PCIE_EgoHandPose Solution for EgoExo4D Hand Pose Challenge
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866929388897959936 |
|---|---|
| author | Chen, Feng Ding, Ling Lertniphonphan, Kanokphan Li, Jian Huang, Kaer Wang, Zhepeng |
| author_facet | Chen, Feng Ding, Ling Lertniphonphan, Kanokphan Li, Jian Huang, Kaer Wang, Zhepeng |
| contents | This report presents our team's 'PCIE_EgoHandPose' solution for the EgoExo4D Hand Pose Challenge at CVPR2024. The main goal of the challenge is to accurately estimate hand poses, which involve 21 3D joints, using an RGB egocentric video image provided for the task. This task is particularly challenging due to the subtle movements and occlusions. To handle the complexity of the task, we propose the Hand Pose Vision Transformer (HP-ViT). The HP-ViT comprises a ViT backbone and transformer head to estimate joint positions in 3D, utilizing MPJPE and RLE loss function. Our approach achieved the 1st position in the Hand Pose challenge with 25.51 MPJPE and 8.49 PA-MPJPE. Code is available at https://github.com/KanokphanL/PCIE_EgoHandPose |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2406_12219 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | PCIE_EgoHandPose Solution for EgoExo4D Hand Pose Challenge Chen, Feng Ding, Ling Lertniphonphan, Kanokphan Li, Jian Huang, Kaer Wang, Zhepeng Computer Vision and Pattern Recognition This report presents our team's 'PCIE_EgoHandPose' solution for the EgoExo4D Hand Pose Challenge at CVPR2024. The main goal of the challenge is to accurately estimate hand poses, which involve 21 3D joints, using an RGB egocentric video image provided for the task. This task is particularly challenging due to the subtle movements and occlusions. To handle the complexity of the task, we propose the Hand Pose Vision Transformer (HP-ViT). The HP-ViT comprises a ViT backbone and transformer head to estimate joint positions in 3D, utilizing MPJPE and RLE loss function. Our approach achieved the 1st position in the Hand Pose challenge with 25.51 MPJPE and 8.49 PA-MPJPE. Code is available at https://github.com/KanokphanL/PCIE_EgoHandPose |
| title | PCIE_EgoHandPose Solution for EgoExo4D Hand Pose Challenge |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2406.12219 |