Learning spatio-temporal dependencies for action recognition

Qiao Cai, Yafeng Yin, Hong Man

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

6 Scopus citations

Abstract

In this paper, we propose a spatio-temporal dependencies learning (STDL) method for action recognition. Inspired by self-organizing map, our method can learn implicit spatial-temporal dependencies from sequential action feature sets while preserving the intrinsic topologies characterized in human actions. A further advantage is its ability to project higher dimensional action feature to lower dimensional latent neural distribution, which significantly reduces the computational cost and data redundancy in the learning and recognition process. An ensemble learning strategy using expectation-maximization is adopted to estimate the latent parameters of STDL model. The effectiveness and robustness of the proposed model is verified through extensive experiments on several benchmark datasets.

Original languageEnglish
Title of host publication2013 IEEE International Conference on Image Processing, ICIP 2013 - Proceedings
Pages3740-3744
Number of pages5
DOIs
StatePublished - 2013
Event2013 20th IEEE International Conference on Image Processing, ICIP 2013 - Melbourne, VIC, Australia
Duration: 15 Sep 201318 Sep 2013

Publication series

Name2013 IEEE International Conference on Image Processing, ICIP 2013 - Proceedings

Conference

Conference2013 20th IEEE International Conference on Image Processing, ICIP 2013
Country/TerritoryAustralia
CityMelbourne, VIC
Period15/09/1318/09/13

Keywords

  • Spatio-temporal dependencies
  • action recognition
  • self-organizing map

Fingerprint

Dive into the research topics of 'Learning spatio-temporal dependencies for action recognition'. Together they form a unique fingerprint.

Cite this