Papers › Learning Delicate Local Representations for Multi-Person Pose Estimation

Learning Delicate Local Representations for Multi-Person Pose Estimation

9 Mar 2020ECCV 2020 8arXiv:2003.04030archive 2025-07-28

Yuanhao Cai, Zhicheng Wang, Zhengxiong Luo, Binyi Yin, Angang Du, Haoqian Wang, Xiangyu Zhang, Xinyu Zhou, Erjin Zhou, Jian Sun

In this paper, we propose a novel method called Residual Steps Network (RSN). RSN aggregates features with the same spatial size (Intra-level features) efficiently to obtain delicate local representations, which retain rich low-level spatial information and result in precise keypoint localization. Additionally, we observe the output features contribute differently to final performance. To tackle this problem, we propose an efficient attention mechanism - Pose Refine Machine (PRM) to make a trade-off between local and global representations in output features and further refine the keypoint locations. Our approach won the 1st place of COCO Keypoint Challenge 2019 and achieves state-of-the-art results on both COCO and MPII benchmarks, without using extra training data and pretrained model. Our single model achieves 78.6 on COCO test-dev, 93.0 on MPII test dataset. Ensembled models achieve 79.2 on COCO test-dev, 77.1 on COCO test-challenge dataset. The source code is publicly available for further research at https://github.com/caiyuanhao1998/RSN/

PaperPDFConference PDFCodeCode Syntology ran

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

For agents, Syntology's MCP tool lists every function and class Syntology harvested from this paper and whether it ran (how to connect): get_harvested_code_for_paper(arxiv_id="2003.04030")

Code

Syntology Ran 2 of 3 code samples harvested from 2 repositories linked to this paper; 1 has no recorded run. Of those that ran: 2 ran · violated contract.

By repository: official repository: 2 samples from 1 repository, 2 ran; community (archive-listed): 1 sample from 1 repository, 0 ran. The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

caiyuanhao1998/RSN officialmentioned in papermentioned on GitHubpytorch report
chenyilun95/tf-cpn mentioned on GitHubtfMIT report
open-mmlab/mmpose pytorchApache-2.0 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

3 samples harvested; 2 ran; 0 honoured the contract we drafted; 1 has no recorded run. Read from Syntology's graph 2026-09-24; that is when this build read the record, not when the samples ran.

2ran · violated contract
1unverified

Licence: 0 of the 3 samples are pointer only, meaning Syntology does not serve that copy's text. This page shows no code text for any sample; each one links to its file in the repository.

Harvested from 2 repositories linked to this paper, official or community; each sample names its own and says which. “Ran” means the sample executed on a synthesized input. It does not mean the output is correct, and nothing here reproduces the paper's results. “Honoured” and “violated” refer to a contract Syntology drafted from the code itself; “our draft was wrong” and “fixture could not drive it” are failures of Syntology's instrument, not of the code.

Each sample ends with its code_sha256, Syntology's identity for that exact code. An agent fetches the stored sample with Syntology's MCP tool get_code(code_sha256="…") (how to connect); click an identity to copy that call.

Repository labels, per sample. official repository: The archive marks this repository official for the paper. named in the paper: The archive records that the paper mentions this repository; it is not marked official. community (archive-listed): In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper. found in paper text by Syntology: Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted. community: Not in the archive's code links for this paper; a community repository Syntology harvested. Samples from a repository marked official are listed first. Licence labels name the repository's licence as recorded at harvest. “Pointer only” means Syntology does not serve that copy's text, for one of four reasons: no licence file was found; the licence was not identified; the licence is recorded as permissive but that copy's record is not marked cleared; or the licence is outside the permissive list Syntology serves text under (MIT, Apache-2.0, BSD and similar). Some licences outside that list permit redistribution, such as WTFPL, and GPL-3.0 under its conditions; they are simply not on the list. Hover a licence label for the reason. File links open the file on GitHub at the default branch, which may have changed since the harvest.

all_gather caiyuanhao1998/RSN/lib/utils/comm.py official repository ran · violated contract MIT (permissive) · 37ff649cdc90971d · report
reduce_dict caiyuanhao1998/RSN/lib/utils/comm.py official repository ran · violated contract MIT (permissive) · 2a3280757ce5a198 · report
get_seg chenyilun95/tf-cpn/models/COCO.res101.256x192.CPN/dataset.py community (archive-listed) unverified MIT (permissive) · 92e487bd163f89e2 · report

Tasks

Keypoint DetectionMulti-Person Pose EstimationPose Estimation

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Keypoint Detection COCO (Common Objects in Context) 4xRSN-50(384×288) Test AP 78.6 #1 of 24 Archive leaderboard report
Keypoint Detection COCO test-challenge 4×RSN-50 AP 77.1 #1 of 8 Archive leaderboard report
Keypoint Detection COCO test-challenge 4×RSN-50 AP50 93.3 #1 of 8 Archive leaderboard report
Keypoint Detection COCO test-challenge 4×RSN-50 AP75 83.6 #1 of 8 Archive leaderboard report
Keypoint Detection COCO test-challenge 4×RSN-50 APL 82.6 #1 of 8 Archive leaderboard report
Keypoint Detection COCO test-challenge 4×RSN-50 AR 82.6 #1 of 8 Archive leaderboard report
Keypoint Detection COCO test-challenge 4×RSN-50 AR50 96.1 #1 of 8 Archive leaderboard report
Keypoint Detection COCO test-challenge 4×RSN-50 AR75 88.2 #1 of 8 Archive leaderboard report
Keypoint Detection COCO test-challenge 4×RSN-50 ARL 88.7 #1 of 8 Archive leaderboard report
Keypoint Detection COCO test-challenge 4×RSN-50 ARM 78.0 #1 of 8 Archive leaderboard report
Multi-Person Pose Estimation COCO (Common Objects in Context) RSN AP 0.792 #1 of 15 Archive leaderboard report
Pose Estimation COCO test-dev 4xRSN-50 (ensemble) AP 79.2 #5 of 47 Archive leaderboard report
Pose Estimation COCO test-dev 4xRSN-50 (ensemble) AP50 94.4 #5 of 47 Archive leaderboard report
Pose Estimation COCO test-dev 4xRSN-50 (ensemble) AP75 87.1 #5 of 47 Archive leaderboard report
Pose Estimation COCO test-dev 4xRSN-50 (ensemble) APL 76.1 #5 of 47 Archive leaderboard report
Pose Estimation COCO test-dev 4xRSN-50 (ensemble) APM 83.8 #5 of 47 Archive leaderboard report
Pose Estimation COCO test-dev 4xRSN-50 (ensemble) AR 84.1 #5 of 47 Archive leaderboard report
Pose Estimation COCO test-dev 4xRSN-50 AP 78.6 #8 of 47 Archive leaderboard report
Pose Estimation COCO test-dev 4xRSN-50 AP50 94.3 #8 of 47 Archive leaderboard report
Pose Estimation COCO test-dev 4xRSN-50 AP75 86.6 #8 of 47 Archive leaderboard report
Pose Estimation COCO test-dev 4xRSN-50 APL 75.5 #8 of 47 Archive leaderboard report
Pose Estimation COCO test-dev 4xRSN-50 APM 83.3 #8 of 47 Archive leaderboard report
Pose Estimation COCO test-dev 4xRSN-50 AR 83.8 #8 of 47 Archive leaderboard report
Pose Estimation MPII Human Pose 4xRSN-50 PCKh-0.5 93.0 #7 of 46 Archive leaderboard report
Pose Estimation MPII Single Person 4xRSN-50 PCKh@0.5 93 #1 of 5 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