Advertisement

Combining Audio and Video by Dominance in Bimodal Emotion Recognition

  • Lixing Huang
  • Le Xin
  • Liyue Zhao
  • Jianhua Tao
Part of the Lecture Notes in Computer Science book series (LNCS, volume 4738)

Abstract

We propose a novel bimodal emotion recognition approach by using the boosting-based framework, in which we can automatically determine the adaptive weights for audio and visual features. In this way, we balance the dominances of audio and visual features dynamically in feature-level to obtain better performance.

References

  1. 1.
    Huang, T.S., Chen, L., Tao, H.: Bimodal emotion recognition by man and machine. In: Proc. ATR Workshop on Virtual Communication Environments, Japan (April 1998)Google Scholar
  2. 2.
    Schapire, R.E., Singer, Y.: Improved boosting algorithms using confidence-rated prediction. Machine Learning 37, 297–336 (1999)zbMATHCrossRefGoogle Scholar
  3. 3.
    Silva, D., Miyasato, T., Nakatsu, R.: Facial emotion recognition using multi-modal information. In: Proc. International Conference on Information and Communications Security, pp. 397–401 (1997)Google Scholar
  4. 4.
    Chen, C.Y., Huang, Y.K., Cook, P.: Visual/Acoustic emotion recognition. In: Proc. International Conference on Multimedia and Expo, pp. 1468–1471 (2005)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2007

Authors and Affiliations

  • Lixing Huang
    • 1
  • Le Xin
    • 1
  • Liyue Zhao
    • 1
  • Jianhua Tao
    • 1
  1. 1.National Laboratory of Pattern Recognition (NLPR), Institute of Automation, Chinese Academy of Sciences 

Personalised recommendations