AI Paper Atlas

Research map / 3D vision / Human pose estimation

Graph-PCNN: Two Stage Human Pose Estimation with Graph Pose Refinement

Jian Wang, Xiang Long, Yuan Gao, Errui Ding, Shilei Wen

ECCV 2020 · 3D vision › Human pose estimation · approach: Heatmap and coordinate pose encoding · 115 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 two-stage framework (stage2 regression) over simple baselineGraph-PCNN (R50) · COCO val2017 128x96AP: 59.3 -> 64.6Improved
add two-stage framework (stage2 regression) over simple baselineGraph-PCNN (R50) · COCO val2017 256x192AP: 70.4 -> 72.6Improved
add two-stage framework (stage2 regression) over simple baselineGraph-PCNN (R50) · COCO val2017 384x288AP: 72.2 -> 73.6Improved
train with Graph-PCNN and use only stage1 heatmap outputGraph-PCNN stage1 (R50) · COCO val2017 128x96stage1 AP: 59.3 -> 61.1Improved
train with Graph-PCNN and use only stage1 heatmap outputGraph-PCNN stage1 (R50) · COCO val2017 384x288stage1 AP: 72.2 -> 72.7Improved
add graph pose refinement instead of struct-agnostic module (ablation)Graph-PCNN (R50) · COCO val2017 128x96stage2 AP: 63.8 -> 64.6Improved
add graph pose refinement instead of struct-agnostic module (ablation)Graph-PCNN (R50) · COCO val2017 128x96stage1 AP: 60.7 -> 61.1Improved
use reliability-weighted messages (with heat response) instead of all weights set to 1 (ablation)GPR · COCO val2017 128x96stage2 AP: 52.1 -> 64.6Improved
add heat response factor to neighbour weights (ablation)GPR · COCO val2017 128x96stage2 AP: 64.5 -> 64.6Improved
add guided points shuffling during training (ablation)GPR · COCO val2017 128x96stage2 AP: 64.3 -> 64.6Improved
replace DARK decoding with Graph-PCNN regression refinementHRNet-W32 128x96 · COCO val2017AP: 70.7 -> 71.5Improved
replace DARK decoding with Graph-PCNN regression refinementResNet-152 128x96 · COCO val2017AP: 63.1 -> 66.1Improved

Later papers that compared with this method

1 later accepted paper reports Graph-PCNN as a baseline in their results tables; 1 of them report a better number on most of the results they share with it.

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