AI Paper Atlas

Research map / 3D vision / Human pose estimation

The Center of Attention: Center-Keypoint Grouping via Attention for Multi-Person Pose Estimation

Guillem Brasó, Nikita Kister, Laura Leal-Taixé

ICCV 2021 · 3D vision › Human pose estimation · approach: Multi-person pose estimation · 56 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 associative-embedding grouping with attention-based CenterGroup grouping (no transformer, same-type) (ablation)CenterGroup (HRNet32) · COCO val2017AP: 67.1 -> 67.5Improved
replace offsets + keypoint matching with attention grouping (ablation)CenterGroup (HRNet32) · COCO val2017AP: 65.3 -> 67.5Improved
make attention type-agnostic (attend over all keypoint types) (ablation)CenterGroup w/o transformer · COCO val2017AP: 67.5 -> 67.5No clear effect
add learned type encoding to type-agnostic attention (ablation)CenterGroup w/o transformer · COCO val2017AP: 67.5 -> 67.9Improved
add keypoint and center transformer encoder (ablation)CenterGroup · COCO val2017AP: 67.9 -> 68.4Improved
add positional encodings to transformer input (ablation)CenterGroup · COCO val2017AP: 68.4 -> 68.6Improved
score poses with center classification instead of heatmap score (ablation)CenterGroup · COCO val2017AP: 66.5 -> 67.1Improved
add keypoint visibility prediction with a simple MLP (ablation)CenterGroup · COCO val2017AP: 67.1 -> 68.2Improved
predict visibility with attention-based head instead of MLP (ablation)CenterGroup · COCO val2017AP: 68.2 -> 68.6Improved
CenterGroup grouping instead of AE grouping (HigherHRNet), speedHigherHRNet · COCO val2017grouping time (ms): 327 -> 52Improved
CenterGroup grouping instead of HigherHRNet on CrowdPoseHrHRNet-W48 · CrowdPose testAP: 65.9 -> 67.6Improved
CenterGroup grouping instead of HigherHRNet on COCO test-devHrHRNet-W32 · COCO test-dev2017 (single-scale)AP: 66.4 -> 67.6Improved

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