Unsupervised discovery of action classes

Unsupervised discovery of action classes (2006)

Cached

Download Links

Other Repositories/Bibliography

DBLP

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

Venue:	In CVPR
Citations:	30 - 2 self

BibTeX

@INPROCEEDINGS{Wang06unsuperviseddiscovery,
    author = {Yang Wang and Hao Jiang and Mark S. Drew and Ze-nian Li and Greg Mori},
    title = {Unsupervised discovery of action classes},
    booktitle = {In CVPR},
    year = {2006},
    pages = {5}
}

Years of Citing Articles

Bookmark

OpenURL

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. 1.

Citations

No citations identified.