AI Paper Atlas

Research map / 3D vision / Human pose estimation

Overlooked Poses Actually Make Sense: Distilling Privileged Knowledge for Human Motion Prediction

Xiaoning Sun, Qiongjie Cui, Huaijiang Sun, Bin Li, Weiqing Li, Jianfeng Lu

ECCV 2022 · 3D vision › Human pose estimation · approach: Human motion prediction · 10 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
use PK-GCN instead of Traj-GCNH3.6M · average MPJPE 1000msMPJPE (mm): 114.3 -> 106.4Improved
use PK-GCN instead of MSR-GCNCMU-Mocap · average MPJPE 400msMPJPE (mm): 42.9 -> 40.3Improved
use PK-GCN instead of Traj-GCN3DPW · average MPJPE 1000msMPJPE (mm): 117.8 -> 114.2Improved
use PK-GCN instead of MSR-GCNCMU-Mocap · average MPJPE 80msMPJPE (mm): 8.1 -> 9.4Hurt
use PK-GCN instead of MSR-GCNH3.6M sitting, eating · MPJPE 400msMPJPE (mm): 40.4 -> 41.8Hurt
use PK-GCN instead of Traj-GCNH3.6M discussion · MPJPE 400msMPJPE (mm): 71.7 -> 47.2Improved
add distilled privileged knowledge (vs traditional pattern TP) (ablation)FP-Network · CMU-MocapMPJPEImproved
add a single privileged pose (ablation)PK-GCN · CMU-MocapMPJPEImproved
use 5 instead of 10 privileged poses (ablation)PK-GCN · CMU-Mocap early testpointsMPJPEMixed
add privileged sequence loss (PSL) to baseline (ablation)Traj-GCN · CMU-Mocap 10-25-10 (400ms)MPJPE (mm): 52.7 -> 54.2Hurt
add privileged sequence loss (PSL) to baseline (ablation)MSR-GCN · CMU-Mocap 10-25-10 (1000ms)MPJPE (mm): 83.0 -> 85.6Hurt
reduce PSL weight to 0.6 (ablation)Traj-GCN · CMU-Mocap 10-25-10 (400ms)MPJPE (mm): 54.2 -> 53.7Mixed

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

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