ML Anthology

Pose Primitive Based Human Action Recognition in Videos or Still Images

Christian Thurau, Václav Hlavác
CVPR 2008
doi:10.1109/CVPR.2008.4587721 /cvpr/2008/thurau2008cvpr-pose/

Abstract

This paper presents a method for recognizing human actions based on pose primitives. In learning mode, the parameters representing poses and activities are estimated from videos. In run mode, the method can be used both for videos or still images. For recognizing pose primitives, we extend a Histogram of Oriented Gradient (HOG) based descriptor to better cope with articulated poses and cluttered background. Action classes are represented by histograms of poses primitives. For sequences, we incorporate the local temporal context by means of n-gram expressions. Action recognition is based on a simple histogram comparison. Unlike the mainstream video surveillance approaches, the proposed method does not rely on background subtraction or dynamic features and thus allows for action recognition in still images.

CVPR Semantic Scholar

Cite

Text

Thurau and Hlavác. "Pose Primitive Based Human Action Recognition in Videos or Still Images." IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2008. doi:10.1109/CVPR.2008.4587721

Markdown

[Thurau and Hlavác. "Pose Primitive Based Human Action Recognition in Videos or Still Images." IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2008.](https://mlanthology.org/cvpr/2008/thurau2008cvpr-pose/) doi:10.1109/CVPR.2008.4587721

BibTeX

@inproceedings{thurau2008cvpr-pose,
  title     = {{Pose Primitive Based Human Action Recognition in Videos or Still Images}},
  author    = {Thurau, Christian and Hlavác, Václav},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition},
  year      = {2008},
  doi       = {10.1109/CVPR.2008.4587721},
  url       = {https://mlanthology.org/cvpr/2008/thurau2008cvpr-pose/}
}