Range-Sample Depth Feature for Action Recognition

CVPR 2014

doi:10.1109/CVPR.2014.104 /cvpr/2014/lu2014cvpr-rangesample/

Abstract

We propose binary range-sample feature in depth. It is based on t tests and achieves reasonable invariance with respect to possible change in scale, viewpoint, and background. It is robust to occlusion and data corruption as well. The descriptor works in a high speed thanks to its binary property. Working together with standard learning algorithms, the proposed descriptor achieves state-of-theart results on benchmark datasets in our experiments. Impressively short running time is also yielded.

PDF CVPR Semantic Scholar

Cite

Text

Lu et al. "Range-Sample Depth Feature for Action Recognition." Conference on Computer Vision and Pattern Recognition, 2014. doi:10.1109/CVPR.2014.104

Markdown

[Lu et al. "Range-Sample Depth Feature for Action Recognition." Conference on Computer Vision and Pattern Recognition, 2014.](https://mlanthology.org/cvpr/2014/lu2014cvpr-rangesample/) doi:10.1109/CVPR.2014.104

BibTeX

@inproceedings{lu2014cvpr-rangesample,
  title     = {{Range-Sample Depth Feature for Action Recognition}},
  author    = {Lu, Cewu and Jia, Jiaya and Tang, Chi-Keung},
  booktitle = {Conference on Computer Vision and Pattern Recognition},
  year      = {2014},
  doi       = {10.1109/CVPR.2014.104},
  url       = {https://mlanthology.org/cvpr/2014/lu2014cvpr-rangesample/}
}