atlas

Research map / 3D vision / Human pose estimation

AdaptivePose: Human Parts as Adaptive Points

AAAI 2022 · 3D vision › Human pose estimation · approach: Multi-person pose estimation · 25 citations (OpenAlex)

Read the paperCheck your idea against 108,967 papers

AI-extracted summary. Written by AI from the paper's title only (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 PPM and receptive field adaptation (ablation)AdaptivePose baseline without PPM, RFA, TR, or auxiliary loss · COCO mini-valAP: 56.0 -> 57.3Helped
Add adaptive two-hop regression (ablation)AdaptivePose baseline without PPM, RFA, TR, or auxiliary loss · COCO mini-valAP: 56.0 -> 60.0Helped
Add receptive field adaptation (ablation)AdaptivePose with PPM and two-hop regression · COCO mini-valAP: 60.0 -> 61.6Helped
Add auxiliary keypoint heatmap loss (ablation)AdaptivePose with PPM, RFA, and two-hop regression · COCO mini-valAP: 61.6 -> 64.9Helped
Share adaptive points across the center-aware and regression branches (ablation)AdaptivePose · COCO mini-valAP: 64.2 -> 64.9Helped
Replace adaptive two-hop regression with hierarchical keypoint regression (ablation)AdaptivePose · COCO mini-valAP: 60.0 -> 58.5Hurt
Add heatmap refinement to the two-hop regressed predictions (ablation)AdaptivePose two-hop regression · COCO mini-valAP: 64.9 -> 64.6Hurt

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