Trajectory-Based modeling of human actions with motion reference points

  • Authors:

  • Yu-Gang Jiang;Qi Dai;Xiangyang Xue;Wei Liu;Chong-Wah Ngo

  • Affiliations:

  • School of Computer Science, Fudan University, Shanghai, China;School of Computer Science, Fudan University, Shanghai, China;School of Computer Science, Fudan University, Shanghai, China;IBM T. J. Watson Research Center, NY;Department of Computer Science, City University of Hong Kong, China

  • Venue:
  • ECCV'12 Proceedings of the 12th European conference on Computer Vision - Volume Part V
  • Year:
  • 2012

Quantified Score

Hi-index 0.00

Visualization

Abstract

Human action recognition in videos is a challenging problem with wide applications. State-of-the-art approaches often adopt the popular bag-of-features representation based on isolated local patches or temporal patch trajectories, where motion patterns like object relationships are mostly discarded. This paper proposes a simple representation specifically aimed at the modeling of such motion relationships. We adopt global and local reference points to characterize motion information, so that the final representation can be robust to camera movement. Our approach operates on top of visual codewords derived from local patch trajectories, and therefore does not require accurate foreground-background separation, which is typically a necessary step to model object relationships. Through an extensive experimental evaluation, we show that the proposed representation offers very competitive performance on challenging benchmark datasets, and combining it with the bag-of-features representation leads to substantial improvement. On Hollywood2, Olympic Sports, and HMDB51 datasets, we obtain 59.5%, 80.6% and 40.7% respectively, which are the best reported results to date.