{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/rethinking-pose-estimation-in-crowds","title":"Rethinking pose estimation in crowds: overcoming the detection information-bottleneck and ambiguity","arxiv_id":"2306.07879","date":"2023-06-13","proceeding":null,"authors":["Mu Zhou","Lucas Stoffl","Mackenzie Weygandt Mathis","Alexander Mathis"],"abstract":"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","url_abs":"https://arxiv.org/abs/2306.07879v2","url_pdf":"https://arxiv.org/pdf/2306.07879v2.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"rethinking-pose-estimation-in-crowds","repo_url":"https://github.com/amathislab/BUCTD","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"animal-pose-estimation","task_name":"Animal Pose Estimation"},{"task_slug":"multi-person-pose-estimation","task_name":"Multi-Person Pose Estimation"},{"task_slug":"pose-estimation","task_name":"Pose Estimation"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/animal-pose-estimation-on-fish-100","task":"Animal Pose Estimation","dataset":"Fish-100","model":"HRNet-W48 + Faster R-CNN","rank_in_archive_order":1,"of":4,"metrics":{"mAP":"89.1"},"uses_additional_data":false},{"leaderboard":"/sota/animal-pose-estimation-on-fish-100","task":"Animal Pose Estimation","dataset":"Fish-100","model":"BUCTD-preNet-W48 (DLCRNet)","rank_in_archive_order":2,"of":4,"metrics":{"mAP":"88.7"},"uses_additional_data":false},{"leaderboard":"/sota/animal-pose-estimation-on-fish-100","task":"Animal Pose Estimation","dataset":"Fish-100","model":"BUCTD-preNet-W48 (CID-W32)","rank_in_archive_order":3,"of":4,"metrics":{"mAP":"88.0"},"uses_additional_data":false},{"leaderboard":"/sota/animal-pose-estimation-on-marmoset-8k","task":"Animal Pose Estimation","dataset":"Marmoset-8K","model":"BUCTD-preNet-W48 (CID-W32)","rank_in_archive_order":1,"of":4,"metrics":{"mAP":"93.3"},"uses_additional_data":false},{"leaderboard":"/sota/animal-pose-estimation-on-marmoset-8k","task":"Animal Pose Estimation","dataset":"Marmoset-8K","model":"CID-W32","rank_in_archive_order":2,"of":4,"metrics":{"mAP":"92.5"},"uses_additional_data":false},{"leaderboard":"/sota/animal-pose-estimation-on-marmoset-8k","task":"Animal Pose Estimation","dataset":"Marmoset-8K","model":"BUCTD-CoAM-W48 (DLCRNet)","rank_in_archive_order":3,"of":4,"metrics":{"mAP":"91.6"},"uses_additional_data":false},{"leaderboard":"/sota/animal-pose-estimation-on-trimouse-161","task":"Animal Pose Estimation","dataset":"TriMouse-161","model":"BUCTD-CoAM-W48 (DLCRNet)","rank_in_archive_order":1,"of":7,"metrics":{"mAP":"99.1"},"uses_additional_data":false},{"leaderboard":"/sota/animal-pose-estimation-on-trimouse-161","task":"Animal Pose Estimation","dataset":"TriMouse-161","model":"DLCRNet","rank_in_archive_order":3,"of":7,"metrics":{"mAP":"95.8 "},"uses_additional_data":false},{"leaderboard":"/sota/animal-pose-estimation-on-trimouse-161","task":"Animal Pose Estimation","dataset":"TriMouse-161","model":"CID-W32","rank_in_archive_order":6,"of":7,"metrics":{"mAP":"86.8"},"uses_additional_data":false},{"leaderboard":"/sota/multi-person-pose-estimation-on-crowdpose","task":"Multi-Person Pose Estimation","dataset":"CrowdPose","model":"BUCTD-W48 (w/cond. input from PETR, and generative sampling)","rank_in_archive_order":2,"of":28,"metrics":{"AP Easy":"83.9","AP Hard":"72.3","AP Medium":"79.0","mAP @0.5:0.95":"78.5"},"uses_additional_data":false},{"leaderboard":"/sota/pose-estimation-on-coco","task":"Pose Estimation","dataset":"COCO (Common Objects in Context)","model":"BUCTD (PETR,  with generative sampling)","rank_in_archive_order":4,"of":10,"metrics":{"AP":"77.8"},"uses_additional_data":false},{"leaderboard":"/sota/pose-estimation-on-coco","task":"Pose Estimation","dataset":"COCO (Common Objects in Context)","model":"BUCTD (PETR, with generative sampling)","rank_in_archive_order":10,"of":10,"metrics":{"APL":"83.7","APM":"74.2"},"uses_additional_data":false},{"leaderboard":"/sota/pose-estimation-on-crowdpose","task":"Pose Estimation","dataset":"CrowdPose","model":"BUCTD-W48 (w/cond. input from PETR, and generative sampling)","rank_in_archive_order":1,"of":12,"metrics":{"AP":"78.5","AP Easy":"83.9","AP Hard":"72.3","AP Medium":"79.0"},"uses_additional_data":false},{"leaderboard":"/sota/pose-estimation-on-crowdpose","task":"Pose Estimation","dataset":"CrowdPose","model":"BUCTD-W48 (w/cond. input from PETR)","rank_in_archive_order":3,"of":12,"metrics":{"AP":"76.7"},"uses_additional_data":false},{"leaderboard":"/sota/pose-estimation-on-crowdpose","task":"Pose Estimation","dataset":"CrowdPose","model":"BUCTD-W48","rank_in_archive_order":6,"of":12,"metrics":{"AP":"72.9"},"uses_additional_data":false},{"leaderboard":"/sota/pose-estimation-on-ochuman","task":"Pose Estimation","dataset":"OCHuman","model":"BUCTD (CID-W32)","rank_in_archive_order":6,"of":19,"metrics":{"Test AP":"47.2","Validation AP":"47.7"},"uses_additional_data":false}],"syntology":{"syntology_url":"https://syntology.ai/paper/2306.07879","atlas_url":"https://app.syntology.ai/?focus=2306.07879","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2306.07879"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-25T09:33:49+00:00","read_at_is":"when the build read Syntology's graph, not when any sample ran","claim":"Per-sample execution status on synthesized fixtures; not a correctness claim about the paper. Samples come from repositories linked to the paper, official or community; repo_kind says which.","repos":[{"provenance":"deterministic:regex_extraction","url":"https://github.com/amathislab/BUCTD","reach":null}],"summary":{"ran":4,"unverified":2},"by_repo_kind":{"official":{"samples":6,"ran":4,"repositories":1}},"repo_kind_vocabulary":{"official":"The archive marks this repository official for the paper","named_in_paper":"The archive records that the paper mentions this repository; it is not marked official","listed":"In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper","found_in_text":"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"},"n_pointer_only_for_licence":0,"samples":[{"code_sha256_prefix":"a844f9a6f9386bd4","entry":"ChannelAttentionModule","repo":"amathislab/BUCTD","repo_kind":"official","path":"lib/models/pose_hrnet_coam.py","file_url":"https://github.com/amathislab/BUCTD/blob/HEAD/lib/models/pose_hrnet_coam.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"a844f9a6f9386bd4"}},{"code_sha256_prefix":"d660799bfda097cb","entry":"PositionAttentionModule","repo":"amathislab/BUCTD","repo_kind":"official","path":"lib/models/pose_hrnet_coam.py","file_url":"https://github.com/amathislab/BUCTD/blob/HEAD/lib/models/pose_hrnet_coam.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"d660799bfda097cb"}},{"code_sha256_prefix":"9b618b70e00f414b","entry":"ScaledDotProductAttention","repo":"amathislab/BUCTD","repo_kind":"official","path":"lib/models/pose_hrnet_coam.py","file_url":"https://github.com/amathislab/BUCTD/blob/HEAD/lib/models/pose_hrnet_coam.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"9b618b70e00f414b"}},{"code_sha256_prefix":"a93236cbfbf7eb1f","entry":"SimplifiedScaledDotProductAttention","repo":"amathislab/BUCTD","repo_kind":"official","path":"lib/models/pose_hrnet_coam.py","file_url":"https://github.com/amathislab/BUCTD/blob/HEAD/lib/models/pose_hrnet_coam.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"a93236cbfbf7eb1f"}},{"code_sha256_prefix":"87ab3b0e6c684486","entry":"CoAMBlock","repo":"amathislab/BUCTD","repo_kind":"official","path":"lib/models/pose_hrnet_coam.py","file_url":"https://github.com/amathislab/BUCTD/blob/HEAD/lib/models/pose_hrnet_coam.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"87ab3b0e6c684486"}},{"code_sha256_prefix":"0424ee6cbfa2e859","entry":"DAModule","repo":"amathislab/BUCTD","repo_kind":"official","path":"lib/models/pose_hrnet_coam.py","file_url":"https://github.com/amathislab/BUCTD/blob/HEAD/lib/models/pose_hrnet_coam.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"0424ee6cbfa2e859"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}