{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,8]],"date-time":"2026-07-08T16:59:25Z","timestamp":1783529965149,"version":"3.55.0"},"reference-count":52,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"9","license":[{"start":{"date-parts":[[2023,9,1]],"date-time":"2023-09-01T00:00:00Z","timestamp":1693526400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2023,9,1]],"date-time":"2023-09-01T00:00:00Z","timestamp":1693526400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,9,1]],"date-time":"2023-09-01T00:00:00Z","timestamp":1693526400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62076117"],"award-info":[{"award-number":["62076117"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62166026"],"award-info":[{"award-number":["62166026"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Jiangxi Key Laboratory of Smart City","award":["20192BCD40002"],"award-info":[{"award-number":["20192BCD40002"]}]},{"DOI":"10.13039\/501100004479","name":"Jiangxi Provincial Natural Science Foundation","doi-asserted-by":"publisher","award":["20224BAB212011"],"award-info":[{"award-number":["20224BAB212011"]}],"id":[{"id":"10.13039\/501100004479","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Circuits Syst. Video Technol."],"published-print":{"date-parts":[[2023,9]]},"DOI":"10.1109\/tcsvt.2023.3269666","type":"journal-article","created":{"date-parts":[[2023,4,24]],"date-time":"2023-04-24T18:41:43Z","timestamp":1682361703000},"page":"4564-4576","source":"Crossref","is-referenced-by-count":29,"title":["Spatiotemporal Learning Transformer for Video-Based Human Pose Estimation"],"prefix":"10.1109","volume":"33","author":[{"ORCID":"https:\/\/orcid.org\/0009-0001-2699-6200","authenticated-orcid":false,"given":"Di","family":"Gai","sequence":"first","affiliation":[{"name":"School of Mathematics and Computer Sciences, the Jiangxi Key Laboratory of Smart City, and the Institute of Metaverse, Nanchang University, Nanchang, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4912-6646","authenticated-orcid":false,"given":"Runyang","family":"Feng","sequence":"additional","affiliation":[{"name":"School of Artificial Intelligence, Jilin University, Changchun, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2526-2181","authenticated-orcid":false,"given":"Weidong","family":"Min","sequence":"additional","affiliation":[{"name":"School of Mathematics and Computer Sciences, the Jiangxi Key Laboratory of Smart City, and the Institute of Metaverse, Nanchang University, Nanchang, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3815-0584","authenticated-orcid":false,"given":"Xiaosong","family":"Yang","sequence":"additional","affiliation":[{"name":"National Centre for Computer Animation, Bournemouth University, Poole, U.K."}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Pengxiang","family":"Su","sequence":"additional","affiliation":[{"name":"School of Software, Nanchang University, Nanchang, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Qi","family":"Wang","sequence":"additional","affiliation":[{"name":"School of Mathematics and Computer Sciences, the Jiangxi Key Laboratory of Smart City, and the Institute of Metaverse, Nanchang University, Nanchang, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1294-9470","authenticated-orcid":false,"given":"Qing","family":"Han","sequence":"additional","affiliation":[{"name":"School of Mathematics and Computer Sciences, the Jiangxi Key Laboratory of Smart City, and the Institute of Metaverse, Nanchang University, Nanchang, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01264-9_17"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00742"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01110"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00059"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58520-4_36"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.511"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.143"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00546"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW53098.2021.00378"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2013.391"},{"key":"ref18","first-page":"1","article-title":"An image is worth 16×16 words: Transformers for image recognition at scale","author":"dosovitskiy","year":"2021","journal-title":"Proc 9th Int Conf Learn Represent (ICLR)"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00704"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.590"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2020.2980194"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.256"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298734"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2011.6126552"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1002\/int.22817"},{"key":"ref41","first-page":"3021","article-title":"Learning temporal pose estimation from sparsely-labeled videos","author":"bertasius","year":"2019","journal-title":"Proc Adv Neural Inf Process Syst Annu Conf Neural Inf Process Syst (NeurIPS)"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00475"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1145\/3519305"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/FG.2017.61"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2013.83"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-15552-9_30"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.214"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01073"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2022.3188716"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/UR49135.2020.9144771"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01305"},{"key":"ref40","first-page":"209","article-title":"Multi-domain pose network for multi-person pose estimation and tracking","volume":"11130","author":"guo","year":"2018","journal-title":"Proc Eur Conf Comput Vis (ECCV) Workshops"},{"key":"ref35","first-page":"53","article-title":"Pose flow: Efficient online pose tracking","author":"xiu","year":"2018","journal-title":"Proc Brit Mach Vis Conf"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00044"},{"key":"ref37","article-title":"FastPose: Towards real-time pose estimation and tracking via scale-normalized multi-task networks","author":"zhang","year":"2019","journal-title":"arXiv 1908 05593"},{"key":"ref36","article-title":"Joint flow: Temporal flow fields for multi person tracking","author":"doering","year":"2018","journal-title":"arXiv 1805 04596"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.495"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01151"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00542"},{"key":"ref2","first-page":"2752","article-title":"Multi-task deep learning for real-time 3D human pose estimation and action recognition","volume":"43","author":"luvizon","year":"2021","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2017.2771306"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00581"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/IJCNN.2019.8851734"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58529-7_29"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00543"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00798"},{"key":"ref25","first-page":"472","article-title":"Simple baselines for human pose estimation and tracking","volume":"11210","author":"xiao","year":"2018","journal-title":"Proc 15th Eur Conf"},{"key":"ref20","first-page":"483","article-title":"Stacked hourglass networks for human pose estimation","author":"xu","year":"2021","journal-title":"Proc IEEE\/CVF Conf Comput Vis Pattern Recognit (CVPR)"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00584"},{"key":"ref21","article-title":"Human pose estimation with spatial contextual information","author":"zhang","year":"2019","journal-title":"arXiv 1901 01760"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01079"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01159"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2022.3141231"}],"container-title":["IEEE Transactions on Circuits and Systems for Video Technology"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/76\/10241245\/10107432.pdf?arnumber=10107432","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,10,2]],"date-time":"2023-10-02T18:09:40Z","timestamp":1696270180000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10107432\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,9]]},"references-count":52,"journal-issue":{"issue":"9"},"URL":"https:\/\/doi.org\/10.1109\/tcsvt.2023.3269666","relation":{},"ISSN":["1051-8215","1558-2205"],"issn-type":[{"value":"1051-8215","type":"print"},{"value":"1558-2205","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,9]]}}}