AI Paper Atlas

Research map / 3D vision / Human pose estimation

PersonLab: Person Pose Estimation and Instance Segmentation with a Bottom-Up, Part-Based, Geometric Embedding Model

George Papandreou, Tyler Zhu, Liang-Chieh Chen, Spyros Gidaris, Jonathan Tompson, Kevin Murphy

ECCV 2018 · 3D vision › Human pose estimation · approach: Multi-person pose estimation · 660 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 recurrent mid- and long-range offset refinement (ablation)PersonLab ResNet-101 · COCO keypoints valAP: 0.632 -> 0.665Improved
add recurrent offset refinement (ablation)PersonLab ResNet-101 · COCO person segmentation valmask AP: 0.355 -> 0.382Improved
add offset refinement, effect on large instances (ablation)PersonLab ResNet-101 · COCO person segmentation vallarge-instance mask AP: 0.501 -> 0.592Improved
use Expected-OKS keypoint scoring instead of Hough scores (hard NMS) (ablation)PersonLab ResNet-101 · COCO keypoints valAP: 0.632 -> 0.647Improved
use soft-NMS instead of hard NMS (Expected-OKS scoring) (ablation)PersonLab ResNet-101 · COCO keypoints valAP: 0.647 -> 0.665Improved
impute keypoints of small person instances for training (ablation)PersonLab ResNet-101 · COCO keypoints valAP: 0.665 -> 0.657Hurt
impute keypoints of small person instances for training (ablation)PersonLab ResNet-101 · COCO person segmentation valmask AP: 0.338 -> 0.382Improved
impute small-instance keypoints, effect on small instances (ablation)PersonLab ResNet-101 · COCO person segmentation valsmall-instance mask AP: 0.076 -> 0.164Improved
reduce output stride from 32 to 16 with atrous convolution (ablation)PersonLab ResNet-101 · COCO keypoints val, input 1401AP: 0.641 -> 0.656Improved
reduce output stride from 16 to 8 (ablation)PersonLab ResNet-101 · COCO keypoints val, input 1401AP: 0.656 -> 0.665Improved
increase input size beyond 1401 to 1801 (stride 8) (ablation)PersonLab ResNet-101 · COCO keypoints valAP: 0.665 -> 0.652Hurt
use ResNet-152 instead of ResNet-101 backbone (single-scale)PersonLab · COCO keypoints test-devAP: 0.655 -> 0.665Improved

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