Papers › The Center of Attention: Center-Keypoint Grouping via Attention for Multi-Person Pose...

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

11 Oct 2021ICCV 2021 10arXiv:2110.05132archive 2025-07-28

Guillem Brasó, Nikita Kister, Laura Leal-Taixé

We introduce CenterGroup, an attention-based framework to estimate human poses from a set of identity-agnostic keypoints and person center predictions in an image. Our approach uses a transformer to obtain context-aware embeddings for all detected keypoints and centers and then applies multi-head attention to directly group joints into their corresponding person centers. While most bottom-up methods rely on non-learnable clustering at inference, CenterGroup uses a fully differentiable attention mechanism that we train end-to-end together with our keypoint detector. As a result, our method obtains state-of-the-art performance with up to 2.5x faster inference time than competing bottom-up methods. Our code is available at https://github.com/dvl-tum/center-group .

PaperPDFConference PDFCode

In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

Code

dvl-tum/center-group officialmentioned in papermentioned on GitHubpytorch report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

ClusteringMulti-Person Pose EstimationPose Estimation

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Multi-Person Pose Estimation COCO (Common Objects in Context) CenterGroup AP 0.714 #6 of 15 Archive leaderboard report
Multi-Person Pose Estimation COCO (Common Objects in Context) CenterGroup Test AP 71.4 #6 of 15 Archive leaderboard report
Multi-Person Pose Estimation CrowdPose CenterGroup AP Easy 76.6 #14 of 28 Archive leaderboard report
Multi-Person Pose Estimation CrowdPose CenterGroup AP Hard 61.5 #14 of 28 Archive leaderboard report
Multi-Person Pose Estimation CrowdPose CenterGroup AP Medium 70.0 #14 of 28 Archive leaderboard report
Multi-Person Pose Estimation CrowdPose CenterGroup mAP @0.5:0.95 69.4 #14 of 28 Archive leaderboard report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

Methods

Linear LayerSoftmax

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections