Dual-Domain Triple Contrast for Cross-Dataset Skeleton-Based Action Recognition
ACM Transactions on Multimedia Computing, Communications, and Applications · 30.04.2025 · 21 (4) · 1-23
DOI: 10.1145/3715917 ↗Kurz gefasst
Fachartikel in der Zeitschrift ACM Transactions on Multimedia Computing, Communications, and Applications, online erschienen am 10.03.2025. Verfasst von Kun Wang und 4 weiteren Autor:innen. Die Arbeit wurde bisher 3-mal zitiert (Crossref) und nennt 62 Literaturangaben. Gefördert von: National Natural Science Foundation of China, Natural Science Foundation of Jiangsu province, Jiangsu Provincial Key Laboratory of Computer Networking Technology.
Abstract (Originalsprache)
Skeleton-based Action Recognition (SAR) is widely recognized for its robustness and efficiency in human action analysis, but its performance in cross-dataset tasks has been limited due to domain shifts between different datasets. To address this challenge, current methods typically approach cross-dataset SAR as an Unsupervised Domain Adaptation (UDA) task, which is tackled using domain adaptation or self-supervised learning strategies. In this article, we propose a Dual-Domain Triple Contrast (D2TC) framework for cross-dataset SAR under the UDA setting. Unlike existing UDA methods that either focus on a single strategy or superficially combine strategies, our D2TC leverages contrastive learning to integrate both strategies into a unified framework. It performs three types of contrastive learning: Self-Supervised Contrastive Learning, Supervised Contrastive Learning, and UDA with Contrastive Learning, across both source and target domains. The triple contrasts go beyond mere summation, effectively bridging the domain gap and enhancing the model’s representational capacity. Additionally, we introduce multi-modal ensemble contrast and extreme skeleton augmentation methods to further enhance the skeleton-based representation learning. Extensive experiments on six cross-dataset settings validate the superiority of our D2TC framework over state-of-the-art methods, demonstrating its effectiveness in reducing domain discrepancies and improving cross-dataset SAR performance. The codes are available on https://github.com/KennCoder7/DualDomainTripleContrast .
Förderung
- National Natural Science Foundation of China
- Natural Science Foundation of Jiangsu province
- Jiangsu Provincial Key Laboratory of Computer Networking Technology
- Jiangsu Provincial Key Laboratory of Network and Information Security
- Key Laboratory of Computer Network and Information Integration of Ministry of Education of China
- Nanjing Purple Mountain Laboratories
Zitieren
APA
Wang, K., Cao, J., Ge, J., Liu, C., & Liu, B. (2025). Dual-Domain Triple Contrast for Cross-Dataset Skeleton-Based Action Recognition. ACM Transactions on Multimedia Computing, Communications, and Applications, 21(4), 1-23. https://doi.org/10.1145/3715917
Vancouver
Wang K, Cao J, Ge J, Liu C, Liu B. Dual-Domain Triple Contrast for Cross-Dataset Skeleton-Based Action Recognition. ACM Transactions on Multimedia Computing, Communications, and Applications. 2025;21(4):1-23. doi:10.1145/3715917
BibTeX
@article{Wang2025,
author = {Wang, Kun and Cao, Jiuxin and Ge, Jiawei and Liu, Chang and Liu, Bo},
title = {Dual-Domain Triple Contrast for Cross-Dataset Skeleton-Based Action Recognition},
journal = {ACM Transactions on Multimedia Computing, Communications, and Applications},
year = {2025},
volume = {21},
number = {4},
pages = {1--23},
doi = {10.1145/3715917}
}
EUVIMED