Cross-media topic detection associated with hot search queries. In: Proceedings of the Fifth International Conference on Internet Multimedia Computing and Service, ICIMCS ’13, pp. 403–406 (2013)Google Scholar
  29. 29.
    Saha, A., Sindhwani, V.: Dynamic nmfs with temporal regularization for online analysis of streaming text. In: Proceedings of NIPS Workshop on Machine Learning for Social Computing, pp. 1C8 (2010)Google Scholar
  30. 30.
    AlSumait, L., Barbara, D., Domeniconi, C.: On-line lda: adaptive topic models for mining text streams with applications to topic detection and tracking. In: Eighth IEEE International Conference on Data Mining, ICDM ’08, pp. 3–12 (2008)Google Scholar
  31. 31.
    Hoffman, M., Blei, D.M., Bach, F.: Online learning for latent Dirichlet allocation. In: NIPS (2010)Google Scholar
  32. 32.
    Dai, X.Y., Chen, Q.C., Wang, X.L., Xu, J.: Online topic detection and tracking of financial news based on hierarchical clustering. In: International Conference on Machine Learning and Cybernetics, ICMLC, vol. 6, pp. 3341–3346 (2010)Google Scholar
  33. 33.
    Freund, Y., Schapire, R.: A decision theoretic generalization of on-line learning and an application to boosting. J. Comput. Syst. Sci. 55(1), 119–139 (1997)CrossRefMathSciNetzbMATHGoogle Scholar
  34. 34.
    Hastie, T., Simard, P.: Models and metrics for handwritten character recognition. Stat. Sci. 13(1), 54–65 (1998)CrossRefzbMATHGoogle Scholar
  35. 35.
    Yang, Y., Xu, D., Nie, F.P.: Ranking with local regression and global aignment for cross media retrieval. In: Proceedings of the 17th ACM International Conference on Multimedia, MM ’09, pp. 175–184 (2009)Google Scholar
  36. 36.
    Cao, J., Zhang, Y., Song, Y., Chen, Z., Zhang, X., Li, J.: Mcg-webv: a benchmark dataset for web video analysis. Technical Report, MCG-ICT-CAS-09-001 (2009)Google Scholar
  37. 37.
    Picard, R.R., Cook, R.D.: Cross-validation of regression models. J. Am. Stat. Assoc. 79(387), 575–583 (1984)CrossRefMathSciNetzbMATHGoogle Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2014

Authors and Affiliations

  1. 1.School of Computer and Control EngineeringUniversity of the Chinese Academy of SciencesBeijingChina
  2. 2.Key Lab of Intelligent Information Processing of Chinese Academy of Sciences (CAS)Institute of Computing Technology, CASBeijingChina
  3. 3.School of Computer Science and TechnologyHarbin Institute of TechnologyHarbinChina
  4. 4.Beijing Municipal Key Laboratory of Multimedia and Intelligent Software TechnologyBeijing University of TechnologyBeijingChina

Personalised recommendations