PCIE_EgoHandPose Solution for EgoExo4D Hand Pose Challenge

Feng Chen; Jian Li; Kaer Huang; Kanokphan Lertniphonphan; Ling Ding; Zhepeng Wang

PCIE_EgoHandPose Solution for EgoExo4D Hand Pose Challenge

Not yet reviewed by Pith; the record is open.

Re-run · record.json Download PDF Read on arXiv ↗

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2406.12219 v1 pith:NAT6YV33 submitted 2024-06-18 cs.CV

Feng Chen , Ling Ding , Kanokphan Lertniphonphan , Jian Li , Kaer Huang , Zhepeng Wang This is my paper · ORCID

classification cs.CV

keywords handchallengeposeegohandposepcietaskegoexo4destimate

verification ladder T0 review T1 audit T2 compute T3 formal

0 comments

read the original abstract

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

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 1 Pith paper

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score. Full citation record

PCIE_Pose Solution for EgoExo4D Pose and Proficiency Estimation Challenge
cs.CV 2025-05 conditional novelty 3.0 of 10

The paper reports first-place results on the CVPR2025 EgoExo4D hand pose, body pose, and proficiency estimation challenges using hybrid transformer-CNN and multimodal fusion architectures.

Pith tools