G3D: A Gaming Action Dataset and Real Time Action Recognition Evaluation Framework
Abstract
In this paper a novel evaluation framework for measuring the performance of real-time action recognition methods is presented. The evaluation framework will extend the time-based event detection metric to model multiple distinct action classes. The proposed metric provides more accurate indications of the performance of action recognition algorithms for games and other similar applications since it takes into consideration restrictions related to time and consecutive repetitions. Furthermore, a new dataset, G3D for real-time action recognition in gaming containing synchronised video, depth and skeleton data is provided. Our results indicate the need of an advanced metric especially designed for games and other similar real-time applications.
Cite
Text
Bloom et al. "G3D: A Gaming Action Dataset and Real Time Action Recognition Evaluation Framework." IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, 2012. doi:10.1109/CVPRW.2012.6239175Markdown
[Bloom et al. "G3D: A Gaming Action Dataset and Real Time Action Recognition Evaluation Framework." IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, 2012.](https://mlanthology.org/cvprw/2012/bloom2012cvprw-g3d/) doi:10.1109/CVPRW.2012.6239175BibTeX
@inproceedings{bloom2012cvprw-g3d,
title = {{G3D: A Gaming Action Dataset and Real Time Action Recognition Evaluation Framework}},
author = {Bloom, Victoria and Makris, Dimitrios and Argyriou, Vasileios},
booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops},
year = {2012},
pages = {7-12},
doi = {10.1109/CVPRW.2012.6239175},
url = {https://mlanthology.org/cvprw/2012/bloom2012cvprw-g3d/}
}