Model and Feature Selection in Hidden Conditional Random Fields with Group Regularization

  • Rodrigo Cilla
  • Miguel A. Patricio
  • Antonio Berlanga
  • José M. Molina
Part of the Lecture Notes in Computer Science book series (LNCS, volume 8073)


Sequence classification is an important problem in computer vision, speech analysis or computational biology. This paper presents a new training strategy for the Hidden Conditional Random Field sequence classifier incorporating model and feature selection. The standard Lasso regularization employed in the estimation of model parameters is replaced by overlapping group-L1 regularization. Depending on the configuration of the overlapping groups, model selection, feature selection,or both are performed. The sequence classifiers trained in this way have better predictive performance. The application of the proposed method in a human action recognition task confirms that fact.


Feature Selection Action Recognition Hide Variable Human Action Recognition High Predictive Performance 
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.
    Krogh, A., Brown, M., Mian, I.S., Sjolander, K., Haussler, D.: Hidden markov models in computational biology: Applications to protein modeling. Journal of Molecular Biology 235, 1501–1531 (1994)CrossRefGoogle Scholar
  2. 2.
    Collins, M.: Discriminative training methods for hidden markov models: Theory and experiments with perceptron algorithms. In: Proceedings of the ACL 2002 Conference on Empirical Methods in Natural Language Processing, vol. 10, pp. 1–8. Association for Computational Linguistics (2002)Google Scholar
  3. 3.
    Yamato, J., Ohya, J., Ishii, K.: Recognizing human action in time-sequential images using hidden markov model. In: Proceedings of the 1992 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, CVPR 1992, pp. 379–385 (1992)Google Scholar
  4. 4.
    Bishop, C., et al.: Pattern recognition and machine learning, vol. 4. Springer, New York (2006)zbMATHGoogle Scholar
  5. 5.
    Quattoni, A., Wang, S., Morency, L.P., Collins, M., Darrell, T.: Hidden conditional random fields. IEEE Transactions on Pattern Analysis and Machine Intelligence 29, 1848–1853 (2007)CrossRefGoogle Scholar
  6. 6.
    Boyd, S., Vandenberghe, L.: Convex optimization. Cambridge University Press (2004)Google Scholar
  7. 7.
    Zhu, C., Byrd, R., Lu, P., Nocedal, J.: Algorithm 778: L-bfgs-b: Fortran subroutines for large-scale bound-constrained optimization. ACM Transactions on Mathematical Software (TOMS) 23, 550–560 (1997)MathSciNetzbMATHCrossRefGoogle Scholar
  8. 8.
    Ng, A.: Feature selection, l 1 vs. l 2 regularization, and rotational invariance. In: Proceedings of the Twenty-First International Conference on Machine Learning, p. 78. ACM (2004)Google Scholar
  9. 9.
    Huang, J., Zhang, T.: The benefit of group sparsity. The Annals of Statistics 38, 1978–2004 (2010)MathSciNetzbMATHCrossRefGoogle Scholar
  10. 10.
    Szabó, Z., Póczos, B., Lorincz, A.: Online group-structured dictionary learning. In: 2011 IEEE Conference on Computer Vision and Pattern Recognition, CVPR, pp. 2865–2872. IEEE (2011)Google Scholar
  11. 11.
    Schmidt, M.: Graphical model structure learning with l1-regularization. PhD thesis, University of British Columbia (2010)Google Scholar
  12. 12.
    Bauschke, H., Lewis, A.: Dykstras algorithm with bregman projections: A convergence proof. Optimization 48, 409–427 (2000)MathSciNetzbMATHCrossRefGoogle Scholar
  13. 13.
    Wang, L., Suter, D.: Visual learning and recognition of sequential data manifolds with applications to human movement analysis. Computer Vision and Image Understanding 110, 153–172 (2008)CrossRefGoogle Scholar
  14. 14.
    Gorelick, L., Blank, M., Shechtman, E., Irani, M., Basri, R.: Actions as space-time shapes. IEEE Transactions on Pattern Analysis and Machine Intelligence 29, 2247–2253 (2007)CrossRefGoogle Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2013

Authors and Affiliations

  • Rodrigo Cilla
    • 1
  • Miguel A. Patricio
    • 1
  • Antonio Berlanga
    • 1
  • José M. Molina
    • 1
  1. 1.Computer Science DepartmentUniversidad Carlos III de MadridColmenarejoSpain

Personalised recommendations