Abstract
In order to increase the success rate of a human action recognition system trained with limited labelled video sequences, we propose an approach which combines an efficient use of the scarce data and a transfer learning improvement. The efficient use of data is implemented using the Fuzzy Observation Hidden Markov Model so as to outperform the constraints of the classical approaches when training with small datasets. Additionally, we use a transfer learning procedure that takes advantage of the fact that some human body poses are shared among actions and then key poses can be trained from external sources. Thanks to this method we have improved the recognition performance in new action classes introduced in the target domain. In order to confirm the usefulness of the approach we have tested the performance using the IXMAS dataset as target domain and the ViHASi dataset as source domain.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
References
Weinland, D., Ronfard, R., Boyer, E.: A survey of vision-based methods for action representation, segmentation and recognition. Computer Vision and Image Understanding 115(2), 224–241 (2011)
Orrite, C., RodrÃguez, M., Montañés, M.: One-sequence learning of human actions. In: Salah, A.A., Lepri, B. (eds.) HBU 2011. LNCS, vol. 7065, pp. 40–51. Springer, Heidelberg (2011)
Laptev, I., Marszałek, M., Schmid, C., Rozenfeld, B.: Learning realistic human actions from movies. In: IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (June 2008)
Scovanner, P., Ali, S., Shah, M.: A 3-dimensional sift descriptor and its application to action recognition. In: Proceedings of the 15th International Conference on Multimedia, MULTIMEDIA 2007, pp. 357–360. ACM, New York (2007)
Weinland, D., Ronfard, R., Boyer, E.: Free viewpoint action recognition using motion history volumes. Computer Vision and Image Understanding 104(2-3), 249–257 (2006)
Ragheb, H., Velastin, S., Remagnino, P., Ellis, T.: ViHASi: virtual human action silhouette data for the performance evaluation of silhouette-based action recognition methods. In: Proceedings of the 1st ACM Workshop on Vision Networks for Behavior Analysis, VNBA 2008, pp. 77–84. ACM, New York (2008)
Rabiner, L.R.: A tutorial on hidden markov models and selected applications in speech recognition. Proceedings of the IEEE 77(2), 257–286 (1989)
Pan, S.J., Yang, Q.: A survey on transfer learning. IEEE Transactions on Knowledge and Data Engineering 22(10), 1345–1359 (2010)
Cook, D., Feuz, K.D., Krishnan, N.C.: Transfer learning for activity recognition: a survey. In: Knowledge and Information Systems, pp. 1–20 (2013)
Liu, J., Shah, M., Kuipers, B., Savarese, S.: Cross-view action recognition via view knowledge transfer. In: IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 3209–3216. IEEE (2011)
Bian, W., Tao, D., Rui, Y.: Cross-domain human action recognition. IEEE Transactions on Systems, Man, and Cybernetics. B Cybernetics 42(2), 298–307 (2012)
Zhu, Y., Zhao, X., Fu, Y., Liu, Y.: Sparse coding on local spatial-temporal volumes for human action recognition. In: Kimmel, R., Klette, R., Sugimoto, A. (eds.) ACCV 2010, Part II. LNCS, vol. 6493, pp. 660–671. Springer, Heidelberg (2011)
Hu, D.H., Zheng, V.W., Yang, Q.: Cross-domain activity recognition via transfer learning. Pervasive and Mobile Computing 7, 344–358 (2011)
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)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2013 Springer International Publishing Switzerland
About this paper
Cite this paper
RodrÃguez, M., Medrano, C., Herrero, E., Orrite, C. (2013). Transfer Learning of Human Poses for Action Recognition. In: Salah, A.A., Hung, H., Aran, O., Gunes, H. (eds) Human Behavior Understanding. HBU 2013. Lecture Notes in Computer Science, vol 8212. Springer, Cham. https://doi.org/10.1007/978-3-319-02714-2_8
Download citation
DOI: https://doi.org/10.1007/978-3-319-02714-2_8
Publisher Name: Springer, Cham
Print ISBN: 978-3-319-02713-5
Online ISBN: 978-3-319-02714-2
eBook Packages: Computer ScienceComputer Science (R0)