Joint Temporal Pooling for Improving Skeleton-based Action Recognition
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2024
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866917751982915584 |
|---|---|
| author | Gunasekara, Shanaka Ramesh Li, Wanqing Yang, Jack Ogunbona, Philip |
| author_facet | Gunasekara, Shanaka Ramesh Li, Wanqing Yang, Jack Ogunbona, Philip |
| contents | In skeleton-based human action recognition, temporal pooling is a critical step for capturing spatiotemporal relationship of joint dynamics. Conventional pooling methods overlook the preservation of motion information and treat each frame equally. However, in an action sequence, only a few segments of frames carry discriminative information related to the action. This paper presents a novel Joint Motion Adaptive Temporal Pooling (JMAP) method for improving skeleton-based action recognition. Two variants of JMAP, frame-wise pooling and joint-wise pooling, are introduced. The efficacy of JMAP has been validated through experiments on the popular NTU RGB+D 120 and PKU-MMD datasets. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2408_09356 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Joint Temporal Pooling for Improving Skeleton-based Action Recognition Gunasekara, Shanaka Ramesh Li, Wanqing Yang, Jack Ogunbona, Philip Computer Vision and Pattern Recognition In skeleton-based human action recognition, temporal pooling is a critical step for capturing spatiotemporal relationship of joint dynamics. Conventional pooling methods overlook the preservation of motion information and treat each frame equally. However, in an action sequence, only a few segments of frames carry discriminative information related to the action. This paper presents a novel Joint Motion Adaptive Temporal Pooling (JMAP) method for improving skeleton-based action recognition. Two variants of JMAP, frame-wise pooling and joint-wise pooling, are introduced. The efficacy of JMAP has been validated through experiments on the popular NTU RGB+D 120 and PKU-MMD datasets. |
| title | Joint Temporal Pooling for Improving Skeleton-based Action Recognition |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2408.09356 |