Advertisement

MAPACo-Training: A Novel Online Learning Algorithm of Behavior Models

  • Heping Li
  • Zhanyi Hu
  • Yihong Wu
  • Fuchao Wu
Part of the Lecture Notes in Computer Science book series (LNCS, volume 4843)

Abstract

The traditional co-training algorithm, which needs a great number of unlabeled examples in advance and then trains classifiers by iterative learning approach, is not suitable for online learning of classifiers. To overcome this barrier, we propose a novel semi-supervised learning algorithm, called MAPACo-Training, by combining the co-training with the principle of Maximum A Posteriori adaptation. This MAPACo-Training algorithm is an online multi-class learning algorithm, and has been successfully applied to online learning of behaviors modeled by Hidden Markov Model. The proposed algorithm is tested with the Li’s database as well as Schuldt’s dataset.

Keywords

Hide Markov Model IEEE Computer Society Gaussian Mixture Model False Acceptance Rate View Versus 
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.
    Li, H., Greenspan, M.: Multi-scale gesture recognition from time-Varying contours. In: IEEE Int’l Conf. On Computer Vision, pp. 236–243. IEEE Computer Society Press, Los Alamitos (2005)Google Scholar
  2. 2.
    Gong, S.G., Xiang, T.: Recognition of group activities using dynamic probabilistic networks. In: IEEE Int’l Conf. On Computer Vision, pp. 742–749. IEEE Computer Society Press, Los Alamitos (2003)CrossRefGoogle Scholar
  3. 3.
    Bobick, A.F., Davis, J.W.: The recognition of human movement using temporal templates. IEEE Trans. on Pattern Analysis and Machine Intelligence 23, 257–267 (2001)CrossRefGoogle Scholar
  4. 4.
    Laptev, I., Linderberg, T.: Space-time interest points. In: IEEE Int’l Conf. On Computer Vision, pp. 432–439. IEEE Computer Society Press, Los Alamitos (2003)CrossRefGoogle Scholar
  5. 5.
    Xiang, T., Gong, S.G.: Video behaviour profiling and abnormality detection without manual labeling. In: IEEE Int’l Conf. On Computer Vision, pp. 1238–1245. IEEE Computer Society Press, Los Alamitos (2005)CrossRefGoogle Scholar
  6. 6.
    Zelnik-Manor, L., Irani, M.: Event-based analysis of video. In: IEEE Conf. on Computer Vision and  Pattern Recognition, pp. 123–130. IEEE Computer Society Press, Los Alamitos (2001)Google Scholar
  7. 7.
    Zhong, H., Shi, J., Visontai, M.: Detecting unusual activity in video. In: IEEE Conf. on Computer Vision and Pattern Recognition, pp. 819–826. IEEE Computer Society Press, Los Alamitos (2004)Google Scholar
  8. 8.
    Zhang, D., Gatica-Perez, D., Bengio, S., McCowan, I.: Semi-supervised adapted HMMs for unusual event detection. In: IEEE Conf. on Computer Vision and Pattern Recognition, pp. 611–618. IEEE Computer Society Press, Los Alamitos (2005)Google Scholar
  9. 9.
    Blum, A., Mitchell, T.: Combining labeled and unlabeled data with co-training. In: 11th Annual Conference on Computational Learning Theory (1998)Google Scholar
  10. 10.
    Levin, A., Viola, P., Freund, Y.: Unsupervised improvement of visual detectors using co-training. In: IEEE Int’l Conf. On Computer Vision, pp. 626–633. IEEE Computer Society Press, Los Alamitos (2003)CrossRefGoogle Scholar
  11. 11.
    Yan, R., Naphade, M.: Semi-supervised cross feature learning for semantic concept detection in videos. In: IEEE Conf. on Computer Vision and Pattern Recognition, pp. 657–663. IEEE Computer Society Press, Los Alamitos (2005)Google Scholar
  12. 12.
    Javed, O., Ali, S., Shah, M.: Online detection and classification of moving objects using progressively improving detectors. In: IEEE Conf. on Computer Vision and Pattern Recognition, pp. 696–701. IEEE Computer Society Press, Los Alamitos (2005)Google Scholar
  13. 13.
    Reynolds, D.A., Quatieri, T.F., Dumn, R.B.: Speaker verification using adapted Gauusian mixture models. Digital Signal Processing 10, 19–41 (2000)CrossRefGoogle Scholar
  14. 14.
    Lucas, B.D., Kanade, T.: An iterative image registration technique with an application to stereo vision. In: DARPA Image Understanding Workshop (April 1981)Google Scholar
  15. 15.
    Lv, F., Nevatia, R.: Recognition and segmentation of 3-D human action using HMM and multi-class adaboost. In: Proc. European Conference on Computer Vision, vol. IV, pp. 359–372 (2006)Google Scholar
  16. 16.
    Zhang, D., Gatica-Perez, D., Bengio, S.: Semi-supervised meeting event recognition with adapted HMMs. In: ICME. IEEE International Conference on Multimedia Expo (2005)Google Scholar
  17. 17.
    Li, H., Hu, Z., Wu, Y., Wu, F.: Behavior modeling and recognition based on space-time image features. In: International Conference on Pattern Recognition, vol. 1, pp. 243–246 (2006)Google Scholar
  18. 18.
    Schuldt, C., Laptev, I., Caputo, B.: Recognizing human actions: a local SVM approach. In: International Conference on Pattern Recognition, vol. 3, pp. 32–36 (2004)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2007

Authors and Affiliations

  • Heping Li
    • 1
    • 2
  • Zhanyi Hu
    • 1
  • Yihong Wu
    • 1
  • Fuchao Wu
    • 1
  1. 1.National Laboratory of Pattern Recognition 
  2. 2.Digital Content Technology Research Center, Institute of Automation,Chinese Academy of Sciences, P.O. 2728, Beijing 100080P.R.China

Personalised recommendations