{"about":{"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.","site":"https://codewithpapers.app","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","syntology":{"site":"https://syntology.ai","developers":"https://syntology.ai/developers","mcp":{"server":"https://syntology.ai/mcp","transport":"streamable-http","server_card":"https://syntology.ai/.well-known/mcp/server-card.json","auth":{"type":"trial token, no account","trial_token":"https://syntology.ai/api/oauth/trial/token","method":"POST","docs":"https://syntology.ai/developers"}},"have":"https://syntology.ai/api/graph/have?x=<method, arXiv id or title> (free, answers coverage only)","paper_base":"https://syntology.ai/paper/","atlas_base":"https://app.syntology.ai/?focus="},"machine_readable":[{"url":"https://codewithpapers.app/llms.txt","what":"the machine catalog: every machine-readable file, counted"},{"url":"https://codewithpapers.app/index/manifest.json","what":"paper-to-code index by arXiv id, with Syntology's counts"},{"url":"https://codewithpapers.app/search/manifest.json","what":"site search index (titles, authors) and its files"},{"url":"https://codewithpapers.app/download","what":"bulk files: Syntology's layer, described there"},{"url":"https://codewithpapers.app/build_manifest.json","what":"the build record: inputs, counts, exclusions, probes"}]},"url":"/paper/learning-to-refine-human-pose-estimation","title":"Learning to Refine Human Pose Estimation","arxiv_id":"1804.07909","date":"2018-04-21","proceeding":null,"authors":["Mihai Fieraru","Anna Khoreva","Leonid Pishchulin","Bernt Schiele"],"abstract":"Multi-person pose estimation in images and videos is an important yet\nchallenging task with many applications. Despite the large improvements in\nhuman pose estimation enabled by the development of convolutional neural\nnetworks, there still exist a lot of difficult cases where even the\nstate-of-the-art models fail to correctly localize all body joints. This\nmotivates the need for an additional refinement step that addresses these\nchallenging cases and can be easily applied on top of any existing method. In\nthis work, we introduce a pose refinement network (PoseRefiner) which takes as\ninput both the image and a given pose estimate and learns to directly predict a\nrefined pose by jointly reasoning about the input-output space. In order for\nthe network to learn to refine incorrect body joint predictions, we employ a\nnovel data augmentation scheme for training, where we model \"hard\" human pose\ncases. We evaluate our approach on four popular large-scale pose estimation\nbenchmarks such as MPII Single- and Multi-Person Pose Estimation, PoseTrack\nPose Estimation, and PoseTrack Pose Tracking, and report systematic improvement\nover the state of the art.","url_abs":"http://arxiv.org/abs/1804.07909v1","url_pdf":"http://arxiv.org/pdf/1804.07909v1.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":[],"tasks":[{"task_slug":"data-augmentation","task_name":"Data Augmentation"},{"task_slug":"keypoint-detection","task_name":"Keypoint Detection"},{"task_slug":"multi-person-pose-estimation","task_name":"Multi-Person Pose Estimation"},{"task_slug":"multi-person-pose-estimation-and-tracking","task_name":"Multi-Person Pose Estimation and Tracking"},{"task_slug":"pose-estimation","task_name":"Pose Estimation"},{"task_slug":"pose-tracking","task_name":"Pose Tracking"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/keypoint-detection-on-mpii-multi-person","task":"Keypoint Detection","dataset":"MPII Multi-Person","model":"Refine","rank_in_archive_order":4,"of":9,"metrics":{"mAP@0.5":"78%"},"uses_additional_data":false},{"leaderboard":"/sota/multi-person-pose-estimation-on-mpii-multi","task":"Multi-Person Pose Estimation","dataset":"MPII Multi-Person","model":"Refine","rank_in_archive_order":4,"of":9,"metrics":{"AP":"78%"},"uses_additional_data":false},{"leaderboard":"/sota/multi-person-pose-estimation-on-posetrack2018","task":"Multi-Person Pose Estimation","dataset":"PoseTrack2018","model":"Refine","rank_in_archive_order":4,"of":4,"metrics":{"Mean mAP":"73.8"},"uses_additional_data":false},{"leaderboard":"/sota/multi-person-pose-estimation-and-tracking-on-1","task":"Multi-Person Pose Estimation and Tracking","dataset":"PoseTrack2018","model":"Refine","rank_in_archive_order":1,"of":1,"metrics":{"MOTA":"58.4"},"uses_additional_data":false},{"leaderboard":"/sota/pose-estimation-on-mpii-single-person","task":"Pose Estimation","dataset":"MPII Single Person","model":"Refine","rank_in_archive_order":2,"of":5,"metrics":{"PCKh@0.5":"92.1"},"uses_additional_data":false}],"syntology":{"syntology_url":"https://syntology.ai/paper/1804.07909","atlas_url":"https://app.syntology.ai/?focus=1804.07909","mcp":null,"developers":"https://syntology.ai/developers","held":true,"reason":"arxiv_id_in_atlas","checked_against":{"atlas_ids":549449,"atlas_ids_sha256":"afd72399dafd9906e9062927f70655952385a3d75488558e1f0484e950ab09b7","read_at":"2026-10-05T01:46:21Z"},"agent_calls":[{"tool":"get_citation_path","arguments":{"paper_1":"1804.07909"},"arguments_in":{"paper_2":"another paper's arXiv id or title"},"call":"get_citation_path(paper_1=\"1804.07909\", paper_2=\"…\")"},{"tool":"get_concepts_for_paper","arguments":{"arxiv_id":"1804.07909"},"call":"get_concepts_for_paper(arxiv_id=\"1804.07909\")"}],"by_repo":[],"by_repo_is":"one row per repository in the archive's code links, Syntology's graph links or the samples; samples 0 means no sample is linked to this paper, a statement about Syntology's coverage, not about the repository: with harvested_for_other_papers present, Syntology harvested the repository for that many other papers, and without it, Syntology harvested nothing from it; placed_by_identical_code counts samples whose link records no repository, placed here because identical code was harvested from this repository for another paper; ran counts executions on a synthesized input and instrument counts failures of Syntology's instrument, not of the code"},"code_links_note":"the archive holds no code link for this paper","arxiv_metadata":null,"syntology_extracted_results":null,"record_sha256":"4599e9cae942c111c24f9d69a171611831fea68d9361af3252a54ede542c11db","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}