Action recognition by multiple features and hyper-sphere multi-class SVM

Jia Liu, Jie Yang, Yi Zhang, Xiangjian He

Research output: Chapter in Book/Conference proceedingConference contributionpeer-review

20 Citations (Scopus)

Abstract

In this paper we propose a novel framework for action recognition based on multiple features for improve action recognition in videos. The fusion of multiple features is important for recognizing actions as often a single feature based representation is not enough to capture the imaging variations (view-point, illumination etc.) and attributes of individuals (size, age, gender etc.). Hence, we use two kinds of features: i) a quantized vocabulary of local spatio-temporal (ST) volumes (cuboids and 2-D SIFT), and ii) the higher-order statistical models of interest points, which aims to capture the global information of the actor. We construct video representation in terms of local space-time features and global features and integrate such representations with hyper-sphere multi-class SVM. Experiments on publicly available datasets show that our proposed approach is effective. An additional experiment shows that using both local and global features provides a richer representation of human action when compared to the use of a single feature type.

Original languageEnglish
Title of host publicationProceedings - 2010 20th International Conference on Pattern Recognition, ICPR 2010
Pages3744-3747
Number of pages4
DOIs
Publication statusPublished - 2010
Externally publishedYes
Event2010 20th International Conference on Pattern Recognition, ICPR 2010 - Istanbul, Turkey
Duration: 23 Aug 201026 Aug 2010

Publication series

NameProceedings - International Conference on Pattern Recognition
ISSN (Print)1051-4651

Conference

Conference2010 20th International Conference on Pattern Recognition, ICPR 2010
Country/TerritoryTurkey
CityIstanbul
Period23/08/1026/08/10

Keywords

  • Human action recognition
  • Hyper-sphere multi-class SVM
  • Multiple features

ASJC Scopus subject areas

  • Computer Vision and Pattern Recognition

Fingerprint

Dive into the research topics of 'Action recognition by multiple features and hyper-sphere multi-class SVM'. Together they form a unique fingerprint.

Cite this