Affinity Contrastive Learning for Skeleton-based Human Activity Understanding
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866908849468866560 |
|---|---|
| author | Liu, Hongda Liu, Yunfan Ren, Min Sui, Lin Wang, Yunlong Sun, Zhenan |
| author_facet | Liu, Hongda Liu, Yunfan Ren, Min Sui, Lin Wang, Yunlong Sun, Zhenan |
| contents | In skeleton-based human activity understanding, existing methods often adopt the contrastive learning paradigm to construct a discriminative feature space. However, many of these approaches fail to exploit the structural inter-class similarities and overlook the impact of anomalous positive samples. In this study, we introduce ACLNet, an Affinity Contrastive Learning Network that explores the intricate clustering relationships among human activity classes to improve feature discrimination. Specifically, we propose an affinity metric to refine similarity measurements, thereby forming activity superclasses that provide more informative contrastive signals. A dynamic temperature schedule is also introduced to adaptively adjust the penalty strength for various superclasses. In addition, we employ a margin-based contrastive strategy to improve the separation of hard positive and negative samples within classes. Extensive experiments on NTU RGB+D 60, NTU RGB+D 120, Kinetics-Skeleton, PKU-MMD, FineGYM, and CASIA-B demonstrate the superiority of our method in skeleton-based action recognition, gait recognition, and person re-identification. The source code is available at https://github.com/firework8/ACLNet. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2601_16694 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Affinity Contrastive Learning for Skeleton-based Human Activity Understanding Liu, Hongda Liu, Yunfan Ren, Min Sui, Lin Wang, Yunlong Sun, Zhenan Computer Vision and Pattern Recognition In skeleton-based human activity understanding, existing methods often adopt the contrastive learning paradigm to construct a discriminative feature space. However, many of these approaches fail to exploit the structural inter-class similarities and overlook the impact of anomalous positive samples. In this study, we introduce ACLNet, an Affinity Contrastive Learning Network that explores the intricate clustering relationships among human activity classes to improve feature discrimination. Specifically, we propose an affinity metric to refine similarity measurements, thereby forming activity superclasses that provide more informative contrastive signals. A dynamic temperature schedule is also introduced to adaptively adjust the penalty strength for various superclasses. In addition, we employ a margin-based contrastive strategy to improve the separation of hard positive and negative samples within classes. Extensive experiments on NTU RGB+D 60, NTU RGB+D 120, Kinetics-Skeleton, PKU-MMD, FineGYM, and CASIA-B demonstrate the superiority of our method in skeleton-based action recognition, gait recognition, and person re-identification. The source code is available at https://github.com/firework8/ACLNet. |
| title | Affinity Contrastive Learning for Skeleton-based Human Activity Understanding |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2601.16694 |