{"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/explicit-box-detection-unifies-end-to-end","title":"Explicit Box Detection Unifies End-to-End Multi-Person Pose Estimation","arxiv_id":"2302.01593","date":"2023-02-03","proceeding":null,"authors":["Jie Yang","Ailing Zeng","Shilong Liu","Feng Li","Ruimao Zhang","Lei Zhang"],"abstract":"This paper presents a novel end-to-end framework with Explicit box Detection for multi-person Pose estimation, called ED-Pose, where it unifies the contextual learning between human-level (global) and keypoint-level (local) information. Different from previous one-stage methods, ED-Pose re-considers this task as two explicit box detection processes with a unified representation and regression supervision. First, we introduce a human detection decoder from encoded tokens to extract global features. It can provide a good initialization for the latter keypoint detection, making the training process converge fast. Second, to bring in contextual information near keypoints, we regard pose estimation as a keypoint box detection problem to learn both box positions and contents for each keypoint. A human-to-keypoint detection decoder adopts an interactive learning strategy between human and keypoint features to further enhance global and local feature aggregation. In general, ED-Pose is conceptually simple without post-processing and dense heatmap supervision. It demonstrates its effectiveness and efficiency compared with both two-stage and one-stage methods. Notably, explicit box detection boosts the pose estimation performance by 4.5 AP on COCO and 9.9 AP on CrowdPose. For the first time, as a fully end-to-end framework with a L1 regression loss, ED-Pose surpasses heatmap-based Top-down methods under the same backbone by 1.2 AP on COCO and achieves the state-of-the-art with 76.6 AP on CrowdPose without bells and whistles. Code is available at https://github.com/IDEA-Research/ED-Pose.","url_abs":"https://arxiv.org/abs/2302.01593v1","url_pdf":"https://arxiv.org/pdf/2302.01593v1.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":"explicit-box-detection-unifies-end-to-end","repo_url":"https://github.com/idea-research/ed-pose","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"explicit-box-detection-unifies-end-to-end","repo_url":"https://github.com/michel-liu/grouppose","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"Apache-2.0"}},{"paper_slug":"explicit-box-detection-unifies-end-to-end","repo_url":"https://github.com/michel-liu/grouppose-paddle","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"paddle","reach":{"status":"ok","spdx":"Apache-2.0"}}],"tasks":[{"task_slug":"2d-human-pose-estimation","task_name":"2D Human Pose Estimation"},{"task_slug":"decoder","task_name":"Decoder"},{"task_slug":"human-detection","task_name":"Human Detection"},{"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"},{"task_slug":"regression-1","task_name":"regression"}],"methods":[{"method_slug":"heatmap","method_name":"Heatmap"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/2d-human-pose-estimation-on-human-art","task":"2D Human Pose Estimation","dataset":"Human-Art","model":"ED-Pose (R50)","rank_in_archive_order":2,"of":10,"metrics":{"AP":"0.723","AP (gt bbox)":"/"},"uses_additional_data":false},{"leaderboard":"/sota/multi-person-pose-estimation-on-crowdpose","task":"Multi-Person Pose Estimation","dataset":"CrowdPose","model":"ED-Pose (Swin-L)","rank_in_archive_order":4,"of":28,"metrics":{"AP Easy":"83.0","AP Hard":"68.3","AP Medium":"77.3","mAP @0.5:0.95":"76.6"},"uses_additional_data":true}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2302.01593","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2302.01593"}},"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/michel-liu/grouppose-paddle","reach":{"status":"ok","spdx":"Apache-2.0"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/idea-research/ed-pose","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/michel-liu/grouppose","reach":{"status":"ok","spdx":"Apache-2.0"}}],"summary":{"unverified":1},"by_repo_kind":{"official":{"samples":1,"ran":0,"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":1,"samples":[{"code_sha256_prefix":"91febdcaa18653c6","entry":"EDPose","repo":"idea-research/ed-pose","repo_kind":"official","path":"models/edpose/edpose.py","file_url":"https://github.com/idea-research/ed-pose/blob/HEAD/models/edpose/edpose.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NOASSERTION","inline_ok":false,"mcp_get_code":{"code_sha256":"91febdcaa18653c6"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}