Loading...

Human action categorization using discriminative local spatio-temporal feature weighting

Ghodrati, A ; Sharif University of Technology | 2012

930 Viewed
  1. Type of Document: Article
  2. DOI: 10.3233/IDA-2012-0538
  3. Publisher: IOP , 2012
  4. Abstract:
  5. New methods based on local spatio-temporal features have exhibited significant performance in action recognition. In these methods, feature selection plays an important role to achieve a superior performance. Actions are represented by local spatio-temporal features extracted from action videos. Action representations are then classified by applying a classifier (such as k-nearest neighbor or SVM). In this paper, we have proposed two feature weighting methods to better discriminate similar actions. We have proposed a definition of feature discrimination power to be used in the feature selection process. Our proposed weighting schemes have greatly improved the final categorization accuracy on the well-known KTH and Weizmann datasets
  6. Keywords:
  7. Bag of spatio-temporal words ; Feature space discriminating ; Feature weighting ; Human action categorization ; local spatio-temporal features ; Action recognition ; Data sets ; Feature discrimination ; Feature space ; Human actions ; K-nearest neighbors ; Spatio-temporal ; Weighting scheme ; Motion estimation
  8. Source: Intelligent Data Analysis ; Volume 16, Issue 4 , July , 2012 , Pages 537-550 ; 1088467X (ISSN)
  9. URL: http://content.iospress.com/articles/intelligent-data-analysis/ida00538