{"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/openpifpaf-composite-fields-for-semantic","title":"OpenPifPaf: Composite Fields for Semantic Keypoint Detection and Spatio-Temporal Association","arxiv_id":"2103.02440","date":"2021-03-03","proceeding":null,"authors":["Sven Kreiss","Lorenzo Bertoni","Alexandre Alahi"],"abstract":"Many image-based perception tasks can be formulated as detecting, associating and tracking semantic keypoints, e.g., human body pose estimation and tracking. In this work, we present a general framework that jointly detects and forms spatio-temporal keypoint associations in a single stage, making this the first real-time pose detection and tracking algorithm. We present a generic neural network architecture that uses Composite Fields to detect and construct a spatio-temporal pose which is a single, connected graph whose nodes are the semantic keypoints (e.g., a person's body joints) in multiple frames. For the temporal associations, we introduce the Temporal Composite Association Field (TCAF) which requires an extended network architecture and training method beyond previous Composite Fields. Our experiments show competitive accuracy while being an order of magnitude faster on multiple publicly available datasets such as COCO, CrowdPose and the PoseTrack 2017 and 2018 datasets. We also show that our method generalizes to any class of semantic keypoints such as car and animal parts to provide a holistic perception framework that is well suited for urban mobility such as self-driving cars and delivery robots.","url_abs":"https://arxiv.org/abs/2103.02440v2","url_pdf":"https://arxiv.org/pdf/2103.02440v2.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":"openpifpaf-composite-fields-for-semantic","repo_url":"https://github.com/vita-epfl/openpifpaf","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"openpifpaf-composite-fields-for-semantic","repo_url":"https://github.com/vita-epfl/openpifpaf_posetrack","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"openpifpaf-composite-fields-for-semantic","repo_url":"https://github.com/openpifpaf/openpifpaf","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"openpifpaf-composite-fields-for-semantic","repo_url":"https://github.com/openpifpaf/openpifpaf_posetrack","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"openpifpaf-composite-fields-for-semantic","repo_url":"https://github.com/openpifpaf/openpifpafwebdemo","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":null},{"paper_slug":"openpifpaf-composite-fields-for-semantic","repo_url":"https://github.com/yasutomo57jp/openpifpaf_ros","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":null}],"tasks":[{"task_slug":"car-pose-estimation","task_name":"Car Pose Estimation"},{"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":"self-driving-cars","task_name":"Self-Driving Cars"}],"methods":[{"method_slug":"composite-fields","method_name":"Composite Fields"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/car-pose-estimation-on-apollocar3d","task":"Car Pose Estimation","dataset":"ApolloCar3D","model":"OpenPifPaf","rank_in_archive_order":2,"of":3,"metrics":{"Detection Rate":"86.1"},"uses_additional_data":false},{"leaderboard":"/sota/keypoint-detection-on-coco-test-dev","task":"Keypoint Detection","dataset":"COCO test-dev","model":"OpenPifPaf","rank_in_archive_order":8,"of":16,"metrics":{"AP":"70.9","APL":"76.8","APM":"67.1"},"uses_additional_data":false},{"leaderboard":"/sota/multi-person-pose-estimation-on-coco","task":"Multi-Person Pose Estimation","dataset":"COCO (Common Objects in Context)","model":"OpenPifPaf","rank_in_archive_order":7,"of":15,"metrics":{"AP":"0.709","Test AP":"70.9","Validation AP":"71.0"},"uses_additional_data":false},{"leaderboard":"/sota/pose-estimation-on-crowdpose","task":"Pose Estimation","dataset":"CrowdPose","model":"OpenPifPaf","rank_in_archive_order":7,"of":12,"metrics":{"AP":"70.5","AP Easy":"78.4","AP Hard":"63.8","AP Medium":"72.1","AP50":"89.1","AP75":"76.1"},"uses_additional_data":false}],"syntology":{"syntology_url":"https://syntology.ai/paper/2103.02440","atlas_url":"https://app.syntology.ai/?focus=2103.02440","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":"2103.02440"},"arguments_in":{"paper_2":"another paper's arXiv id or title"},"call":"get_citation_path(paper_1=\"2103.02440\", paper_2=\"…\")"},{"tool":"get_concepts_for_paper","arguments":{"arxiv_id":"2103.02440"},"call":"get_concepts_for_paper(arxiv_id=\"2103.02440\")"}],"by_repo":[{"repo":"vita-epfl/openpifpaf","kind":"official","samples":0,"ran":0,"instrument":0,"unverified":0,"harvested_for_other_papers":1,"harvested_for":["2105.06152"],"harvested_for_calls":[{"arxiv_id":"2105.06152","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"2105.06152"},"call":"get_harvested_code_for_paper(arxiv_id=\"2105.06152\")"}]},{"repo":"vita-epfl/openpifpaf_posetrack","kind":"official","samples":0,"ran":0,"instrument":0,"unverified":0},{"repo":"openpifpaf/openpifpaf","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0},{"repo":"openpifpaf/openpifpaf_posetrack","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0},{"repo":"openpifpaf/openpifpafwebdemo","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0},{"repo":"yasutomo57jp/openpifpaf_ros","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":"fb6dc75a238e82e1580fa4e43ef95d4a20edf3152dafc440d59523a6919ba17a","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}