Action detection using multiple Spatial-Temporal Interest Point features

Liangliang Cao, Ying Li Tian, Zicheng Liu, Benjamin Yao, Zhengyou Zhang, Thomas S. Huang

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

This paper considers the problem of detecting actions from cluttered videos. Compared with the classical action recognition problem, this paper aims to estimate not only the scene category of a given video sequence, but also the spatial-temporal locations of the action instances. In recent years, many feature extraction schemes have been designed to describe various aspects of actions. However, due to the difficulty of action detection, e.g., the cluttered background and potential occlusions, a single type of features cannot solve the action detection problems perfectly in cluttered videos. In this paper, we attack the detection problem by combining multiple Spatial-Temporal Interest Point (STIP) features, which detect salient patches in the video domain, and describe these patches by feature of local regions. The difficulty of combining multiple STIP features for action detection is two folds: First, the number of salient patches detected by different STIP methods varies across different salient patches. How to combine such features is not considered by existing fusion methods [13] [5]. Second, the detection in the videos should be efficient, which excludes many slow machine learning algorithms. To handle these two difficulties, we propose a new approach which combines Gaussian MixtureModel with Branch-and-Bound search to efficiently locate the action of interest. We build a new challenging dataset for our action detection task, and our algorithm obtains impressive results. On classical KTH dataset, our method outperforms the state-of-theart methods.

Original languageEnglish (US)
Title of host publication2010 IEEE International Conference on Multimedia and Expo, ICME 2010
Pages340-345
Number of pages6
DOIs
StatePublished - Nov 22 2010
Event2010 IEEE International Conference on Multimedia and Expo, ICME 2010 - Singapore, Singapore
Duration: Jul 19 2010Jul 23 2010

Publication series

Name2010 IEEE International Conference on Multimedia and Expo, ICME 2010

Other

Other2010 IEEE International Conference on Multimedia and Expo, ICME 2010
CountrySingapore
CitySingapore
Period7/19/107/23/10

ASJC Scopus subject areas

  • Human-Computer Interaction
  • Software

Fingerprint Dive into the research topics of 'Action detection using multiple Spatial-Temporal Interest Point features'. Together they form a unique fingerprint.

Cite this