DTTM: A Discriminative Temporal Topic Model for Facial Expression Recognition

  • Lifeng Shang
  • Kwok-Ping Chan
  • Guodong Pan
Part of the Lecture Notes in Computer Science book series (LNCS, volume 6938)

Abstract

This paper presents a discriminative temporal topic model (DTTM) for facial expression recognition. Our DTTM is developed by introducing temporal and categorical information into Latent Dirichlet Allocation (LDA) topic model. Temporal information is integrated by placing an asymmetric Dirichlet prior over document-topic distributions. The discriminative ability is improved by a supervised term weighting scheme. We describe the resulting DTTM in detail and show how it can be applied to facial expression recognition. Experiments on CMU expression database illustrate that the proposed DTTM is very effective in facial expression recognition.

Keywords

Facial Expression Topic Model Latent Dirichlet Allocation Facial Expression Recognition Active Appearance Model 
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.

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. 1.
    Blei, D., Ng, A., Jordan, M.: Latent dirichlet allocation. JMLR 3(2-3), 993–1022 (2003)MATHGoogle Scholar
  2. 2.
    Blei, D., Lafferty, J.D.: Dynamic topic models. In: ICML (2006)Google Scholar
  3. 3.
    Blei, D., McAuliffe, J.D.: Supervised topic models. In: NIPS, pp. 121–128 (2007)Google Scholar
  4. 4.
    Chang, Y., Hu, C., Turk, M.: Probabilistic expression analysis on manifolds. In: CVPR, pp. 520–527 (2004)Google Scholar
  5. 5.
    Cootes, T.F., Edwards, G.J., Taylor, C.J.: Active appearance models. IEEE Trans. on PAMI 23(6), 681–685 (2001)CrossRefGoogle Scholar
  6. 6.
    Debole, F. and Sebastiani, F.: Supervised term weighting for automated text categorization. In: ACM SAC, pp. 784–788 (2003)Google Scholar
  7. 7.
    Ekman, P., Friesen, W.V.: Facial Action Coding System (FACS): Manual. Consulting Psychologists Press, Palo Alto (1978)Google Scholar
  8. 8.
    Fei-Fei, L., Perona, P.: A bayesian hierarchical model for learning natural scene categories. In: CVPR, pp. 524–531 (2005)Google Scholar
  9. 9.
    Griffiths, T.L., Steyvers, M.: Finding scientific topics. PNAS 101, 5228–5235 (2004)CrossRefGoogle Scholar
  10. 10.
    Kanade, T., Cohn, J.F., Tian, Y.: Comprehensive database for facial expression analysis. In: FG, pp. 46–53 (2000)Google Scholar
  11. 11.
    Lacoste-Julien, S., Sha, F., Jordan, M.I.: DiscLDA: Discriminative learning for dimensionality reduction and classification. In: NIPS, pp. 897–904 (2008)Google Scholar
  12. 12.
    Shang, L., Chan, K.P.: A temporal latent topic model for facial expression recognition. In: Kimmel, R., Klette, R., Sugimoto, A. (eds.) ACCV 2010, Part IV. LNCS, vol. 6495, pp. 51–63. Springer, Heidelberg (2011)CrossRefGoogle Scholar
  13. 13.
    Steyvers, M., Smyth, P., Rosen-Zvi, M., Griffiths, T.: Probabilistic Author-Topic Models for Information Discovery. In: KDD, pp. 306–315 (2004)Google Scholar
  14. 14.
    Wang, X., Grimson, E.: Spatial latent dirichlet allocation. In: NIPS (2007)Google Scholar
  15. 15.
    Wang, C., Blei, D., Heckerman, D.: Continuous time dynamic topic models. In: UAI (2008)Google Scholar
  16. 16.
    Wang, X., McCallum, A.: Topics over time: A non-Markov continuous-time model of topical trends. In: SIGKDD (2006)Google Scholar
  17. 17.
    Wei, X., Sun, J., Wang, X.: Dynamic mixture models for multiple time-series. In: IJCAI, pp. 2909–2914 (2007)Google Scholar
  18. 18.
    Wilson, A.T., Chew, P.A.: Term weighting schmes for latent Dirichlet allocation. In: NAACL, pp. 465–473 (2010)Google Scholar
  19. 19.
    Zhou, M., Liang, L., Sun, J., Wang, Y.: AAM based face tracking with temporal matching and face segmentation. In: CVPR, pp. 701-708 (2010)Google Scholar
  20. 20.
    Zhu, J., Ahmed, A., Xing, E.P.: MedLDA: Maximum margin supervised topic models for regression and classification. In: ICML (2009)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2011

Authors and Affiliations

  • Lifeng Shang
    • 1
  • Kwok-Ping Chan
    • 1
  • Guodong Pan
    • 1
  1. 1.The University of Hong KongPokfulamHong Kong

Personalised recommendations