Attention-guided mask learning for self-supervised 3D action recognition
Abstract Most existing 3D action recognition works rely on the supervised learning paradigm, yet the limited availability of annotated data limits the full potential of encoding networks. As a result, effective self-supervised pre-training strategies have been actively researched. In this paper, we...
Gardado en:
| Autor Principal: | |
|---|---|
| Formato: | Artigo |
| Idioma: | Inglês |
| Publicado: |
Springer
2024-07-01
|
| Series: | Complex & Intelligent Systems |
| Assuntos: | |
| Acceso en liña: | https://doi.org/10.1007/s40747-024-01558-1 |
| Tags: |
Sen Etiquetas, Sexa o primeiro en etiquetar este rexistro!
|