Publication Type

Journal Article

Version

publishedVersion

Publication Date

11-2015

Abstract

Human action recognition in unconstrained videos is a challenging problem with many applications. Most state-of-the-art approaches adopted the well-known bag-of-features representations, generated based on isolated local patches or patch trajectories, where motion patterns, such as object-object and object-background relationships are mostly discarded. In this paper, we propose a simple representation aiming at modeling these motion relationships. We adopt global and local reference points to explicitly characterize motion information, so that the final representation is more robust to camera movements, which widely exist in unconstrained videos. Our approach operates on the top of visual codewords generated on dense local patch trajectories, and therefore, does not require foreground-background separation, which is normally a critical and difficult step in modeling object relationships. Through an extensive set of experimental evaluations, we show that the proposed representation produces a very competitive performance on several challenging benchmark data sets. Further combining it with the standard bag-of-features or Fisher vector representations can lead to substantial improvements.

Keywords

Human action recognition, trajectory, motion, representation, reference points, camera motion

Discipline

Computer Sciences | Graphics and Human Computer Interfaces

Research Areas

Intelligent Systems and Optimization

Publication

IEEE Transactions on Image Processing

Volume

24

Issue

11

First Page

3781

Last Page

3795

ISSN

1057-7149

Identifier

10.1109/TIP.2015.2456412

Publisher

Institute of Electrical and Electronics Engineers

Download

Share

COinS