AI Paper Atlas

Research map / 3D vision / Human pose estimation

Motion-X: A Large-scale 3D Expressive Whole-body Human Motion Dataset

Jing Lin, Ailing Zeng, Shunlin Lu, Yuanhao Cai, Ruimao Zhang, Haoqian Wang, Lei Zhang

NeurIPS 2023 · 3D vision › Human pose estimation · approach: Physics and sensor-based motion capture · 23 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
train on Motion-X instead of HumanML3DMLD · HumanML3D testFID: 1.579 -> 0.999Improved
train on Motion-X instead of HumanML3DMLD · Motion-X testFID: 12.309 -> 0.914Improved
train on Motion-X instead of HumanML3DMLD · Motion-X testR-Precision: 0.570 -> 0.733Improved
add frame-level face and body pose descriptions to semantic text input (ablation)MLD · Motion-X testFID: 38% reduction in FIDImproved
add 10% Motion-X single-view data to trainingHand4Whole · EHF and AGORA valMPVPE: 7.8% decreaseImproved
use learning-based progressive fitting for SMPL-X annotation vs prior fitting methodsannotation pipeline · EHFPA-MPVPE: over 30% error reductionImproved

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy