Hidden Conditional Random Fields for Action Recognition

Lifang Chen, Nico van der Aa, Robby T. Tan, Remco C. Veltkamp

Abstract

In the field of action recognition, the design of features has been explored extensively, but the choice of action classification methods is limited. Commonly used classification methods like k-Nearest Neighbors and Support Vector Machines assume conditional independency between features. In contrast, Hidden Conditional Random Fields (HCRFs) include the spatial or temporal dependencies of features to be better suited for rich, overlapping features. In this paper, we investigate the performance of HCRF and Max-Margin HCRF and their baseline versions, the root model and Multi-class SVM, respectively, for action recognition on the Weizmann dataset. We introduce the Part Labels method, which uses explicitly the part labels learned by HCRF as a new set of local features. We show that only modelling spatial structures in 2D space is not sufficient to justify the additional complexity of HCRF, MMHCRF or the Part Labels method for action recognition.

References

  1. Blank, M., Gorelick, L., Shechtman, E., Irani, M., and Basri, R. (2005). Actions as space-time shapes. In ICCV'05.
  2. Byrd, R., Nocedal, J., and Schnabel, R. (1994). Representations of quasi-newton matrices and their use in limited memory methods. Mathematical Programming, 63:129-156.
  3. Crammer, K. and Singer, Y. (2002). On the algorithmic implementation of multiclass kernel-based vector machines. The Journal of Machine Learning Research, 2:265-292.
  4. Efros, A., Berg, A., Mori, G., and Malik, J. (2003). Recognizing action at a distance. In ICCV'03.
  5. Felzenszwalb, P., McAllester, D., and Ramanan, D. (2008). A discriminatively trained, multiscale, deformable part model. In CVPR'08.
  6. Jhuang, H., Serre, T., Wolf, L., and Poggio, T. (2007). A biologically inspired system for action recognition. In ICCV'07.
  7. Kumar, S. and Hebert, M. (2003). Discriminative random fields: A discriminative framework for contextual interaction in classification. In ICCV'03.
  8. Niebles, J. and Fei-Fei, L. (2007). A hierarchical model of shape and appearance for human action classification. In CVPR'07.
  9. Quattoni, A., Collins, M., and Darrell, T. (2004). Conditional random fields for object recognition. In NIPS'04.
  10. Quattoni, A., Wang, S., Morency, L.-P., Collinsl, M., and Darrell, T. (2007). Hidden conditional random fields. IEEE Transactions on Pattern Analysis and Machine Intelligence, 29(10):1848-1852.
  11. Scovanner, P., Ali, S., and Shah, M. (2007). A 3- dimensional SIFT descriptor and its application to action recognition. In Proc. of the 15th international conference on Multimedia.
  12. Wang, Y. and Mori, G. (2011). Hidden part models for human action recognition: Probabilistic versus maxmargin. IEEE Transactions on Pattern Analysis and Machine Intelligence, 33(7):1310-1323.
  13. Yamato, J., Ohya, J., and Ishii, K. (1992). Recognizing human action in time-sequential images using hidden markov model. In CVPR'92.
  14. Yedidia, J., Freeman, W., and Weiss, Y. (2003). Understanding belief propagation and its generalizations. In Exploring artificial intelligence in the new millennium, pages 239-269.
Download


Paper Citation


in Harvard Style

Chen L., van der Aa N., T. Tan R. and C. Veltkamp R. (2014). Hidden Conditional Random Fields for Action Recognition . In Proceedings of the 9th International Conference on Computer Vision Theory and Applications - Volume 2: VISAPP, (VISIGRAPP 2014) ISBN 978-989-758-004-8, pages 240-247. DOI: 10.5220/0004652902400247


in Bibtex Style

@conference{visapp14,
author={Lifang Chen and Nico van der Aa and Robby T. Tan and Remco C. Veltkamp},
title={Hidden Conditional Random Fields for Action Recognition},
booktitle={Proceedings of the 9th International Conference on Computer Vision Theory and Applications - Volume 2: VISAPP, (VISIGRAPP 2014)},
year={2014},
pages={240-247},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0004652902400247},
isbn={978-989-758-004-8},
}


in EndNote Style

TY - CONF
JO - Proceedings of the 9th International Conference on Computer Vision Theory and Applications - Volume 2: VISAPP, (VISIGRAPP 2014)
TI - Hidden Conditional Random Fields for Action Recognition
SN - 978-989-758-004-8
AU - Chen L.
AU - van der Aa N.
AU - T. Tan R.
AU - C. Veltkamp R.
PY - 2014
SP - 240
EP - 247
DO - 10.5220/0004652902400247