{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,11]],"date-time":"2026-06-11T14:33:26Z","timestamp":1781188406539,"version":"3.54.1"},"reference-count":89,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"6","license":[{"start":{"date-parts":[[2023,6,1]],"date-time":"2023-06-01T00:00:00Z","timestamp":1685577600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2023,6,1]],"date-time":"2023-06-01T00:00:00Z","timestamp":1685577600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,6,1]],"date-time":"2023-06-01T00:00:00Z","timestamp":1685577600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"National Key R&D Program of China","award":["2017YFA0700800"],"award-info":[{"award-number":["2017YFA0700800"]}]},{"name":"Shanghai Municipal Science and Technology","award":["2021SHZDZX0102"],"award-info":[{"award-number":["2021SHZDZX0102"]}]},{"name":"Shanghai Qi Zhi Institute"},{"DOI":"10.13039\/501100008838","name":"Shanghai Municipal Commission of Economy and Informatization","doi-asserted-by":"publisher","award":["2018-RGZN-02046"],"award-info":[{"award-number":["2018-RGZN-02046"]}],"id":[{"id":"10.13039\/501100008838","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Pattern Anal. Mach. Intell."],"published-print":{"date-parts":[[2023,6,1]]},"DOI":"10.1109\/tpami.2022.3222784","type":"journal-article","created":{"date-parts":[[2022,11,17]],"date-time":"2022-11-17T20:37:10Z","timestamp":1668717430000},"page":"7157-7173","source":"Crossref","is-referenced-by-count":600,"title":["AlphaPose: Whole-Body Regional Multi-Person Pose Estimation and Tracking in Real-Time"],"prefix":"10.1109","volume":"45","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-0758-0293","authenticated-orcid":false,"given":"Hao-Shu","family":"Fang","sequence":"first","affiliation":[{"name":"Department of Electrical and Computer Engineering, Shanghai Jiao Tong University, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1932-8914","authenticated-orcid":false,"given":"Jiefeng","family":"Li","sequence":"additional","affiliation":[{"name":"Department of Electrical and Computer Engineering, Shanghai Jiao Tong University, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hongyang","family":"Tang","sequence":"additional","affiliation":[{"name":"Department of Electrical and Computer Engineering, Shanghai Jiao Tong University, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Chao","family":"Xu","sequence":"additional","affiliation":[{"name":"Department of Electrical and Computer Engineering, Shanghai Jiao Tong University, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1153-5230","authenticated-orcid":false,"given":"Haoyi","family":"Zhu","sequence":"additional","affiliation":[{"name":"Department of Electrical and Computer Engineering, Shanghai Jiao Tong University, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0165-5909","authenticated-orcid":false,"given":"Yuliang","family":"Xiu","sequence":"additional","affiliation":[{"name":"Perceiving Systems, Max Planck Institute for Intelligent Systems, Stuttgart, Germany"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0478-0692","authenticated-orcid":false,"given":"Yong-Lu","family":"Li","sequence":"additional","affiliation":[{"name":"Department of Electrical and Computer Engineering, Shanghai Jiao Tong University, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4023-9257","authenticated-orcid":false,"given":"Cewu","family":"Lu","sequence":"additional","affiliation":[{"name":"Department of Electrical and Computer Engineering, Shanghai Jiao Tong University, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46466-4_3"},{"key":"ref57","article-title":"FastPose: Towards real-time pose estimation and tracking via scale-normalized multi-task networks","author":"zhang","year":"2019"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.533"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00581"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.471"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1007\/s10994-020-05929-w"},{"key":"ref14","year":"2016"},{"key":"ref58","article-title":"On the properties of the softmax function with application in game theory and reinforcement learning","author":"gao","year":"2017"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00798"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2020.2980194"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7299020"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00475"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.458"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00677"},{"key":"ref17","article-title":"OpenPose: Realtime multi-person 2D pose estimation using part affinity fields","author":"cao","year":"2018"},{"key":"ref16","first-page":"1799","article-title":"Joint training of a convolutional network and a graphical model for human pose estimation","author":"tompson","year":"2014","journal-title":"Proc Conf Neural Inf Process Syst"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01112"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58545-7_12"},{"key":"ref51","first-page":"209","article-title":"Multi-domain pose network for multi-person pose estimation and tracking","author":"guo","year":"2018","journal-title":"Proc Eur Conf Comput Vis Workshops"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01110"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1016\/j.cag.2019.09.002"},{"key":"ref45","first-page":"536","article-title":"Integral human pose regression","author":"sun","year":"2018","journal-title":"Proc Eur Conf Comput Vis"},{"key":"ref89","first-page":"227","article-title":"A top-down approach to articulated human pose estimation and tracking","author":"ning","year":"2018","journal-title":"Proc Eur Conf Comput Vis"},{"key":"ref48","article-title":"LightTrack: A generic framework for online top-down human pose tracking","author":"ning","year":"2019"},{"key":"ref47","article-title":"Pose flow: Efficient online pose tracking","author":"xiu","year":"2018"},{"key":"ref42","first-page":"467","article-title":"LIFT: Learned invariant feature transform","author":"yi","year":"2016","journal-title":"Proc Eur Conf Comput Vis"},{"key":"ref86","article-title":"Adam: A method for stochastic optimization","author":"kingma","year":"2014"},{"key":"ref41","article-title":"Learning visual feature spaces for robotic manipulation with deep spatial autoencoders","author":"finn","year":"2015"},{"key":"ref85","article-title":"MOT16: A benchmark for multi-object tracking","author":"milan","year":"2016"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/WACV.2019.00162"},{"key":"ref88","doi-asserted-by":"publisher","DOI":"10.1109\/IJCNN.2019.8851734"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00539"},{"key":"ref87","article-title":"Joint flow: Temporal flow fields for multi person tracking","author":"doering","year":"2018"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00044"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.511"},{"key":"ref7","doi-asserted-by":"crossref","DOI":"10.1007\/978-3-319-46484-8_29","article-title":"Stacked hourglass networks for human pose estimation","author":"newell","year":"2016"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2012.6248052"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-15552-9_30"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW.2018.00308"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2013.459"},{"key":"ref5","first-page":"3394","article-title":"Conditional regression forests for human pose estimation","author":"sun","year":"2012","journal-title":"Proc IEEE Conf Comput Vis Pattern Recognit"},{"key":"ref82","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00634"},{"key":"ref81","article-title":"YOLOX: Exceeding YOLO series in 2021","author":"ge","year":"2021"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/WACV.2018.00048"},{"key":"ref84","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.23"},{"key":"ref83","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.593"},{"key":"ref80","article-title":"MXNet: A flexible and efficient machine learning library for heterogeneous distributed systems","author":"chen","year":"2015"},{"key":"ref35","article-title":"Objects as points","author":"xingyi","year":"2019"},{"key":"ref79","first-page":"8026","article-title":"PyTorch: An imperative style, high-performance deep learning library","author":"paszke","year":"2019","journal-title":"Proc Int Conf Neural Inf Process"},{"key":"ref34","first-page":"3021","article-title":"Learning temporal pose estimation from sparsely-labeled videos","author":"bertasius","year":"2019","journal-title":"Proc Int Conf Neural Inf Process"},{"key":"ref78","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.89"},{"key":"ref37","article-title":"DirectPose: Direct end-to-end multi-person pose estimation","author":"tian","year":"2019"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00705"},{"key":"ref31","first-page":"466","article-title":"Simple baselines for human pose estimation and tracking","author":"xiao","year":"2018","journal-title":"Proc Eur Conf Comput Vis"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01079"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00742"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2013.191"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00689"},{"key":"ref77","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.207"},{"key":"ref32","first-page":"91","article-title":"Faster R-CNN: Towards real-time object detection with region proposal networks","author":"ren","year":"2015","journal-title":"Proc Int Conf Neural Inf Process"},{"key":"ref76","doi-asserted-by":"publisher","DOI":"10.1109\/WACV.2018.00163"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1016\/j.cviu.2006.08.002"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/FG.2018.00126"},{"key":"ref39","first-page":"6982","article-title":"Single-network whole-body pose estimation","author":"hidalgo","year":"2019","journal-title":"Proc IEEE\/CVF Int Conf Comput Vis"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58607-2_31"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1016\/j.imavis.2018.12.001"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2018.2879980"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW.2011.6130513"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00227"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00542"},{"key":"ref23","doi-asserted-by":"crossref","first-page":"13498","DOI":"10.1109\/TITS.2021.3124981","article-title":"OpenPifPaf: Composite fields for semantic keypoint detection and spatio-temporal association","volume":"23","author":"sven","year":"2022","journal-title":"IEEE Trans Intell Transp Syst"},{"key":"ref67","article-title":"Towards real-time multi-object tracking","author":"wang","year":"2019"},{"key":"ref26","first-page":"2274","article-title":"Associative embedding: End-to-end learning for joint detection and grouping","author":"newell","year":"2017","journal-title":"Proc Int Conf Neural Inf Process"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.143"},{"key":"ref69","first-page":"7482","article-title":"Multi-task learning using uncertainty to weigh losses for scene geometry and semantics","author":"kendall","year":"2018","journal-title":"Proc IEEE Conf Comput Vis Pattern Recognit"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.256"},{"key":"ref64","article-title":"YOLOv3: An incremental improvement","author":"redmon","year":"2018"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58565-5_33"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01225"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.5244\/C.27.58"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-48881-3_44"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.395"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00584"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00543"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.322"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01084"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00090"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1016\/j.imavis.2016.01.002"}],"container-title":["IEEE Transactions on Pattern Analysis and Machine Intelligence"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/34\/10120646\/09954214.pdf?arnumber=9954214","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,4,4]],"date-time":"2025-04-04T19:26:32Z","timestamp":1743794792000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9954214\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,6,1]]},"references-count":89,"journal-issue":{"issue":"6"},"URL":"https:\/\/doi.org\/10.1109\/tpami.2022.3222784","relation":{},"ISSN":["0162-8828","2160-9292","1939-3539"],"issn-type":[{"value":"0162-8828","type":"print"},{"value":"2160-9292","type":"electronic"},{"value":"1939-3539","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,6,1]]}}}