{"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/distribution-aware-coordinate-representation","title":"Distribution-Aware Coordinate Representation for Human Pose Estimation","arxiv_id":"1910.06278","date":"2019-10-14","proceeding":"CVPR 2020 6","authors":["Feng Zhang","Xiatian Zhu","Hanbin Dai","Mao Ye","Ce Zhu"],"abstract":"While being the de facto standard coordinate representation in human pose estimation, heatmap is never systematically investigated in the literature, to our best knowledge. This work fills this gap by studying the coordinate representation with a particular focus on the heatmap. Interestingly, we found that the process of decoding the predicted heatmaps into the final joint coordinates in the original image space is surprisingly significant for human pose estimation performance, which nevertheless was not recognised before. In light of the discovered importance, we further probe the design limitations of the standard coordinate decoding method widely used by existing methods, and propose a more principled distribution-aware decoding method. Meanwhile, we improve the standard coordinate encoding process (i.e. transforming ground-truth coordinates to heatmaps) by generating accurate heatmap distributions for unbiased model training. Taking the two together, we formulate a novel Distribution-Aware coordinate Representation of Keypoint (DARK) method. Serving as a model-agnostic plug-in, DARK significantly improves the performance of a variety of state-of-the-art human pose estimation models. Extensive experiments show that DARK yields the best results on two common benchmarks, MPII and COCO, consistently validating the usefulness and effectiveness of our novel coordinate representation idea.","url_abs":"https://arxiv.org/abs/1910.06278v1","url_pdf":"https://arxiv.org/pdf/1910.06278v1.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":"distribution-aware-coordinate-representation","repo_url":"https://github.com/leoxiaobin/deep-high-resolution-net.pytorch","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"distribution-aware-coordinate-representation","repo_url":"https://github.com/Klawens/SwinPose","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"Apache-2.0"}},{"paper_slug":"distribution-aware-coordinate-representation","repo_url":"https://github.com/chandyalex/Darkpose_Tensorflow","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok"}},{"paper_slug":"distribution-aware-coordinate-representation","repo_url":"https://github.com/ilovepose/DarkPose","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"distribution-aware-coordinate-representation","repo_url":"https://github.com/PaddlePaddle/PaddleDetection","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"paddle","reach":null},{"paper_slug":"distribution-aware-coordinate-representation","repo_url":"https://github.com/open-mmlab/mmpose","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"pytorch","reach":{"status":"ok","spdx":"Apache-2.0"}}],"tasks":[{"task_slug":"keypoint-detection","task_name":"Keypoint Detection"},{"task_slug":"multi-person-pose-estimation","task_name":"Multi-Person Pose Estimation"},{"task_slug":"pose-estimation","task_name":"Pose Estimation"}],"methods":[{"method_slug":"heatmap","method_name":"Heatmap"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/keypoint-detection-on-coco","task":"Keypoint Detection","dataset":"COCO (Common Objects in Context)","model":"DarkPose(384x288)","rank_in_archive_order":5,"of":24,"metrics":{"Test AP":"76.2"},"uses_additional_data":false},{"leaderboard":"/sota/multi-person-pose-estimation-on-coco","task":"Multi-Person Pose Estimation","dataset":"COCO (Common Objects in Context)","model":"DarkPose","rank_in_archive_order":2,"of":15,"metrics":{"AP":"0.774"},"uses_additional_data":true},{"leaderboard":"/sota/pose-estimation-on-coco-test-dev","task":"Pose Estimation","dataset":"COCO test-dev","model":"HRNet-W48+DARK","rank_in_archive_order":10,"of":47,"metrics":{"AP":"77.4","AP50":"92.6","AP75":"84.6","APL":"83.7","APM":"73.6","AR":"82.3"},"uses_additional_data":false},{"leaderboard":"/sota/pose-estimation-on-mpii-human-pose","task":"Pose Estimation","dataset":"MPII Human Pose","model":"DarkPose","rank_in_archive_order":25,"of":46,"metrics":{"PCKh-0.5":"90.6"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1910.06278","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1910.06278"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-24T18:15:14+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":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/open-mmlab/mmpose","reach":{"status":"ok","spdx":"Apache-2.0"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/ilovepose/DarkPose","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/chandyalex/Darkpose_Tensorflow","reach":{"status":"ok"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/PaddlePaddle/PaddleDetection","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/leoxiaobin/deep-high-resolution-net.pytorch","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/Klawens/SwinPose","reach":{"status":"ok","spdx":"Apache-2.0"}}],"summary":{"ran_fixture":3,"ran_draft_wrong":2,"unverified":4},"by_repo_kind":{"listed":{"samples":9,"ran":5,"repositories":2}},"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":"b91b38261b03587d","entry":"calc_dists","repo":"Klawens/SwinPose","repo_kind":"listed","path":"lib/core/evaluate.py","file_url":"https://github.com/Klawens/SwinPose/blob/HEAD/lib/core/evaluate.py","link_basis":"harvester_set","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"b91b38261b03587d"}},{"code_sha256_prefix":"fac5364e2f53c6db","entry":"conv3x3","repo":"Klawens/SwinPose","repo_kind":"listed","path":"lib/models/pose_hrnet.py","file_url":"https://github.com/Klawens/SwinPose/blob/HEAD/lib/models/pose_hrnet.py","link_basis":"harvester_set","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"fac5364e2f53c6db"}},{"code_sha256_prefix":"1c2da88027e6e151","entry":"dist_acc","repo":"Klawens/SwinPose","repo_kind":"listed","path":"lib/core/evaluate.py","file_url":"https://github.com/Klawens/SwinPose/blob/HEAD/lib/core/evaluate.py","link_basis":"harvester_set","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"1c2da88027e6e151"}},{"code_sha256_prefix":"55c58ef5f795e3d1","entry":"get_max_preds","repo":"ilovepose/DarkPose","repo_kind":"listed","path":"lib/core/inference.py","file_url":"https://github.com/ilovepose/DarkPose/blob/HEAD/lib/core/inference.py","link_basis":"first_harvest_node","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"deterministic","behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"55c58ef5f795e3d1"}},{"code_sha256_prefix":"6700129ef38592b0","entry":"taylor","repo":"ilovepose/DarkPose","repo_kind":"listed","path":"lib/core/inference.py","file_url":"https://github.com/ilovepose/DarkPose/blob/HEAD/lib/core/inference.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"6700129ef38592b0"}},{"code_sha256_prefix":"a81d7a40407a092a","entry":"gaussian_blur","repo":"Klawens/SwinPose","repo_kind":"listed","path":"lib/core/inference.py","file_url":"https://github.com/Klawens/SwinPose/blob/HEAD/lib/core/inference.py","link_basis":"harvester_set","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":"a81d7a40407a092a"}},{"code_sha256_prefix":"78015ae361e585ca","entry":"get_pose_net","repo":"Klawens/SwinPose","repo_kind":"listed","path":"lib/models/pose_hrnet.py","file_url":"https://github.com/Klawens/SwinPose/blob/HEAD/lib/models/pose_hrnet.py","link_basis":"harvester_set","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":"78015ae361e585ca"}},{"code_sha256_prefix":"498dab54632ae89c","entry":"get_pose_net","repo":"Klawens/SwinPose","repo_kind":"listed","path":"lib/models/hourglass.py","file_url":"https://github.com/Klawens/SwinPose/blob/HEAD/lib/models/hourglass.py","link_basis":"harvester_set","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":"498dab54632ae89c"}},{"code_sha256_prefix":"dda50630404ba452","entry":"get_pose_net","repo":"Klawens/SwinPose","repo_kind":"listed","path":"lib/models/pose_resnet.py","file_url":"https://github.com/Klawens/SwinPose/blob/HEAD/lib/models/pose_resnet.py","link_basis":"harvester_set","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":"dda50630404ba452"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}