ML Anthology

Sequential Reliable-Inference for Rapid Detection of Human Actions

James W. Davis
CVPRW 2004 pp. 111
doi:10.1109/CVPR.2004.435 /cvprw/2004/davis2004cvprw-sequential/

Abstract

We present a probabilistic reliable-inference framework to address the issue of rapid-and-reliable detection of human actions. The approach determines the shortest video exposure needed for low-latency recognition by sequentially evaluating a series of posterior class ratios to find the earliest reliable decision point. Results are presented for a set of people walking, running, and standing at different styles and multiple viewpoints, and compared to an alternative ML approach.

CVPRW Semantic Scholar

Cite

Text

Davis. "Sequential Reliable-Inference for Rapid Detection of Human Actions." IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, 2004. doi:10.1109/CVPR.2004.435

Markdown

[Davis. "Sequential Reliable-Inference for Rapid Detection of Human Actions." IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, 2004.](https://mlanthology.org/cvprw/2004/davis2004cvprw-sequential/) doi:10.1109/CVPR.2004.435

BibTeX

@inproceedings{davis2004cvprw-sequential,
  title     = {{Sequential Reliable-Inference for Rapid Detection of Human Actions}},
  author    = {Davis, James W.},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops},
  year      = {2004},
  pages     = {111},
  doi       = {10.1109/CVPR.2004.435},
  url       = {https://mlanthology.org/cvprw/2004/davis2004cvprw-sequential/}
}