AI Paper Atlas

Research map / 3D vision / Human pose estimation

Bias-Compensated Integral Regression for Human Pose Estimation

Kerui Gu, Linlin Yang, Michael Bi Mi, Angela Yao

TPAMI 2023 · 3D vision › Human pose estimation · approach: Heatmap and coordinate pose encoding · 25 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 bias compensation (de-bias) (ablation)integral regression (IPR) · COCO val (SBL-ResNet50)AP: 68.2 -> 71.0Improved
add Gaussian prior loss L_de (first 120 epochs) (ablation)integral regression (IPR) · COCO val (SBL-ResNet50)AP: 68.2 -> 70.4Improved
add Laplacian heatmap shrinkage regularizer L_reg (ablation)integral regression (IPR) · COCO val (SBL-ResNet50)AP: 68.2 -> 69.5Improved
apply L_de for all epochs instead of 120 (ablation)integral regression + L_de · COCO val (SBL-ResNet50)AP: 70.4 -> 70.2Hurt
combine L_de and de-bias (BCIR) (ablation)integral regression (IPR) · COCO val (SBL-ResNet50)AP: 68.2 -> 71.2Improved
set beta to 1 instead of 10 (ablation)BCIR · COCO val (SBL-ResNet50)AP: 71.2 -> 70.7Hurt
set beta to 20 instead of 10 (ablation)BCIR · COCO val (SBL-ResNet50)AP: 71.2 -> 70.3Hurt
add BCIR to integral regressionSBL-ResNet50 · COCO valAP: 68.2 -> 71.2Improved
add BCIR to integral regressionHRNet-W32 · COCO valAP: 72.9 -> 75.8Improved
add BCIR to integral regressionSBL-ResNet50 · MPII valPCKh@0.5: 86.2 -> 87.9Improved
add BCIR to 2.5D regression2.5D regression · RHD test2D AUC: 84.4 -> 85.8Improved
use integral regression instead of detection on hard samples (1-5 joints, 32-64px)SBL · COCO valEPE: 9.23 -> 8.10Improved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 0 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