{"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/lstm-pose-machines","title":"LSTM Pose Machines","arxiv_id":"1712.06316","date":"2017-12-18","proceeding":"CVPR 2018 6","authors":["Yue Luo","Jimmy Ren","Zhouxia Wang","Wenxiu Sun","Jinshan Pan","Jianbo Liu","Jiahao Pang","Liang Lin"],"abstract":"We observed that recent state-of-the-art results on single image human pose\nestimation were achieved by multi-stage Convolution Neural Networks (CNN).\nNotwithstanding the superior performance on static images, the application of\nthese models on videos is not only computationally intensive, it also suffers\nfrom performance degeneration and flicking. Such suboptimal results are mainly\nattributed to the inability of imposing sequential geometric consistency,\nhandling severe image quality degradation (e.g. motion blur and occlusion) as\nwell as the inability of capturing the temporal correlation among video frames.\nIn this paper, we proposed a novel recurrent network to tackle these problems.\nWe showed that if we were to impose the weight sharing scheme to the\nmulti-stage CNN, it could be re-written as a Recurrent Neural Network (RNN).\nThis property decouples the relationship among multiple network stages and\nresults in significantly faster speed in invoking the network for videos. It\nalso enables the adoption of Long Short-Term Memory (LSTM) units between video\nframes. We found such memory augmented RNN is very effective in imposing\ngeometric consistency among frames. It also well handles input quality\ndegradation in videos while successfully stabilizes the sequential outputs. The\nexperiments showed that our approach significantly outperformed current\nstate-of-the-art methods on two large-scale video pose estimation benchmarks.\nWe also explored the memory cells inside the LSTM and provided insights on why\nsuch mechanism would benefit the prediction for video-based pose estimations.","url_abs":"http://arxiv.org/abs/1712.06316v4","url_pdf":"http://arxiv.org/pdf/1712.06316v4.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":"lstm-pose-machines","repo_url":"https://github.com/lawy623/LSTM_Pose_Machines","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"none","reach":null}],"tasks":[{"task_slug":"2d-human-pose-estimation","task_name":"2D Human Pose Estimation"},{"task_slug":"pose-estimation","task_name":"Pose Estimation"}],"methods":[{"method_slug":"convolution","method_name":"Convolution"},{"method_slug":"lstm","method_name":"LSTM"},{"method_slug":"speed","method_name":"SPEED"},{"method_slug":"sigmoid-activation","method_name":"Sigmoid Activation"},{"method_slug":"tanh-activation","method_name":"Tanh Activation"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/2d-human-pose-estimation-on-jhmdb-2d-poses","task":"2D Human Pose Estimation","dataset":"JHMDB (2D poses only)","model":"LSTM PM","rank_in_archive_order":5,"of":5,"metrics":{"PCK":"93.6"},"uses_additional_data":false},{"leaderboard":"/sota/pose-estimation-on-j-hmdb","task":"Pose Estimation","dataset":"J-HMDB","model":"LSTM PM","rank_in_archive_order":3,"of":5,"metrics":{"Mean PCK@0.2":"93.6"},"uses_additional_data":false},{"leaderboard":"/sota/pose-estimation-on-upenn-action","task":"Pose Estimation","dataset":"UPenn Action","model":"LSTM PM","rank_in_archive_order":3,"of":5,"metrics":{"Mean PCK@0.2":"97.7"},"uses_additional_data":false}],"syntology":{"syntology_url":"https://syntology.ai/paper/1712.06316","atlas_url":"https://app.syntology.ai/?focus=1712.06316","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":"1712.06316"},"arguments_in":{"paper_2":"another paper's arXiv id or title"},"call":"get_citation_path(paper_1=\"1712.06316\", paper_2=\"…\")"},{"tool":"get_concepts_for_paper","arguments":{"arxiv_id":"1712.06316"},"call":"get_concepts_for_paper(arxiv_id=\"1712.06316\")"}],"by_repo":[{"repo":"lawy623/LSTM_Pose_Machines","kind":"official","samples":0,"ran":0,"instrument":0,"unverified":0}],"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":"33d814785285a5e81df14faf351c1ea130629e88c66cd31593d1c665fd44dec5","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}