Papers › Simple Pose: Rethinking and Improving a Bottom-up Approach for Multi-Person Pose Estimation

Simple Pose: Rethinking and Improving a Bottom-up Approach for Multi-Person Pose Estimation

24 Nov 2019arXiv:1911.10529archive 2025-07-28

Jia Li, Wen Su, Zengfu Wang

We rethink a well-know bottom-up approach for multi-person pose estimation and propose an improved one. The improved approach surpasses the baseline significantly thanks to (1) an intuitional yet more sensible representation, which we refer to as body parts to encode the connection information between keypoints, (2) an improved stacked hourglass network with attention mechanisms, (3) a novel focal L2 loss which is dedicated to hard keypoint and keypoint association (body part) mining, and (4) a robust greedy keypoint assignment algorithm for grouping the detected keypoints into individual poses. Our approach not only works straightforwardly but also outperforms the baseline by about 15% in average precision and is comparable to the state of the art on the MS-COCO test-dev dataset. The code and pre-trained models are publicly available online.

PaperPDFCode

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

Code

hellojialee/Improved-Body-Parts officialmentioned on GitHubpytorch report
diamondto/IBP mentioned on GitHubpytorch report
osmr/imgclsmob mentioned on GitHubmxnetMIT 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

2D Human Pose EstimationKeypoint DetectionMulti-Person Pose EstimationPose Estimation

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Keypoint Detection COCO test-dev Simple Pose AP 68.1 #9 of 16 Archive leaderboard report
Keypoint Detection COCO test-dev Simple Pose APL 70.5 #9 of 16 Archive leaderboard report
Keypoint Detection COCO test-dev Simple Pose APM 66.8 #9 of 16 Archive leaderboard report
Keypoint Detection COCO test-dev Simple Pose AR 72.1 #9 of 16 Archive leaderboard report
Keypoint Detection COCO test-dev Simple Pose AR50 88.2 #9 of 16 Archive leaderboard report
Multi-Person Pose Estimation COCO test-dev Identity Mapping Hourglass AP 68.1 #9 of 15 Archive leaderboard report
Multi-Person Pose Estimation COCO test-dev Identity Mapping Hourglass APL 70.5 #9 of 15 Archive leaderboard report
Multi-Person Pose Estimation COCO test-dev Identity Mapping Hourglass APM 66.8 #9 of 15 Archive leaderboard report
Multi-Person Pose Estimation COCO test-dev Identity Mapping Hourglass AR 72.1 #9 of 15 Archive leaderboard report
Multi-Person Pose Estimation COCO test-dev Identity Mapping Hourglass AR50 88.2 #9 of 15 Archive leaderboard report
Pose Estimation COCO test-dev Simple Pose AP 68.1 #36 of 47 Archive leaderboard report
Pose Estimation COCO test-dev Simple Pose APL 70.5 #36 of 47 Archive leaderboard report
Pose Estimation COCO test-dev Simple Pose APM 66.8 #36 of 47 Archive leaderboard report
Pose Estimation COCO test-dev Simple Pose AR 88.2 #36 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.

Methods

1x1 ConvolutionConvolutionHourglass ModuleMax PoolingReLUResidual ConnectionStacked Hourglass Network

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