Abstract
We present a novel transfer learning approach to cross-camera action recognition. Inspired by canonical correlation analysis (CCA), we first extract the spatio-temporal visual words from videos captured at different views, and derive a correlation subspace as a joint representation for different bag-of-words models at different views. Different from prior CCA-based approaches which simply train standard classifiers such as SVM in the resulting subspace, we explore the domain transfer ability of CCA in the correlation subspace, in which each dimension has a different capability in correlating source and target data. In our work, we propose a novel SVM with a correlation regularizer which incorporates such ability into the design of the SVM. Experiments on the IXMAS dataset verify the effectiveness of our method, which is shown to outperform state-of-the-art transfer learning approaches without taking such domain transfer ability into consideration.
Keywords
- Support Vector Machine
- Action Recognition
- Canonical Correlation Analysis
- Target Domain
- Transfer Learning
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.
References
Holte, M., Tran, C., Trivedi, M., Moeslund, T.: Human action recognition using multiple views: a comparative perspective on recent developments. In: ACM MM Joint Workshop on HGBU (2011)
Rao, C., Yilmaz, A., Shah, M.: View-invariant representation and recognition of actions. IJCV 50, 203–226 (2002)
Weinland, D., Ronfard, R., Boyer, E.: Free viewpoint action recognition using motion history volumes. CVIU 104, 249–257 (2006)
Pan, S.J., Yang, Q.: A survey on transfer learning. IEEE TKDE 22, 1345–1359 (2010)
Farhadi, A., Tabrizi, M.K.: Learning to Recognize Activities from the Wrong View Point. In: Forsyth, D., Torr, P., Zisserman, A. (eds.) ECCV 2008, Part I. LNCS, vol. 5302, pp. 154–166. Springer, Heidelberg (2008)
Liu, J., Shah, M., Kuipers, B., Savarese, S.: Cross-view action recognition via view knowledge transfer. In: CVPR (2011)
Hotelling, H.: Relations between two sets of variates. Biometrika 28, 321–377 (1936)
Poppe, R.: A survey on vision-based human action recognition. IVC 28, 976–990 (2010)
Tran, C., Trivedi, M.: Human body modelling and tracking using volumetric representation: Selected recent studies and possibilities for extensions. In: ICDSC (2008)
Blank, M., Gorelick, L., Shechtman, E., Irani, M., Basri, R.: Actions as space-time shapes. In: ICCV (2005)
Dollár, P., Rabaud, V., Cottrell, G., Belongie, S.: Behavior recognition via sparse spatio-temporal features. In: ICCV Joint Workshop on VS-PETS (2005)
Laptev, I.: On space-time interest points. IJCV 64, 107–123 (2005)
ul Haq, A., Gondal, I., Murshed, M.: On dynamic scene geometry for view-invariant action matching. In: CVPR (2011)
Li, R., Zickler, T.: Discriminative virtual views for cross-view action recognition. In: CVPR (2012)
Blitzer, J., Foster, D., Kakade, S.: Domain adaptation with coupled subspaces. In: AISTATS (2011)
Hardoon, D.R., Szedmak, S., Shawe-Taylor, J.: Canonical correlation analysis: An overview with application to learning methods. Neural Computation 16, 2639–2664 (2004)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2012 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Huang, CH., Yeh, YR., Wang, YC.F. (2012). Recognizing Actions across Cameras by Exploring the Correlated Subspace. In: Fusiello, A., Murino, V., Cucchiara, R. (eds) Computer Vision – ECCV 2012. Workshops and Demonstrations. ECCV 2012. Lecture Notes in Computer Science, vol 7583. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-33863-2_34
Download citation
DOI: https://doi.org/10.1007/978-3-642-33863-2_34
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-642-33862-5
Online ISBN: 978-3-642-33863-2
eBook Packages: Computer ScienceComputer Science (R0)