Share Email Print

Optical Engineering

Hybrid generative-discriminative human action recognition by combining spatiotemporal words with supervised topic models
Author(s): Hao Sun; Cheng Wang; Boliang Wang
Format Member Price Non-Member Price
PDF $20.00 $25.00
cover GOOD NEWS! Your organization subscribes to the SPIE Digital Library. You may be able to download this paper for free. Check Access

Paper Abstract

We present a hybrid generative-discriminative learning method for human action recognition from video sequences. Our model combines a bag-of-words component with supervised latent topic models. A video sequence is represented as a collection of spatiotemporal words by extracting space-time interest points and describing these points using both shape and motion cues. The supervised latent Dirichlet allocation (sLDA) topic model, which employs discriminative learning using labeled data under a generative framework, is introduced to discover the latent topic structure that is most relevant to action categorization. The proposed algorithm retains most of the desirable properties of generative learning while increasing the classification performance though a discriminative setting. It has also been extended to exploit both labeled data and unlabeled data to learn human actions under a unified framework. We test our algorithm on three challenging data sets: the KTH human motion data set, the Weizmann human action data set, and a ballet data set. Our results are either comparable to or significantly better than previously published results on these data sets and reflect the promise of hybrid generative-discriminative learning approaches.

Paper Details

Date Published: 1 February 2011
PDF: 11 pages
Opt. Eng. 50(2) 027203 doi: 10.1117/1.3537969
Published in: Optical Engineering Volume 50, Issue 2
Show Author Affiliations
Hao Sun, National Univ. of Defense Technology (China)
Cheng Wang, Xiamen Univ. (China)
Boliang Wang, Xiamen Univ. (China)

© SPIE. Terms of Use
Back to Top