AI Paper Atlas

Research map / 3D vision / Human pose estimation

Single-Network Whole-Body Pose Estimation

Gines Hidalgo, Yaadhav Raaj, Haroon Idrees, Donglai Xiang, Hanbyul Joo, Tomas Simon, Yaser Sheikh

ICCV 2019 · 3D vision › Human pose estimation · approach: Multi-person pose estimation · 117 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 deeper higher-resolution architecture instead of shallow OpenPose-sized network (ablation)whole-body network · COCO val (multi-scale)Body AP: 60.9 -> 65.6Improved
use deeper higher-resolution architecture instead of shallow network (ablation)whole-body network · COCO val (multi-scale)Foot AP: 70.2 -> 76.2Improved
add face and hand keypoints to the shallow body-foot modelshallow OpenPose-style network · COCO val bodyBody AP: 65.3 -> 60.9Hurt
add face and hand keypoints to the deep body-foot modeldeep network · COCO val bodyBody AP: 66.4 -> 65.6Hurt
deep body-foot architecture instead of OpenPose body-footbody-foot detector · COCO val (multi-scale)Body AP: 65.3 -> 66.4Improved
choose 3 PAF stages with 8 blocks and 96-256w over 1 stage with 10 blocks at equal run-time (ablation)PAF network · COCO val bodyAP: 65.8 -> 66.4Improved
use 5 PAF stages with narrow width instead of 3 stages (ablation)PAF network · COCO val bodyAP: 66.4 -> 65.5Hurt
deep instead of shallow whole-body on hard in-the-wild faces (ablation)whole-body network · i-bug faceFace AR: 50.6 -> 54.5Improved
deep whole-body vs OpenPose on in-the-wild faceswhole-body network · i-bug faceFace AR: 52.4 -> 54.5Improved
single-network deep whole-body vs OpenPose on lab-recorded faceswhole-body network · Multi-PIE faceFace AR: 96.3 -> 93.2Hurt
deep instead of shallow whole-body on hand (ablation)whole-body network · Hand MPIIHand AR: 82.4 -> 88.1Improved
deep whole-body vs OpenPose on in-the-wild handswhole-body network · Hand MPIIHand AR: 82.7 -> 88.1Improved

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