Papers › Towards High Performance Human Keypoint Detection

Towards High Performance Human Keypoint Detection

3 Feb 2020arXiv:2002.00537archive 2025-07-28

Jing Zhang, Zhe Chen, DaCheng Tao

Human keypoint detection from a single image is very challenging due to occlusion, blur, illumination and scale variance. In this paper, we address this problem from three aspects by devising an efficient network structure, proposing three effective training strategies, and exploiting four useful postprocessing techniques. First, we find that context information plays an important role in reasoning human body configuration and invisible keypoints. Inspired by this, we propose a cascaded context mixer (CCM), which efficiently integrates spatial and channel context information and progressively refines them. Then, to maximize CCM's representation capability, we develop a hard-negative person detection mining strategy and a joint-training strategy by exploiting abundant unlabeled data. It enables CCM to learn discriminative features from massive diverse poses. Third, we present several sub-pixel refinement techniques for postprocessing keypoint predictions to improve detection accuracy. Extensive experiments on the MS COCO keypoint detection benchmark demonstrate the superiority of the proposed method over representative state-of-the-art (SOTA) methods. Our single model achieves comparable performance with the winner of the 2018 COCO Keypoint Detection Challenge. The final ensemble model sets a new SOTA on this benchmark.

PaperPDFCode

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

Code

chaimi2013/CCM officialmentioned in paper 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

Human DetectionKeypoint DetectionPose EstimationVocal Bursts Intensity Prediction

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Pose Estimation COCO test-dev CCM+ AP 78.9 #6 of 47 Archive leaderboard report
Pose Estimation COCO test-dev CCM+ AP50 93.8 #6 of 47 Archive leaderboard report
Pose Estimation COCO test-dev CCM+ AP75 86 #6 of 47 Archive leaderboard report
Pose Estimation COCO test-dev CCM+ APL 84.5 #6 of 47 Archive leaderboard report
Pose Estimation COCO test-dev CCM+ APM 75 #6 of 47 Archive leaderboard report
Pose Estimation COCO test-dev CCM+ AR 83.6 #6 of 47 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.

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