AI Paper Atlas

Research map / 3D vision / Human pose estimation

Joint-Relation Transformer for Multi-Person Motion Prediction

Qingyao Xu, Weibo Mao, Jingze Gong, Chenxin Xu, Siheng Chen, Weidi Xie, Ya Zhang, Yanfeng Wang

ICCV 2023 · 3D vision › Human pose estimation · approach: Human motion prediction · 27 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
add relation information (distance and physical constraints) and fusion layers over plain multi-person joint attention (ablation)Joint-Relation Transformer · 3DPW-SoMoF/RCVIM AVG: 41.7 -> 39.5Improved
add distance relation information only (ablation)Joint-Relation Transformer · 3DPW-SoMoF/RCVIM AVG: 41.7 -> 41.1Improved
add physical constraints (bone adjacency and connectivity) only (ablation)Joint-Relation Transformer · 3DPW-SoMoF/RCVIM AVG: 41.7 -> 40.8Improved
add future relative-distance supervision (ablation)Joint-Relation Transformer with both relation types · 3DPW-SoMoF/RCVIM AVG: 40.3 -> 39.5Improved
model interaction between persons instead of single-person model (ablation)Joint-Relation Transformer · 3DPW-SoMoF/RCVIM AVG: 46.2 -> 41.7Improved
add relation information to the single-person model (ablation)single-person variant · 3DPW-SoMoF/RCVIM AVG: 46.2 -> 45.1Improved
use Joint-Relation Transformer instead of SoMoFormer on drift-removed datamulti-person motion prediction · 3DPW-SoMoF/RCVIM AVG / 900ms: 43.8/74.8 -> 39.5/68.8Improved
use Joint-Relation Transformer instead of SoMoFormer on the original 3DPW-SoMoF with camera driftmulti-person motion prediction · 3DPW-SoMoFVIM AVG: 46.3 -> 47.2Hurt
use Joint-Relation Transformer instead of MRT on CMU-Mocapmulti-person motion prediction · CMU-MocapMPJPE 3s: 21.8 -> 18.5Improved

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