One-Sequence Learning of Human Actions

  • Carlos Orrite
  • Mario Rodríguez
  • Miguel Montañés
Part of the Lecture Notes in Computer Science book series (LNCS, volume 7065)


In this paper we address the problem of human action recognition from a single training sequence per class using a modified version of the Hidden Markov Model. Inspired by codebook approaches in object and scene categorization, we first construct a codebook of possible discrete observations by applying a clustering algorithm to all samples from all classes. The number of clusters defines the size of the codebook. Given a new observation, we assign to it a probability to belong to every cluster, i.e., to correspond to a discrete value of the codebook. In this sense, we change the ‘winner takes all’ rule in the discrete-observation HMM for a distributed probability of membership. It implies the modification of the Baum-Welch algorithm for training discrete HMM to be able to deal with fuzzy observations. We compare our approach with other models such as, dynamic time warping (DTW), continuous-observation HMM, Conditional Random Fields (CRF) and Hidden Conditional Random Fields (HCRF) for human action recognition.


Hide Markov Model Training Sequence Dynamic Time Warping Conditional Random Field Human Action Recognition 
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.
    Huda, S., Yearwood, J., Togneri, R.: A Constraint-Based Evolutionary Learning Approach to the Expectation Maximization for Optimal Estimation of the Hidden Markov Model for Speech Signal Modelling. IEEE Trans. Syst., Man, Cyber. B, Cybern. 39(1), 182–197 (2009)CrossRefGoogle Scholar
  2. 2.
    Quattoni, A., Wang, S.B., Morency, L.-P., Collins, M., Darrell, T.: Hidden Conditional Random Fields. IEEE Transactions on Pattern Analysis and Machine Intelligence 29(10), 1848–1852 (2007)CrossRefGoogle Scholar
  3. 3.
    Lafferty, J., McCallum, A., Pereira, F.: Conditional Random Fields: Probabilistic Models for Segmenting and Labeling Sequence Data. In: Proceedings 18th International Conf. on Machine Learning, pp. 282–289 (2001)Google Scholar
  4. 4.
    Gunawardana, A., Mahajan, M., Acero, A., Platt, J.C.: Hidden conditional random fields for phone classification. In: International Conference on Speech Communication and Technology, pp. 1117–1120 (2005)Google Scholar
  5. 5.
    Zhang, J., Gong, S.: Action categorization with modified hidden conditional random field. Pattern Recognition 43(1), 197–203 (2010)CrossRefzbMATHGoogle Scholar
  6. 6.
    Fei-Fei, L., Fergus, R., Perona, P.: One-Shot Learning of Object Categories. IEEE Transactions on Pattern Analysis and Machine Intelligence 28, 594–611 (2006)CrossRefGoogle Scholar
  7. 7.
    Yang, W., Wang, Y., Mori, G.: Human Action Recognition from a Single Clip per Action. In: 2nd International Workshop on Machine Learning for Vision-based Motion Analysis (2009)Google Scholar
  8. 8.
    Seo, H.J., Milanfar, P.: Action Recognition from One Example. IEEE Transactions on Pattern Analysis and Machine Intelligence 33(5), 867–882 (2011)CrossRefGoogle Scholar
  9. 9.
    Ryoo, M.S., Yu, W.: One Video is Sufficient? Human Activity Recognition Using Active Video Composition. In: WACV 2011 (2011)Google Scholar
  10. 10.
    Liang, Y.-M., Shih, S.-W., Shih, A.C.-C., Liao, H.-Y.M., Lin, C.-C.: Learning Atomic Human Actions Using Variable-Length Markov Models. IEEE Trans. Syst., Man, Cyber. B, Cybern. 39(1), 268–280 (2009)CrossRefGoogle Scholar
  11. 11.
    Niebles, J.C., Wang, H., Fei-Fei, L.: Unsupervised Learning of Human Action Categories Using Spatial-Temporal Words. IJCV 79(3) (September 2008)Google Scholar
  12. 12.
    Schuldt, C., Laptev, I., Caputo, B.: Recognizing Human Actions: a Local SVM Approach. In: ICPR 2004 (2004)Google Scholar
  13. 13.
    Dollar, P., Rabaud, V., Cottrell, G., Belongie, S.: Behavior Recognition via Sparse Spatio- Temporal Features. In: IEEE Workshop on VS-PETS 2005 (2005)Google Scholar
  14. 14.
    Bobick, A.F., Davis, J.W.: The Recognition of Human Movement Using Temporal Templates. IEEE Transactions on Pattern Analysis and Machine Intelligence 23(3), 257–267 (2001)CrossRefGoogle Scholar
  15. 15.
    Rabiner, L.R.: A tutorial on hidden Markov models and selected applications in speech recognition. Proceedings of the IEEE, 257–286 (1989)Google Scholar
  16. 16.
    Uguz, H., Ozturk, A., Saracoglu, R., Arslan, A.: A biomedical system based on fuzzy discrete hidden Markov model for the diagnosis of the brain diseases. Expert Systems with Applications 35, 1104–1114 (2008)CrossRefGoogle Scholar
  17. 17.
    Gorelick, L., Blank, M., Shechtman, E., Irani, M., Basri, R.: Actions as Space-Time Shapes. IEEE Transactions on Pattern Analysis and Machine Intelligence 29(12), 2247–2253 (2007)CrossRefGoogle Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2011

Authors and Affiliations

  • Carlos Orrite
    • 1
  • Mario Rodríguez
    • 1
  • Miguel Montañés
    • 1
  1. 1.I3A, University of ZaragozaSpain

Personalised recommendations