Unsupervised Discovery of Action Classes

Yang Wang, Hao Jiang, Mark S. Drew, Ze-Nian Li, Greg Mori

CVPR 2006 pp. 1654-1661

doi:10.1109/CVPR.2006.321 /cvpr/2006/wang2006cvpr-unsupervised/

Abstract

In this paper we consider the problem of describing the action being performed by human figures in still images. We will attack this problem using an unsupervised learning approach, attempting to discover the set of action classes present in a large collection of training images. These action classes will then be used to label test images. Our approach uses the coarse shape of the human figures to match pairs of images. The distance between a pair of images is computed using a linear programming relaxation technique. This is a computationally expensive process, and we employ a fast pruning method to enable its use on a large collection of images. Spectral clustering is then performed using the resulting distances. We present clustering and image labeling results on a variety of datasets.

PDF CVPR Semantic Scholar

Cite

Text

Wang et al. "Unsupervised Discovery of Action Classes." IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2006. doi:10.1109/CVPR.2006.321

Markdown

[Wang et al. "Unsupervised Discovery of Action Classes." IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2006.](https://mlanthology.org/cvpr/2006/wang2006cvpr-unsupervised/) doi:10.1109/CVPR.2006.321

BibTeX

@inproceedings{wang2006cvpr-unsupervised,
  title     = {{Unsupervised Discovery of Action Classes}},
  author    = {Wang, Yang and Jiang, Hao and Drew, Mark S. and Li, Ze-Nian and Mori, Greg},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition},
  year      = {2006},
  pages     = {1654-1661},
  doi       = {10.1109/CVPR.2006.321},
  url       = {https://mlanthology.org/cvpr/2006/wang2006cvpr-unsupervised/}
}