Publication Type

Journal Article

Version

publishedVersion

Publication Date

12-2017

Abstract

Human action recognition remains challenging in realistic videos, where scale and viewpoint changes make the problem complicated. Many complex models have been developed to overcome these difficulties, while we explore using low-level features and typical classifiers to achieve the state-of-the-art performance. The baseline model of feature encoding for action recognition is bag-of-words model, which has shown high efficiency but ignores the arrangement of local features. Refined methods compensate for this problem by using a large number of co-occurrence descriptors or a concatenation of the local distributions in designed segments. In contrast, this article proposes to encode the relative position of visual words using a simple but very compact method called sliding coordinates coding (SCC). The SCC vector of each kind of word is only an eight-dimensional vector which is more compact than many of the spatial or spatial-temporal pooling methods in the literature. Our key observation is that the relative position is robust to the variations of video scale and view angle. Additionally, we design a temporal cutting scheme to define the margin of coding within video clips, since visual words far away from each other have little relationship. In experiments, four action data sets, including KTH, Rochester Activities, IXMAS, and UCF YouTube, are used for performance evaluation. Results show that our method achieves comparable or better performance than the state of the art, while using more compact and less complex models.

Keywords

Human action recognition, bag-of-words model, local feature

Discipline

Artificial Intelligence and Robotics | Numerical Analysis and Scientific Computing

Research Areas

Data Science and Engineering

Publication

International Journal of Advanced Robotic Systems

Volume

14

Issue

6

First Page

1

Last Page

12

ISSN

1729-8806

Identifier

10.1177/1729881417746114

Publisher

SAGE Publications (UK and US): Open Access Titles / SAGE Publishing

Copyright Owner and License

Authors

Additional URL

https://doi.org/10.1177/1729881417746114

Download

Share

COinS