English

Spatio-Temporal Covariance Descriptors for Action and Gesture Recognition

Computer Vision and Pattern Recognition 2013-03-26 v1 Human-Computer Interaction

Abstract

We propose a new action and gesture recognition method based on spatio-temporal covariance descriptors and a weighted Riemannian locality preserving projection approach that takes into account the curved space formed by the descriptors. The weighted projection is then exploited during boosting to create a final multiclass classification algorithm that employs the most useful spatio-temporal regions. We also show how the descriptors can be computed quickly through the use of integral video representations. Experiments on the UCF sport, CK+ facial expression and Cambridge hand gesture datasets indicate superior performance of the proposed method compared to several recent state-of-the-art techniques. The proposed method is robust and does not require additional processing of the videos, such as foreground detection, interest-point detection or tracking.

Keywords

Cite

@article{arxiv.1303.6021,
  title  = {Spatio-Temporal Covariance Descriptors for Action and Gesture Recognition},
  author = {Andres Sanin and Conrad Sanderson and Mehrtash T. Harandi and Brian C. Lovell},
  journal= {arXiv preprint arXiv:1303.6021},
  year   = {2013}
}
R2 v1 2026-06-21T23:47:28.167Z