Unsupervised Domain Adaptation for Human Pose Action Recognition

Mattias Billast, Tom De Schepper, Tom De Schepper, Kevin Mets

2024

Abstract

Personalized human action recognition is important to give accurate feedback about motion patterns, but there is likely no labeled data available to update the model in a supervised way. Unsupervised domain adaptation can solve this problem by closing the gap between seen data and new unseen users. We test several domain adaptation techniques and compare them with each other on this task. We show that all tested techniques improve on the model without any domain adaptation and are only trained on labeled source data. We add multiple improvements by designing a better feature representation tailored to the new user. These improvements include added contrastive loss and varying the backbone encoder. We would need between 30% and 40% labeled data of the new user to get the same results.

Paper Citation

in Harvard Style

Billast M., De Schepper T. and Mets K. (2024). Unsupervised Domain Adaptation for Human Pose Action Recognition. In Proceedings of the 19th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications - Volume 2: VISAPP; ISBN 978-989-758-679-8, SciTePress, pages 837-844. DOI: 10.5220/0012573400003660

in Bibtex Style

@conference{visapp24,
author={Mattias Billast and Tom De Schepper and Kevin Mets},
title={Unsupervised Domain Adaptation for Human Pose Action Recognition},
booktitle={Proceedings of the 19th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications - Volume 2: VISAPP},
year={2024},
pages={837-844},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0012573400003660},
isbn={978-989-758-679-8},
}

in EndNote Style

TY - CONF

JO - Proceedings of the 19th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications - Volume 2: VISAPP
TI - Unsupervised Domain Adaptation for Human Pose Action Recognition
SN - 978-989-758-679-8
AU - Billast M.
AU - De Schepper T.
AU - Mets K.
PY - 2024
SP - 837
EP - 844
DO - 10.5220/0012573400003660
PB - SciTePress