Variational Contrastive Learning for Skeleton-based Action Recognition
Fuente:
arXiv
Salvato in:
| Autori principali: | , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2026
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866908760047353856 |
|---|---|
| author | Nguyen, Dang Dinh Latif, Decky Aspandi Zaharia, Titus |
| author_facet | Nguyen, Dang Dinh Latif, Decky Aspandi Zaharia, Titus |
| contents | In recent years, self-supervised representation learning for skeleton-based action recognition has advanced with the development of contrastive learning methods. However, most of contrastive paradigms are inherently discriminative and often struggle to capture the variability and uncertainty intrinsic to human motion. To address this issue, we propose a variational contrastive learning framework that integrates probabilistic latent modeling with contrastive self-supervised learning. This formulation enables the learning of structured and semantically meaningful representations that generalize across different datasets and supervision levels. Extensive experiments on three widely used skeleton-based action recognition benchmarks show that our proposed method consistently outperforms existing approaches, particularly in low-label regimes. Moreover, qualitative analyses show that the features provided by our method are more relevant given the motion and sample characteristics, with more focus on important skeleton joints, when compared to the other methods. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2601_07666 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Variational Contrastive Learning for Skeleton-based Action Recognition Nguyen, Dang Dinh Latif, Decky Aspandi Zaharia, Titus Computer Vision and Pattern Recognition Artificial Intelligence In recent years, self-supervised representation learning for skeleton-based action recognition has advanced with the development of contrastive learning methods. However, most of contrastive paradigms are inherently discriminative and often struggle to capture the variability and uncertainty intrinsic to human motion. To address this issue, we propose a variational contrastive learning framework that integrates probabilistic latent modeling with contrastive self-supervised learning. This formulation enables the learning of structured and semantically meaningful representations that generalize across different datasets and supervision levels. Extensive experiments on three widely used skeleton-based action recognition benchmarks show that our proposed method consistently outperforms existing approaches, particularly in low-label regimes. Moreover, qualitative analyses show that the features provided by our method are more relevant given the motion and sample characteristics, with more focus on important skeleton joints, when compared to the other methods. |
| title | Variational Contrastive Learning for Skeleton-based Action Recognition |
| topic | Computer Vision and Pattern Recognition Artificial Intelligence |
| url | https://arxiv.org/abs/2601.07666 |