AI Paper Atlas

Research map / 3D vision / Human pose estimation

Stacked Hourglass Networks for Human Pose Estimation

Alejandro Newell, Kaiyu Yang, Jia Deng

ECCV 2016 · 3D vision › Human pose estimation · approach: Heatmap and coordinate pose encoding · 5,720 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
increase stacks from 2 to 4 hourglasses at equal parameters (ablation)Stacked Hourglass · MPII validationaccuracy: 87.4% -> 87.8%Improved
increase stacks from 4 to 8 hourglasses at equal parameters (ablation)Stacked Hourglass · MPII validationaccuracy: 87.8% -> 88.1%Improved
increase stacks from 2 to 8 on halfway intermediate predictions (ablation)Stacked Hourglass · MPII validationintermediate accuracy: 84.6% -> 86.5% -> 87.1%Improved
stack two hourglasses instead of a single hourglass with same layers (ablation)Hourglass · MPII validation training curvevalidation accuracyImproved
add intermediate supervision to a single hourglass (ablation)Hourglass · MPII validation training curvevalidation accuracyImproved
combine stacking with intermediate supervision (ablation)Hourglass · MPII validation training curvevalidation accuracyImproved
average heatmaps of original and flipped input at test time (ablation)Stacked Hourglass · MPII validationaccuracy: 1% average improvementImproved
replace standard large-filter convolutions with residual or Inception modules (ablation)Hourglass layers · MPIIperformanceImproved
further explore layer modifications beyond residual modules (ablation)Hourglass layers · MPIIperformanceNo clear effect
evaluate only visible wrists rather than all wristsStacked Hourglass · MPII validation wristaccuracy: 85.5% -> 93.6%Improved
evaluate only occluded wrists rather than all wristsStacked Hourglass · MPII validation wristaccuracy: 85.5% -> 61.1%Hurt
evaluate only visible elbows rather than all elbowsStacked Hourglass · MPII validation elbowaccuracy: 90.5% -> 95.1%Improved

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