Horror Video Scene Recognition Based on Multi-view Multi-instance Learning

  • Xinmiao Ding
  • Bing Li
  • Weiming Hu
  • Weihua Xiong
  • Zhenchong Wang
Part of the Lecture Notes in Computer Science book series (LNCS, volume 7726)


Comparing with the research of pornographic content filtering on Web, Web horror content filtering, especially horror video scene recognition is still on the stage of exploration. Most existing methods identify horror scene only from independent frames, ignoring the context cues among frames in a video scene. In this paper, we propose a Multi-view Multi-Instance Leaning (M2IL) model based on joint sparse coding technique that takes the bag of instances from independent view and contextual view into account simultaneously and apply it on horror scene recognition. Experiments on a horror video dataset collected from internet demonstrate that our method’s performance is superior to the other existing algorithms.


Sparse Code High Dimensional Feature Space Video Scene Scene Recognition Multiple Instance Learn 
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. 1.
    Hu, W.M., Wu, O., Chen, Z.: Recognition of pornographic web pages by classifying texts and images. IEEE TPAMI 29, 1019–1034 (2007)CrossRefGoogle Scholar
  2. 2.
    Hanjalic, A., Xu, L.Q.: Affective video content representation and modeling. IEEE TMM 7, 143–154 (2005)Google Scholar
  3. 3.
    Wang, H.L., Cheong, L.: Affective understanding in film. IEEE TCSVT 16, 689–704 (2006)Google Scholar
  4. 4.
    Kang, H.B.: Affective content detection using hmms. ACM MM, 259–262 (2003)Google Scholar
  5. 5.
    Wang, J.C., Li, B., Hu, W.M., et al.: Horror movie scene recognition based on emotional perception. In: ICIP, pp. 1489–1492 (2010)Google Scholar
  6. 6.
    Wang, J.C., Li, B., Hu, W.M., et al.: Horror video scene recognition via mutiple-instance learning. In: ICASSP, pp. 1325–1328 (2011)Google Scholar
  7. 7.
    Wu, B., Jiang, X., Sun, T., Zhang, S., Chu, X., Shen, C., Fan, J.: A Novel Horror Scene Detection Scheme on Revised Multiple Instance Learning Model. In: Lee, K.-T., Tsai, W.-H., Liao, H.-Y.M., Chen, T., Hsieh, J.-W., Tseng, C.-C. (eds.) MMM 2011 Part II. LNCS, vol. 6524, pp. 359–370. Springer, Heidelberg (2011)CrossRefGoogle Scholar
  8. 8.
    Li, B., Xiong, W.H., Hu, W.M.: Web horror image recognition based on context-aware multi-instance learning. In: ICDM, pp. 1158–1163 (2011)Google Scholar
  9. 9.
    Dietterich, T.G., Lathrop, R.H., Lozano-Perez, T.: Solving the multiple-instance problem with axis-parallel rectangles. Artif. Intell. 89, 31–71 (1997)zbMATHCrossRefGoogle Scholar
  10. 10.
    Maron, O., Lozano-Perez, T.: A framework for multiple-instance learning. In: NIPS, pp. 570–576 (1998)Google Scholar
  11. 11.
    Wang, J., Zucker, J.: Solving the multi-instance problem: A lazy learning approach. In: ICML, pp. 1119–1125 (2000)Google Scholar
  12. 12.
    Zhang, Q., Goldman, S.A.: Em-dd: An improved multi-instance learning technique. In: NIPS, pp. 1073–1080 (2002)Google Scholar
  13. 13.
    Gartner, T., Flach, P.A.: A.Kowalczyk, Smola, A.J.: Multi-instance kernels. In: ICML, pp. 179–186 (2002)Google Scholar
  14. 14.
    Andrews, S., Tsochantaridis, I., Hofmann, T.: Support vector machines for multiple instance learning. In: NIPS, pp. 561–568 (2003)Google Scholar
  15. 15.
    Zhou, Z., Xu, J.: On the relation between multi-instance learning and semi-supervised learning. In: ICML, pp. 1167–1174 (2007)Google Scholar
  16. 16.
    Zhou, Z., Sun, Y., Li, Y.: Multi-instance learning by treating instances as non-i.i.d. samples. In: ICML, pp. 1249–1256 (2009)Google Scholar
  17. 17.
    Tenenbaum, J.B., de Silva, V., Langford, J.C.: A global geometric framework for nonlinear dimensionality reduction. Science 290, 2319–2323 (2000)CrossRefGoogle Scholar
  18. 18.
    Yuan, X., Yan., S.: Visual classification with multi-task joint sparse representation. In: CVPR, pp. 3493–3500 (2010)Google Scholar
  19. 19.
    Tseng, P.: On accelerated proximal gradient methods for convex-concave optimization. SIAM Journal of Optimization (2008)Google Scholar
  20. 20.
    Cernekova, Z., Pitas, I., Nikou, C.: Information theory-based shot cut/fade detection and video summarization. IEEE TCSVT 16, 82–91 (2006)Google Scholar
  21. 21.
    Ou, L., Luo, M., Woodcock, A., Wright, A.: A study of colour emotion and colour preference.part i: Colour emotions for single colours. Color Research & Application 29, 232–240 (2004)CrossRefGoogle Scholar
  22. 22.
    Ou, L., Luo, M.: A colour harmony model for two-colour combinations. Color Research & Application 31, 191–204 (2006)Google Scholar
  23. 23.
    Geusebroek, J., Smeulders, A.: A six-stimulus theory for stochastic texture. International Journal of Computer Vision 62, 7–16 (2005)Google Scholar
  24. 24.
    Wang, H.Y., Yang, Q., Zhang, H.: Adaptive p-posterior mixturemodel kernels for multiple instance learning. In: ICML, pp. 1136–1143 (2008)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2013

Authors and Affiliations

  • Xinmiao Ding
    • 1
    • 2
    • 3
  • Bing Li
    • 2
  • Weiming Hu
    • 2
  • Weihua Xiong
    • 2
  • Zhenchong Wang
    • 1
  1. 1.China University of Mining and TechnologyBeijingChina
  2. 2.National Laboratory of Pattern Recognition, Institute of AutomationCASChina
  3. 3.Shandong Institute of Business and TechnologyChina

Personalised recommendations