{"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/real-time-2d-multi-person-pose-estimation-on","title":"Real-time 2D Multi-Person Pose Estimation on CPU: Lightweight OpenPose","arxiv_id":"1811.12004","date":"2018-11-29","proceeding":null,"authors":["Daniil Osokin"],"abstract":"In this work we adapt multi-person pose estimation architecture to use it on\nedge devices. We follow the bottom-up approach from OpenPose, the winner of\nCOCO 2016 Keypoints Challenge, because of its decent quality and robustness to\nnumber of people inside the frame. With proposed network design and optimized\npost-processing code the full solution runs at 28 frames per second (fps) on\nIntel$\\unicode{xAE}$ NUC 6i7KYB mini PC and 26 fps on Core$^{TM}$ i7-6850K CPU.\nThe network model has 4.1M parameters and 9 billions floating-point operations\n(GFLOPs) complexity, which is just ~15% of the baseline 2-stage OpenPose with\nalmost the same quality. The code and model are available as a part of\nIntel$\\unicode{xAE}$ OpenVINO$^{TM}$ Toolkit.","url_abs":"http://arxiv.org/abs/1811.12004v1","url_pdf":"http://arxiv.org/pdf/1811.12004v1.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":"real-time-2d-multi-person-pose-estimation-on","repo_url":"https://github.com/2xic/openpose-pigs","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"unanswered"}},{"paper_slug":"real-time-2d-multi-person-pose-estimation-on","repo_url":"https://github.com/Daniil-Osokin/lightweight-human-pose-estimation-3d-demo.pytorch","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"unanswered"}},{"paper_slug":"real-time-2d-multi-person-pose-estimation-on","repo_url":"https://github.com/Daniil-Osokin/lightweight-human-pose-estimation.pytorch","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"real-time-2d-multi-person-pose-estimation-on","repo_url":"https://github.com/ModelBunker/Lightweight-OpenPose-PyTorch","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"real-time-2d-multi-person-pose-estimation-on","repo_url":"https://github.com/Rocketbase-AI/rockets-lightpose","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"real-time-2d-multi-person-pose-estimation-on","repo_url":"https://github.com/hsk9767/open_pose","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"real-time-2d-multi-person-pose-estimation-on","repo_url":"https://github.com/murdockhou/lightweight_openpose","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":null},{"paper_slug":"real-time-2d-multi-person-pose-estimation-on","repo_url":"https://github.com/omkarbhope/Pose-Estimation","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"unanswered"}},{"paper_slug":"real-time-2d-multi-person-pose-estimation-on","repo_url":"https://github.com/osmr/imgclsmob","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"mxnet","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"real-time-2d-multi-person-pose-estimation-on","repo_url":"https://github.com/tyIceStream/lightweight-human-pose-estimation.OpenCV","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":null,"task_name":"CPU"},{"task_slug":"multi-person-pose-estimation","task_name":"Multi-Person Pose Estimation"},{"task_slug":"pose-estimation","task_name":"Pose Estimation"}],"methods":[{"method_slug":"pc","method_name":"pc"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/1811.12004","atlas_url":"https://app.syntology.ai/?focus=1811.12004","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":"1811.12004"},"arguments_in":{"paper_2":"another paper's arXiv id or title"},"call":"get_citation_path(paper_1=\"1811.12004\", paper_2=\"…\")"},{"tool":"get_concepts_for_paper","arguments":{"arxiv_id":"1811.12004"},"call":"get_concepts_for_paper(arxiv_id=\"1811.12004\")"}],"by_repo":[{"repo":"2xic/openpose-pigs","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0},{"repo":"Daniil-Osokin/lightweight-human-pose-estimation-3d-demo.pytorch","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0},{"repo":"Daniil-Osokin/lightweight-human-pose-estimation.pytorch","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0},{"repo":"ModelBunker/Lightweight-OpenPose-PyTorch","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0,"harvested_for_other_papers":1,"harvested_for":["1712.03453"],"harvested_for_calls":[{"arxiv_id":"1712.03453","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"1712.03453"},"call":"get_harvested_code_for_paper(arxiv_id=\"1712.03453\")"}]},{"repo":"Rocketbase-AI/rockets-lightpose","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0},{"repo":"hsk9767/open_pose","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0},{"repo":"murdockhou/lightweight_openpose","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0},{"repo":"omkarbhope/Pose-Estimation","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0},{"repo":"osmr/imgclsmob","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0,"harvested_for_other_papers":1,"harvested_for":["2004.08955"],"harvested_for_calls":[{"arxiv_id":"2004.08955","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"2004.08955"},"call":"get_harvested_code_for_paper(arxiv_id=\"2004.08955\")"}]},{"repo":"tyIceStream/lightweight-human-pose-estimation.OpenCV","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0}],"by_repo_harvested_for_is":"harvested_for: the arXiv ids (as Syntology's graph holds them) of every paper whose samples Syntology's graph links to this repository, in arXiv-id order, complete; the page names the first 3 and says how many more. A link only: it does not say the papers are the same work, that one copied the other, or that the code implements this paper's method; harvested_for_calls gives the get_harvested_code_for_paper call for each arXiv-shaped id among them","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":null,"arxiv_metadata":null,"syntology_extracted_results":null,"record_sha256":"23dfa95e4bc86b3491ae1e07e417d91efa12c04484fe075854f12b966e554cf0","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}