{"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/unipose-detecting-any-keypoints","title":"X-Pose: Detecting Any Keypoints","arxiv_id":"2310.08530","date":"2023-10-12","proceeding":null,"authors":["Jie Yang","Ailing Zeng","Ruimao Zhang","Lei Zhang"],"abstract":"This work aims to address an advanced keypoint detection problem: how to accurately detect any keypoints in complex real-world scenarios, which involves massive, messy, and open-ended objects as well as their associated keypoints definitions. Current high-performance keypoint detectors often fail to tackle this problem due to their two-stage schemes, under-explored prompt designs, and limited training data. To bridge the gap, we propose X-Pose, a novel end-to-end framework with multi-modal (i.e., visual, textual, or their combinations) prompts to detect multi-object keypoints for any articulated (e.g., human and animal), rigid, and soft objects within a given image. Moreover, we introduce a large-scale dataset called UniKPT, which unifies 13 keypoint detection datasets with 338 keypoints across 1,237 categories over 400K instances. Training with UniKPT, X-Pose effectively aligns text-to-keypoint and image-to-keypoint due to the mutual enhancement of multi-modal prompts based on cross-modality contrastive learning. Our experimental results demonstrate that X-Pose achieves notable improvements of 27.7 AP, 6.44 PCK, and 7.0 AP compared to state-of-the-art non-promptable, visual prompt-based, and textual prompt-based methods in each respective fair setting. More importantly, the in-the-wild test demonstrates X-Pose's strong fine-grained keypoint localization and generalization abilities across image styles, object categories, and poses, paving a new path to multi-object keypoint detection in real applications. Our code and dataset are available at https://github.com/IDEA-Research/X-Pose.","url_abs":"https://arxiv.org/abs/2310.08530v2","url_pdf":"https://arxiv.org/pdf/2310.08530v2.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":"unipose-detecting-any-keypoints","repo_url":"https://github.com/IDEA-Research/UniPose","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"NOASSERTION"}},{"paper_slug":"unipose-detecting-any-keypoints","repo_url":"https://github.com/idea-research/x-pose","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"NOASSERTION"}}],"tasks":[{"task_slug":"2d-human-pose-estimation","task_name":"2D Human Pose Estimation"},{"task_slug":"2d-pose-estimation","task_name":"2D Pose Estimation"},{"task_slug":"animal-pose-estimation","task_name":"Animal Pose Estimation"},{"task_slug":"contrastive-learning","task_name":"Contrastive Learning"},{"task_slug":"keypoint-detection","task_name":"Keypoint Detection"},{"task_slug":"multi-person-pose-estimation","task_name":"Multi-Person Pose Estimation"}],"methods":[{"method_slug":"align","method_name":"ALIGN"},{"method_slug":"contrastive-learning","method_name":"Contrastive Learning"},{"method_slug":"focus","method_name":"Focus"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/2d-human-pose-estimation-on-human-art","task":"2D Human Pose Estimation","dataset":"Human-Art","model":"UniPose","rank_in_archive_order":1,"of":10,"metrics":{"AP":"0.759"},"uses_additional_data":true},{"leaderboard":"/sota/2d-pose-estimation-on-300w","task":"2D Pose Estimation","dataset":"300W","model":"UniPose","rank_in_archive_order":1,"of":1,"metrics":{"Mean PCK@0.2":"99.4"},"uses_additional_data":true},{"leaderboard":"/sota/2d-pose-estimation-on-animal-kingdom","task":"2D Pose Estimation","dataset":"Animal Kingdom","model":"UniPose","rank_in_archive_order":1,"of":1,"metrics":{"Mean PCK@0.2":"96.1","PCK@0.05":"71.5"},"uses_additional_data":true},{"leaderboard":"/sota/2d-pose-estimation-on-desert-locust","task":"2D Pose Estimation","dataset":"Desert Locust","model":"UniPose","rank_in_archive_order":1,"of":1,"metrics":{"Mean PCK@0.2":"99.9"},"uses_additional_data":true},{"leaderboard":"/sota/2d-pose-estimation-on-macaquepose","task":"2D Pose Estimation","dataset":"MacaquePose","model":"UniPose","rank_in_archive_order":1,"of":1,"metrics":{"AP":"79.4"},"uses_additional_data":true},{"leaderboard":"/sota/2d-pose-estimation-on-vinegar-fly","task":"2D Pose Estimation","dataset":"Vinegar Fly","model":"UniPose","rank_in_archive_order":1,"of":1,"metrics":{"Mean PCK@0.2":"99.9"},"uses_additional_data":true},{"leaderboard":"/sota/animal-pose-estimation-on-ap-10k","task":"Animal Pose Estimation","dataset":"AP-10K","model":"UniPose","rank_in_archive_order":4,"of":10,"metrics":{"AP":"79.2"},"uses_additional_data":true},{"leaderboard":"/sota/multi-person-pose-estimation-on-coco","task":"Multi-Person Pose Estimation","dataset":"COCO (Common Objects in Context)","model":"UniPose","rank_in_archive_order":3,"of":15,"metrics":{"AP":"0.768"},"uses_additional_data":true}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2310.08530","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2310.08530"}},"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/idea-research/x-pose","reach":{"status":"ok","spdx":"NOASSERTION"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/IDEA-Research/UniPose","reach":{"status":"ok","spdx":"NOASSERTION"}}],"summary":{"ran":9,"ran_fixture":1,"ran_draft_wrong":1,"unverified":2},"by_repo_kind":{"official":{"samples":13,"ran":11,"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":13,"samples":[{"code_sha256_prefix":"32a6ee4e27f89e71","entry":"crop","repo":"idea-research/x-pose","repo_kind":"official","path":"transforms.py","file_url":"https://github.com/idea-research/x-pose/blob/HEAD/transforms.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NOASSERTION","inline_ok":false,"mcp_get_code":{"code_sha256":"32a6ee4e27f89e71"}},{"code_sha256_prefix":"16ffb3896995c049","entry":"func_attention","repo":"IDEA-Research/UniPose","repo_kind":"official","path":"models/UniPose/fuse_modules.py","file_url":"https://github.com/IDEA-Research/UniPose/blob/HEAD/models/UniPose/fuse_modules.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NOASSERTION","inline_ok":false,"mcp_get_code":{"code_sha256":"16ffb3896995c049"}},{"code_sha256_prefix":"e3b2768e6a9c1cb5","entry":"gen_encoder_output_proposals","repo":"IDEA-Research/UniPose","repo_kind":"official","path":"models/UniPose/utils.py","file_url":"https://github.com/IDEA-Research/UniPose/blob/HEAD/models/UniPose/utils.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"e3b2768e6a9c1cb5"}},{"code_sha256_prefix":"00d365116e665402","entry":"get_sine_pos_embed","repo":"IDEA-Research/UniPose","repo_kind":"official","path":"models/UniPose/utils.py","file_url":"https://github.com/IDEA-Research/UniPose/blob/HEAD/models/UniPose/utils.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NOASSERTION","inline_ok":false,"mcp_get_code":{"code_sha256":"00d365116e665402"}},{"code_sha256_prefix":"a940274705e77acb","entry":"l1norm","repo":"IDEA-Research/UniPose","repo_kind":"official","path":"models/UniPose/fuse_modules.py","file_url":"https://github.com/IDEA-Research/UniPose/blob/HEAD/models/UniPose/fuse_modules.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NOASSERTION","inline_ok":false,"mcp_get_code":{"code_sha256":"a940274705e77acb"}},{"code_sha256_prefix":"906ace82161a66eb","entry":"l2norm","repo":"IDEA-Research/UniPose","repo_kind":"official","path":"models/UniPose/fuse_modules.py","file_url":"https://github.com/IDEA-Research/UniPose/blob/HEAD/models/UniPose/fuse_modules.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NOASSERTION","inline_ok":false,"mcp_get_code":{"code_sha256":"906ace82161a66eb"}},{"code_sha256_prefix":"93ac42433372f73b","entry":"post_process","repo":"IDEA-Research/UniPose","repo_kind":"official","path":"models/UniPose/mask_generate.py","file_url":"https://github.com/IDEA-Research/UniPose/blob/HEAD/models/UniPose/mask_generate.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NOASSERTION","inline_ok":false,"mcp_get_code":{"code_sha256":"93ac42433372f73b"}},{"code_sha256_prefix":"6473ea3973310f60","entry":"prepare_for_mask","repo":"IDEA-Research/UniPose","repo_kind":"official","path":"models/UniPose/mask_generate.py","file_url":"https://github.com/IDEA-Research/UniPose/blob/HEAD/models/UniPose/mask_generate.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NOASSERTION","inline_ok":false,"mcp_get_code":{"code_sha256":"6473ea3973310f60"}},{"code_sha256_prefix":"23eb1c50e6bb2ba5","entry":"sigmoid_focal_loss","repo":"IDEA-Research/UniPose","repo_kind":"official","path":"models/UniPose/utils.py","file_url":"https://github.com/IDEA-Research/UniPose/blob/HEAD/models/UniPose/utils.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"23eb1c50e6bb2ba5"}},{"code_sha256_prefix":"f9fd6241d935f07b","entry":"window_partition","repo":"IDEA-Research/UniPose","repo_kind":"official","path":"models/UniPose/swin_transformer.py","file_url":"https://github.com/IDEA-Research/UniPose/blob/HEAD/models/UniPose/swin_transformer.py","link_basis":"harvester_set","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"f9fd6241d935f07b"}},{"code_sha256_prefix":"fb32094c6dbece71","entry":"window_reverse","repo":"IDEA-Research/UniPose","repo_kind":"official","path":"models/UniPose/swin_transformer.py","file_url":"https://github.com/IDEA-Research/UniPose/blob/HEAD/models/UniPose/swin_transformer.py","link_basis":"harvester_set","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"fb32094c6dbece71"}},{"code_sha256_prefix":"3eb47e0aa4d44ce5","entry":"hflip","repo":"idea-research/x-pose","repo_kind":"official","path":"transforms.py","file_url":"https://github.com/idea-research/x-pose/blob/HEAD/transforms.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":"3eb47e0aa4d44ce5"}},{"code_sha256_prefix":"a82091666b9db8cf","entry":"multi_head_attention_forward","repo":"IDEA-Research/UniPose","repo_kind":"official","path":"models/UniPose/attention.py","file_url":"https://github.com/IDEA-Research/UniPose/blob/HEAD/models/UniPose/attention.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"a82091666b9db8cf"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}