Action Quality Assessment Across Multiple Actions
Abstract
Can learning to measure the quality of an action help in measuring the quality of other actions? If so, can consolidated samples from multiple actions help improve the performance of current approaches? In this paper, we carry out experiments to see if knowledge transfer is possible in the action quality assessment (AQA) setting. Experiments are carried out on our newly released AQA dataset (http://rtis.oit.unlv.edu/datasets.html) consisting of 1106 action samples from seven actions with quality as measured by expert human judges. Our experimental results show that there is utility in learning a single model across multiple actions.
Cite
Text
Parmar and Morris. "Action Quality Assessment Across Multiple Actions." IEEE/CVF Winter Conference on Applications of Computer Vision, 2019. doi:10.1109/WACV.2019.00161Markdown
[Parmar and Morris. "Action Quality Assessment Across Multiple Actions." IEEE/CVF Winter Conference on Applications of Computer Vision, 2019.](https://mlanthology.org/wacv/2019/parmar2019wacv-action/) doi:10.1109/WACV.2019.00161BibTeX
@inproceedings{parmar2019wacv-action,
title = {{Action Quality Assessment Across Multiple Actions}},
author = {Parmar, Paritosh and Morris, Brendan},
booktitle = {IEEE/CVF Winter Conference on Applications of Computer Vision},
year = {2019},
pages = {1468-1476},
doi = {10.1109/WACV.2019.00161},
url = {https://mlanthology.org/wacv/2019/parmar2019wacv-action/}
}