AI Paper Atlas

Research map / 3D vision / Human pose estimation

Hierarchical Binary CNNs for Landmark Localization with Limited Resources

Adrian Bulat, Georgios Tzimiropoulos

TPAMI 2018 · 3D vision › Human pose estimation · approach: Heatmap and coordinate pose encoding · 35 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
replace original bottleneck with hierarchical parallel multi-scale block (same parameters)binary HG · MPII valPCKh: 67.2% -> 72.7%Improved
remove 1x1 convolutions from the multi-scale block (ablation)binary HG · MPII valPCKh: 69.3% -> 75.5%Improved
widen the thin 3x3 layer from 128 to 256 channels (ablation)binary bottleneck · MPII valPCKh: 67.2% -> 70.7%Improved
add multi-scale filtering (max-pool branch and decomposed 5x5) (ablation)binary bottleneck · MPII valPCKh: 67.2% -> 69.3%Improved
add data augmentation (ablation)binary Ours Final · MPII valPCKh: 72.1% -> 76%Improved
use sigmoid cross-entropy loss instead of L2 (ablation)binary Ours Final · MPII valPCKh: 73.8% -> 76%Improved
use max pooling instead of average pooling (ablation)binary Ours Final · MPII valPCKh: 71.9% -> 76%Improved
add ReLU after each convolutional layer (ablation)binary Ours Final · MPII valPCKh: 76% -> 78.1%Improved
replace residual blocks in upsampling branches with skip concatenation (improved HG) (ablation)binary HG with Ours block · MPII valPCKh: 76% -> 76.6%Improved
stack a second binarized HG network (ablation)binary HG with Ours block · MPII valPCKh: 76% -> 79.9%Improved
stack a third binarized HG network (ablation)binary HG with Ours block · MPII valPCKh: 79.9% -> 81.3%Improved
increase block cardinality up to 16 (ablation)binary Ours block · MPII valPCKh: 1% lowerHurt

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