Boosted multi-class semi-supervised learning for human action recognition

  • Authors:

  • Tianzhu Zhang;Si Liu;Changsheng Xu;Hanqing Lu

  • Affiliations:

  • National Lab of Pattern Recognition, Institute of Automation, Chinese Academy of Sciences, Beijing 100190, China and China-Singapore Institute of Digital Media, Singapore 119615, Singapore;National Lab of Pattern Recognition, Institute of Automation, Chinese Academy of Sciences, Beijing 100190, China and China-Singapore Institute of Digital Media, Singapore 119615, Singapore;National Lab of Pattern Recognition, Institute of Automation, Chinese Academy of Sciences, Beijing 100190, China and China-Singapore Institute of Digital Media, Singapore 119615, Singapore;National Lab of Pattern Recognition, Institute of Automation, Chinese Academy of Sciences, Beijing 100190, China and China-Singapore Institute of Digital Media, Singapore 119615, Singapore

  • Venue:
  • Pattern Recognition
  • Year:
  • 2011

Quantified Score

Hi-index 0.01

Visualization

Abstract

Human action recognition is a challenging task due to significant intra-class variations, occlusion, and background clutter. Most of the existing work use the action models based on statistic learning algorithms for classification. To achieve good performance on recognition, a large amount of the labeled samples are therefore required to train the sophisticated action models. However, collecting labeled samples is labor-intensive. To tackle this problem, we propose a boosted multi-class semi-supervised learning algorithm in which the co-EM algorithm is adopted to leverage the information from unlabeled data. Three key issues are addressed in this paper. Firstly, we formulate the action recognition in a multi-class semi-supervised learning problem to deal with the insufficient labeled data and high computational expense. Secondly, boosted co-EM is employed for the semi-supervised model construction. To overcome the high dimensional feature space, weighted multiple discriminant analysis (WMDA) is used to project the features into low dimensional subspaces in which the Gaussian mixture models (GMM) are trained and boosting scheme is used to integrate the subspace models. Thirdly, we present the upper bound of the training error in multi-class framework, which is able to guide the novel classifier construction. In theory, the proposed solution is proved to minimize this upper error bound. Experimental results have shown good performance on public datasets.