AI Paper Atlas

Research map / Detection and segmentation / CNN features

Pose Proposal Networks

Taiki Sekii

ECCV 2018 · Detection and segmentation › CNN features · approach: Region-based and query-based detectors · 49 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 part-scale information via box IoU p(I|R,k,i) and box-based NMS (ablation)PPN ResNet-18 · MPII Multi-Person validationmAP: 72.4 -> 75.5Improved
add part-scale information via box IoU p(I|R,k,i) and box-based NMS (ablation)PPN ResNet-50 · MPII Multi-Person validationmAP: 75.9 -> 78.1Improved
add part-scale information via box IoU p(I|R,k,i) and box-based NMS (ablation)PPN ResNet-101 · MPII Multi-Person validationmAP: 77.5 -> 78.7Improved
add global-context parts association (route-based score) instead of local-only (ablation)PPN ResNet-18 · MPII Multi-Person validationmAP: 73.3 -> 75.5Improved
add global-context parts association (route-based score) instead of local-only (ablation)PPN ResNet-50 · MPII Multi-Person validationmAP: 77.5 -> 78.1Improved
add global-context parts association (route-based score) instead of local-only (ablation)PPN ResNet-101 · MPII Multi-Person validationmAP: 78.4 -> 78.7Improved
add global-context parsing, compared across depth (ablation)PPN ResNet-18 vs ResNet-101 · MPII Multi-Person validationmAP: -2.2% vs -0.3%Improved
deepen backbone from ResNet-18 to ResNet-50 to ResNet-101PPN · MPII Multi-Person test (entire)mAP: 72.8 -> 75.9 -> 76.6Improved
deepen backbone from ResNet-18 to ResNet-50 to ResNet-101PPN · MPII Multi-Person test (288-image subset)mAP: 76.6 -> 79.4 -> 79.1Mixed
use ResNet-18 PPN instead of ResNet-152 DeeperCut part detectorPPN · MPII Single-Person testPCKh: 88.1 vs 88.5 PCKh; 388 vs 34 FPSMixed

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