Learning human actions by combining global dynamics and local appearance

Luo, G. and Yang, S. and Tian, G. and Yuan, C. and Hu, W. and Maybank, Stephen J. (2014) Learning human actions by combining global dynamics and local appearance. IEEE Transactions on Pattern Analysis and Machine Intelligence 36 (12), pp. 2466-2482. ISSN 0162-8828.

Abstract

In this paper, we address the problem of human action recognition through combining global temporal dynamics and local visual spatio-temporal appearance features. For this purpose, in the global temporal dimension, we propose to model the motion dynamics with robust linear dynamical systems (LDSs) and use the model parameters as motion descriptors. Since LDSs live in a non-Euclidean space and the descriptors are in non-vector form, we propose a shift invariant subspace angles based distance to measure the similarity between LDSs. In the local visual dimension, we construct curved spatio-temporal cuboids along the trajectories of densely sampled feature points and describe them using histograms of oriented gradients (HOG). The distance between motion sequences is computed with the Chi-Squared histogram distance in the bag-of-words framework. Finally we perform classification using the maximum margin distance learning method by combining the global dynamic distances and the local visual distances. We evaluate our approach for action recognition on five short clips data sets, namely Weizmann, KTH, UCF sports, Hollywood2 and UCF50, as well as three long continuous data sets, namely VIRAT, ADL and CRIM13. We show competitive results as compared with current state-of-the-art methods.

Metadata

Statistics

DownloadsShow export options

Export as XMLJSONCSV

Activity Overview

6 month trend

550Downloads

6 month trend

220Hits

Additional statistics are available via IRStats2.

Archive Staff Only (login required)

Edit/View Item