Publication Type

Conference Proceeding Article

Version

publishedVersion

Publication Date

10-2012

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.

Keywords

Action Recognition, Human Action Recognition, Histogram Intersection, Dense Trajectory, Video Stabilization

Discipline

Databases and Information Systems | Graphics and Human Computer Interfaces

Research Areas

Data Science and Engineering

Publication

Computer Vision: 12th European Conference, ECCV 2012, Florence, Italy, October 7-13: Proceedings

Volume

7576

First Page

425

Last Page

438

ISBN

9783642337147

Identifier

10.1007/978-3-642-33715-4_31

Publisher

Springer

City or Country

Cham

Additional URL

https://doi.org/10.1007/978-3-642-33715-4_31

Download

Share

COinS