Cross-dataset action detection

Liangliang Cao, Zicheng Liu, Thomas S. Huang

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

Abstract

In recent years, many research works have been carried out to recognize human actions from video clips. To learn an effective action classifier, most of the previous approaches rely on enough training labels. When being required to recognize the action in a different dataset, these approaches have to re-train the model using new labels. However, labeling video sequences is a very tedious and time-consuming task, especially when detailed spatial locations and time durations are required. In this paper, we propose an adaptive action detection approach which reduces the requirement of training labels and is able to handle the task of cross-dataset action detection with few or no extra training labels. Our approach combines model adaptation and action detection into a Maximum a Posterior (MAP) estimation framework, which explores the spatialtemporal coherence of actions and makes good use of the prior information which can be obtained without supervision. Our approach obtains state-of-the-art results on KTH action dataset using only 50% of the training labels in tradition approaches. Furthermore, we show that our approach is effective for the cross-dataset detection which adapts the model trained on KTH to two other challenging datasets.

Original languageEnglish (US)
Title of host publication2010 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, CVPR 2010
Pages1998-2005
Number of pages8
DOIs
StatePublished - Aug 31 2010
Event2010 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, CVPR 2010 - San Francisco, CA, United States
Duration: Jun 13 2010Jun 18 2010

Publication series

NameProceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition
ISSN (Print)1063-6919

Other

Other2010 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, CVPR 2010
CountryUnited States
CitySan Francisco, CA
Period6/13/106/18/10

ASJC Scopus subject areas

  • Software
  • Computer Vision and Pattern Recognition

Fingerprint Dive into the research topics of 'Cross-dataset action detection'. Together they form a unique fingerprint.

  • Cite this

    Cao, L., Liu, Z., & Huang, T. S. (2010). Cross-dataset action detection. In 2010 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, CVPR 2010 (pp. 1998-2005). [5539875] (Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition). https://doi.org/10.1109/CVPR.2010.5539875