Group Feature Selection for Audio-Based Video Genre Classification

  • Gerhard Sageder
  • Maia Zaharieva
  • Christian Breiteneder
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 9516)


The performance of video genre classification approaches strongly depends on the selected feature set. Feature selection requires for expert knowledge and is commonly driven by the underlying data, investigated video genres, and previous experience in related application scenarios. An alteration of the genres of interest results in reconsideration of the employed features by an expert. In this work, we introduce an unsupervised method for the selection of features that efficiently represent the underlying data. Performed experiments in the context of audio-based video genre classification demonstrate the outstanding performance of the proposed approach and its robustness across different video datasets and genres.


Genre classification Group feature selection Audio features 



This work has been partly funded by the Vienna Science and Technology Fund (WWTF) through project ICT12-010. The authors are thankful to Marcus Hudec for pointing our interest towards CCA. The authors would also like to thank Maurizio Montagnuolo from RAI Centre for Research and Technological Innovation for providing the RAI TV dataset.


  1. 1.
    Breiman, L.: Random forests. Mach. Learn. 45(1), 5–32 (2001)zbMATHCrossRefGoogle Scholar
  2. 2.
    Brezeale, D., Cook, D.: Automatic video classification: a survey of the literature. IEEE Trans. Syst. Man Cybern. 38(3), 416–430 (2008)CrossRefGoogle Scholar
  3. 3.
    Cover, T., Hart, P.: Nearest neighbor pattern classification. IEEE Trans. Inf. Theor. 13(1), 21–27 (1967)zbMATHCrossRefGoogle Scholar
  4. 4.
    Dinh, P.Q., Dorai, C., Venkatesh, S.: Video genre categorization using audio wavelet coefficients. In: Asian Conference on Computer Vision (2002)Google Scholar
  5. 5.
    Ekenel, H.K., Semela, T.: Multimodal genre classification of TV programs and YouTube videos. Multimedia Tools Appl. 63(2), 547–567 (2013)CrossRefGoogle Scholar
  6. 6.
    Guo, J., Gurrin, C.: Short user-generated videos classification using accompanied audio categories. In: ACM International Workshop on Audio and Multimedia Methods for Large-scale Video Analysis, pp. 15–20 (2012)Google Scholar
  7. 7.
    Hotelling, H.: Relations between two sets of variates. Biometrika 28, 321–377 (1936)zbMATHCrossRefGoogle Scholar
  8. 8.
    Huang, Y.-F., Wang, S.-H.: Movie genre classification using SVM with audio and video features. In: Huang, R., Ghorbani, A.A., Pasi, G., Yamaguchi, T., Yen, N.Y., Jin, B. (eds.) AMT 2012. LNCS, vol. 7669, pp. 1–10. Springer, Heidelberg (2012) CrossRefGoogle Scholar
  9. 9.
    Jolliffe, I.: Principal Component Analysis. Springer Series in Statistics. Springer, Heidelberg (2002) zbMATHGoogle Scholar
  10. 10.
    Kim, S., Georgiou, P., Narayanan, S.: On-line genre classification of TV programs using audio content. In: IEEE International Conference on Acoustics, Speech and Signal Processing, pp. 798–802 (2013)Google Scholar
  11. 11.
    Mitrovic, D., Zeppelzauer, M., Breiteneder, C.: Features for content-based audio retrieval. Adv. Comput.: Improving Web 78, 71–150 (2010)CrossRefGoogle Scholar
  12. 12.
    Montagnuolo, M., Messina, A.: TV genre classification using multimodal information and multilayer perceptrons. In: Basili, R., Pazienza, M.T. (eds.) AI*IA 2007. LNCS (LNAI), vol. 4733, pp. 730–741. Springer, Heidelberg (2007) CrossRefGoogle Scholar
  13. 13.
    Montagnuolo, M., Messina, A.: Parallel neural networks for multimodal video genre classification. Multimedia Tools Appl. 41(1), 125–159 (2009)CrossRefGoogle Scholar
  14. 14.
    Natarajan, R., Chandrakala, S.: Audio-based event detection in videos - a comprehensive survey. Int. J. Eng. Technol. 6(4), 1663–1674 (2014)Google Scholar
  15. 15.
    Roach, M., Mason, J., Xu, L.Q.: Video genre verification using both acoustic and visual modes. In: IEEE Workshop on Multimedia Signal Processing, pp. 157–160 (2002)Google Scholar
  16. 16.
    Roach, M., Mason, J.: Classification of video genre using audio. Eurospeech 4, 2693–2696 (2001)Google Scholar
  17. 17.
    Rouvier, M., Linares, G., Matrouf, D.: On-the-fly video genre classification by combination of audio features. In: IEEE International Conference on Acoustics Speech and Signal Processing, pp. 45–48 (2010)Google Scholar
  18. 18.
    Rouvier, M., Oger, S., Linares, G., Matrouf, D., Merialdo, B., Li, Y.: Audio-based video genre identification. IEEE/ACM Audio, Speech, Lang. Process. 23(6), 1031–1041 (2015)CrossRefGoogle Scholar
  19. 19.
    Sageder, G., Zaharieva, M., Zeppelzauer, M.: Unsupervised selection of robust audio feature subsets. In: SIAM International Conference on Data Mining, pp. 686–694 (2014)Google Scholar
  20. 20.
    Saz, O., Doulaty, M., Hain, T.: Background-tracking acoustic features for genre identification of broadcast shows. In: IEEE Spoken Language Technology Workshop, pp. 118–123 (2014)Google Scholar
  21. 21.
    Song, Y., Zhao, M., Yagnik, J., Wu, X.: Taxonomic classification for web-based videos. In: IEEE Conference on Computer Vision and Pattern Recognition, pp. 871–878 (2010)Google Scholar
  22. 22.
    Vapnik, V.: Nature Statistical Learning Theory. Springer, Heidelberg (1995) zbMATHCrossRefGoogle Scholar
  23. 23.
    Wu, X., Zhao, W.L., Ngo, C.W.: Towards google challenge: Combining contextual and social information for web video categorization. In: ACM International Conference on Multimedia, pp. 1109–1110 (2009)Google Scholar
  24. 24.
    Zhang, N., Duan, L.Y., Li, L., Huang, Q., Du, J., Gao, W., Guan, L.: A generic approach for systematic analysis of sports videos. ACM Trans. Intell. Syst. Technol. 3(3), 46:1–46:29 (2012)Google Scholar

Copyright information

© Springer International Publishing Switzerland 2016

Authors and Affiliations

  1. 1.Multimedia Information Systems GroupUniversity of ViennaViennaAustria
  2. 2.Interactive Media Systems GroupVienna University of TechnologyViennaAustria

Personalised recommendations