Papers › Rethinking pose estimation in crowds: overcoming the detection information-bottleneck...

Rethinking pose estimation in crowds: overcoming the detection information-bottleneck and ambiguity

13 Jun 2023arXiv:2306.07879archive 2025-07-28

Mu Zhou, Lucas Stoffl, Mackenzie Weygandt Mathis, Alexander Mathis

Frequent interactions between individuals are a fundamental challenge for pose estimation algorithms. Current pipelines either use an object detector together with a pose estimator (top-down approach), or localize all body parts first and then link them to predict the pose of individuals (bottom-up). Yet, when individuals closely interact, top-down methods are ill-defined due to overlapping individuals, and bottom-up methods often falsely infer connections to distant bodyparts. Thus, we propose a novel pipeline called bottom-up conditioned top-down pose estimation (BUCTD) that combines the strengths of bottom-up and top-down methods. Specifically, we propose to use a bottom-up model as the detector, which in addition to an estimated bounding box provides a pose proposal that is fed as condition to an attention-based top-down model. We demonstrate the performance and efficiency of our approach on animal and human pose estimation benchmarks. On CrowdPose and OCHuman, we outperform previous state-of-the-art models by a significant margin. We achieve 78.5 AP on CrowdPose and 48.5 AP on OCHuman, an improvement of 8.6% and 7.8% over the prior art, respectively. Furthermore, we show that our method strongly improves the performance on multi-animal benchmarks involving fish and monkeys. The code is available at https://github.com/amathislab/BUCTD

PaperPDFCodeCode 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="2306.07879")

Code

Syntology Ran 4 of 6 code samples harvested from 1 repository linked to this paper; 2 have no recorded run. Of those that ran: 4 ran with no contract checked.

By repository: official repository: 6 samples from 1 repository, 4 ran. The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

amathislab/BUCTD 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

6 samples harvested; 4 ran; 0 honoured the contract we drafted; 2 have no recorded run. Read from Syntology's graph 2026-09-24; that is when this build read the record, not when the samples ran.

4ran
2unverified

Licence: 0 of the 6 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 amathislab/BUCTD. “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.

ChannelAttentionModule amathislab/BUCTD/lib/models/pose_hrnet_coam.py official repository ran · metamorphic tier: deterministic Apache-2.0 (permissive) · a844f9a6f9386bd4 · report
PositionAttentionModule amathislab/BUCTD/lib/models/pose_hrnet_coam.py official repository ran · metamorphic tier: deterministic Apache-2.0 (permissive) · d660799bfda097cb · report
ScaledDotProductAttention amathislab/BUCTD/lib/models/pose_hrnet_coam.py official repository ran · metamorphic tier: deterministic Apache-2.0 (permissive) · 9b618b70e00f414b · report
SimplifiedScaledDotProductAttention amathislab/BUCTD/lib/models/pose_hrnet_coam.py official repository ran · metamorphic tier: invariant fingerprinted Apache-2.0 (permissive) · a93236cbfbf7eb1f · report
CoAMBlock amathislab/BUCTD/lib/models/pose_hrnet_coam.py official repository unverified Apache-2.0 (permissive) · 87ab3b0e6c684486 · report
DAModule amathislab/BUCTD/lib/models/pose_hrnet_coam.py official repository unverified Apache-2.0 (permissive) · 0424ee6cbfa2e859 · report

Tasks

Animal Pose EstimationMulti-Person Pose EstimationPose Estimation

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Animal Pose Estimation Fish-100 HRNet-W48 + Faster R-CNN mAP 89.1 #1 of 4 Archive leaderboard report
Animal Pose Estimation Fish-100 BUCTD-preNet-W48 (DLCRNet) mAP 88.7 #2 of 4 Archive leaderboard report
Animal Pose Estimation Fish-100 BUCTD-preNet-W48 (CID-W32) mAP 88.0 #3 of 4 Archive leaderboard report
Animal Pose Estimation Marmoset-8K BUCTD-preNet-W48 (CID-W32) mAP 93.3 #1 of 4 Archive leaderboard report
Animal Pose Estimation Marmoset-8K CID-W32 mAP 92.5 #2 of 4 Archive leaderboard report
Animal Pose Estimation Marmoset-8K BUCTD-CoAM-W48 (DLCRNet) mAP 91.6 #3 of 4 Archive leaderboard report
Animal Pose Estimation TriMouse-161 BUCTD-CoAM-W48 (DLCRNet) mAP 99.1 #1 of 7 Archive leaderboard report
Animal Pose Estimation TriMouse-161 DLCRNet mAP 95.8 #3 of 7 Archive leaderboard report
Animal Pose Estimation TriMouse-161 CID-W32 mAP 86.8 #6 of 7 Archive leaderboard report
Multi-Person Pose Estimation CrowdPose BUCTD-W48 (w/cond. input from PETR, and generative sampling) AP Easy 83.9 #2 of 28 Archive leaderboard report
Multi-Person Pose Estimation CrowdPose BUCTD-W48 (w/cond. input from PETR, and generative sampling) AP Hard 72.3 #2 of 28 Archive leaderboard report
Multi-Person Pose Estimation CrowdPose BUCTD-W48 (w/cond. input from PETR, and generative sampling) AP Medium 79.0 #2 of 28 Archive leaderboard report
Multi-Person Pose Estimation CrowdPose BUCTD-W48 (w/cond. input from PETR, and generative sampling) mAP @0.5:0.95 78.5 #2 of 28 Archive leaderboard report
Pose Estimation COCO (Common Objects in Context) BUCTD (PETR, with generative sampling) AP 77.8 #4 of 10 Archive leaderboard report
Pose Estimation COCO (Common Objects in Context) BUCTD (PETR, with generative sampling) APL 83.7 #10 of 10 Archive leaderboard report
Pose Estimation COCO (Common Objects in Context) BUCTD (PETR, with generative sampling) APM 74.2 #10 of 10 Archive leaderboard report
Pose Estimation CrowdPose BUCTD-W48 (w/cond. input from PETR, and generative sampling) AP 78.5 #1 of 12 Archive leaderboard report
Pose Estimation CrowdPose BUCTD-W48 (w/cond. input from PETR, and generative sampling) AP Easy 83.9 #1 of 12 Archive leaderboard report
Pose Estimation CrowdPose BUCTD-W48 (w/cond. input from PETR, and generative sampling) AP Hard 72.3 #1 of 12 Archive leaderboard report
Pose Estimation CrowdPose BUCTD-W48 (w/cond. input from PETR, and generative sampling) AP Medium 79.0 #1 of 12 Archive leaderboard report
Pose Estimation CrowdPose BUCTD-W48 (w/cond. input from PETR) AP 76.7 #3 of 12 Archive leaderboard report
Pose Estimation CrowdPose BUCTD-W48 AP 72.9 #6 of 12 Archive leaderboard report
Pose Estimation OCHuman BUCTD (CID-W32) Test AP 47.2 #6 of 19 Archive leaderboard report
Pose Estimation OCHuman BUCTD (CID-W32) Validation AP 47.7 #6 of 19 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