3DInAction: Understanding Human Actions in 3D Point Clouds
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2023
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866913289937616896 |
|---|---|
| author | Ben-Shabat, Yizhak Shrout, Oren Gould, Stephen |
| author_facet | Ben-Shabat, Yizhak Shrout, Oren Gould, Stephen |
| contents | We propose a novel method for 3D point cloud action recognition. Understanding human actions in RGB videos has been widely studied in recent years, however, its 3D point cloud counterpart remains under-explored. This is mostly due to the inherent limitation of the point cloud data modality -- lack of structure, permutation invariance, and varying number of points -- which makes it difficult to learn a spatio-temporal representation. To address this limitation, we propose the 3DinAction pipeline that first estimates patches moving in time (t-patches) as a key building block, alongside a hierarchical architecture that learns an informative spatio-temporal representation. We show that our method achieves improved performance on existing datasets, including DFAUST and IKEA ASM. Code is publicly available at https://github.com/sitzikbs/3dincaction. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2303_06346 |
| institution | arXiv |
| publishDate | 2023 |
| record_format | arxiv |
| spellingShingle | 3DInAction: Understanding Human Actions in 3D Point Clouds Ben-Shabat, Yizhak Shrout, Oren Gould, Stephen Computer Vision and Pattern Recognition We propose a novel method for 3D point cloud action recognition. Understanding human actions in RGB videos has been widely studied in recent years, however, its 3D point cloud counterpart remains under-explored. This is mostly due to the inherent limitation of the point cloud data modality -- lack of structure, permutation invariance, and varying number of points -- which makes it difficult to learn a spatio-temporal representation. To address this limitation, we propose the 3DinAction pipeline that first estimates patches moving in time (t-patches) as a key building block, alongside a hierarchical architecture that learns an informative spatio-temporal representation. We show that our method achieves improved performance on existing datasets, including DFAUST and IKEA ASM. Code is publicly available at https://github.com/sitzikbs/3dincaction. |
| title | 3DInAction: Understanding Human Actions in 3D Point Clouds |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2303.06346 |