Regular Articles

Action recognition using spatiotemporal features and hybrid generative/discriminative models

[+] Author Affiliations
Jia Liu

Shanghai Jiao Tong University, Institute of Image Processing and Pattern Recognition, 800 Dongchuan Road, Shanghai 200240, China

Jie Yang

Shanghai Jiao Tong University, Institute of Image Processing and Pattern Recognition, 800 Dongchuan Road, Shanghai 200240, China

J. Electron. Imaging. 21(2), 023010 (May 22, 2012). doi:10.1117/1.JEI.21.2.023010
History: Received August 8, 2011; Revised February 16, 2012; Accepted March 12, 2012
Text Size: A A A

Abstract.  We propose a new method for human action recognition based on multiple features and a hybrid generative/discriminative model. Specifically, we propose a new action representation based on computing a rich set of descriptors from Affine-SIFT key point trajectories. A new hybrid generative/discriminative approach based on support vector machine and topic model is proposed using Fisher kernel method for action recognition. Fisher score for the topic model is evaluated by the variational inference algorithm. To obtain efficient and compact representations for actions, we develop a feature fusion method to combine spatial-temporal local motion descriptors and demonstrate how this kernel framework can be used to combine different types of features and models into a single classifier. Our experiments, conducted on a number of popular datasets, show performance improvements over the corresponding generative approach and are competitive with the best results reported in the literature.

Figures in this Article
© 2012 SPIE and IS&T

Topics

Matrices ; Video

Citation

Jia Liu and Jie Yang
"Action recognition using spatiotemporal features and hybrid generative/discriminative models", J. Electron. Imaging. 21(2), 023010 (May 22, 2012). ; http://dx.doi.org/10.1117/1.JEI.21.2.023010


Access This Article
Sign in or Create a personal account to Buy this article ($20 for members, $25 for non-members).

Some tools below are only available to our subscribers or users with an online account.

Related Content

Customize your page view by dragging & repositioning the boxes below.

Related Book Chapters

PubMed Articles
Advertisement
  • Don't have an account?
  • Subscribe to the SPIE Digital Library
  • Create a FREE account to sign up for Digital Library content alerts and gain access to institutional subscriptions remotely.
Access This Article
Sign in or Create a personal account to Buy this article ($20 for members, $25 for non-members).
Access This Proceeding
Sign in or Create a personal account to Buy this article ($15 for members, $18 for non-members).
Access This Chapter

Access to SPIE eBooks is limited to subscribing institutions and is not available as part of a personal subscription. Print or electronic versions of individual SPIE books may be purchased via SPIE.org.