Improved rank pooling strategy for complex action recognition

Document Type

Conference Proceeding

Publication Date

11-27-2017

Publication Title

2017 IEEE International Conference on Systems, Man, and Cybernetics, SMC 2017

Volume

2017-January

First Page

1351

Last Page

1356

Abstract

Feature ranking from video-wide temporal evolution brings reliable information for complex action recognition. However, a video may contain similar features in the sequence of frames which deliver unnecessary information to the ranking function. This paper proposes a method to improve the rankpooling strategy which captures the optimized latent structure of the video sequence data. The optimization is followed by removing the redundant features from the sequence data. The cosine and correlation distance metrics are employed to detect the identical features and extract the most efficient information from the video frames. Then, the ranked features are generated from the optimized and clean sequence data. The proposed improvement is easy to implement, fast to compute and effective in recognizing complex actions. As a result, the proposed approach reaches remarkable action recognition performance on benchmark datasets, namely Hollywood2, URADL, and HMDB51. The results are further compared with state-of-the-art techniques in the experiment section to confirm the effectiveness of the improved rank pooling framework.

DOI

10.1109/SMC.2017.8122801

ISBN

9781538616451

Share

COinS