AI Paper Atlas

Research map / 3D vision / Human pose estimation

Regularizing Vector Embedding in Bottom-Up Human Pose Estimation

Haixin Wang, Lu Zhou, Yingying Chen, Ming Tang, Jinqiao Wang

ECCV 2022 · 3D vision › Human pose estimation · approach: Heatmap and coordinate pose encoding · 19 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 embedding regularization (scale loss) (ablation)AE (HRNet-W32) · CrowdPose TestAP: 64.8 -> 66.0Improved
add adjusted heatmap (ablation)AE + embedding regularization · CrowdPose TestAP: 66.0 -> 67.6Improved
add weighted L2-loss on top of regularization and adjusted heatmap (ablation)Coupled Embedding · CrowdPose TestAP: 67.6 -> 68.9Improved
add all strategies (regularization, adjusted heatmap, weighted loss) (ablation)AE (HRNet-W32) · CrowdPose TestAP_hard: 57.5 -> 60.8Improved
add scale loss to AE for grouping (ablation)AE · CrowdPose Test subset3 (>6 instances, top 20% occlusion)AP: 49.8 -> 52.0Improved
add scale loss to AE for grouping (ablation)AE · CrowdPose Test subset4 (>6 instances, last 20% occlusion)AP: 60.3 -> 62.2Improved
add scale loss to AE for grouping (ablation)AE · CrowdPose Test subset1 (2-5 instances, top 20% occlusion)AP: 64.4 -> 65.9Improved
add scale loss to AE for grouping (ablation)AE · CrowdPose Test subset2 (2-5 instances, last 20% occlusion)AP: 78.8 -> 78.7No clear effect
use instance scale directly as Gaussian scale factor instead of fixed sigma (ablation)AE · CrowdPose TestAP: 64.8 -> 63.9Hurt
use learned embedding-derived scale factor for heatmap sigma (ablation)Coupled Embedding · CrowdPose TestAP: 67.6 -> 67.6Improved
increase embedding dimensionality M from 4 to 8 (ablation)Coupled Embedding · CrowdPose TestAP: 67.1 -> 67.6Improved
increase embedding dimensionality M from 8 to 16 (ablation)Coupled Embedding · CrowdPose TestAP: 67.6 -> 67.3No clear effect

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