AI Paper Atlas

Research map / 3D vision / Human pose estimation

AlphaPose: Whole-Body Regional Multi-Person Pose Estimation and Tracking in Real-Time

Hao-Shu Fang, Jiefeng Li, Hongyang Tang, Chao Xu, Haoyi Zhu, Yuliang Xiu, Yong–Lu Li, Cewu Lu

TPAMI 2022 · 3D vision › Human pose estimation · approach: Multi-person pose estimation · 855 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 two-step heatmap normalization instead of one-step soft-max (ablation)FastPose50 · Halpe-FullBodymAP: 38.1 -> 44.1Improved
use two-step heatmap normalization instead of one-step soft-max (ablation)FastPose50 · COCO valmAP: 67.1 -> 69.5Improved
add symmetric integral keypoints regression (SIKR) (ablation)FastPose50 · Halpe-FullBodymAP: 42.3 -> 44.1Improved
add symmetric integral keypoints regression (SIKR) (ablation)FastPose50 · COCO valmAP: 64.6 -> 69.5Improved
add parametric pose NMS (ablation)FastPose50 · Halpe-FullBodymAP: 43.7 -> 44.1Improved
add parametric pose NMS (ablation)FastPose50 · COCO valmAP: 68.2 -> 69.5Improved
add part-guided proposal generator (PGPG) (ablation)FastPose50-dcn · Halpe-FullBodymAP: 47.1 -> 48.4Improved
use symmetric integral regression instead of heatmapFastPose50 · Halpe-FullBody (full-body)AP: 0.417 -> 0.441Improved
use symmetric integral regression instead of heatmapFastPose · COCO test-dev (body)AP: 0.718 -> 0.649Hurt
add deformable convolution to the backboneFastPose50-si · Halpe-FullBody (full-body)AP: 0.441 -> 0.462Improved
add multi-domain knowledge distillation and PGPG training (ablation)FastPose50-dcn-si · Halpe-FullBody (full-body)AP: 0.462 -> 0.484Improved
use ResNet152 instead of ResNet50 backboneFastPose-si · Halpe-FullBody (full-body)AP: 0.441 -> 0.451Improved

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