{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,21]],"date-time":"2026-05-21T16:17:46Z","timestamp":1779380266668,"version":"3.53.1"},"reference-count":55,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"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":["62171251"],"award-info":[{"award-number":["62171251"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Special Foundations for the Development of Strategic Emerging Industries of Shenzhen","award":["JCYJ20200109143035495"],"award-info":[{"award-number":["JCYJ20200109143035495"]}]},{"name":"Special Foundations for the Development of Strategic Emerging Industries of Shenzhen","award":["CJGJZD20210408092804011"],"award-info":[{"award-number":["CJGJZD20210408092804011"]}]},{"name":"Special Foundations for the Development of Strategic Emerging Industries of Shenzhen","award":["JSGG20211108092812020"],"award-info":[{"award-number":["JSGG20211108092812020"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Multimedia"],"published-print":{"date-parts":[[2024]]},"DOI":"10.1109\/tmm.2023.3321438","type":"journal-article","created":{"date-parts":[[2023,10,2]],"date-time":"2023-10-02T18:00:45Z","timestamp":1696269645000},"page":"4039-4049","source":"Crossref","is-referenced-by-count":26,"title":["Global and Local Spatio-Temporal Encoder for 3D Human Pose Estimation"],"prefix":"10.1109","volume":"26","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-7847-3807","authenticated-orcid":false,"given":"Yong","family":"Wang","sequence":"first","affiliation":[{"name":"School of Artificial Intelligence, Chongqing University of Technology, Chongqing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5771-3886","authenticated-orcid":false,"given":"Hongbo","family":"Kang","sequence":"additional","affiliation":[{"name":"School of Artificial Intelligence, Chongqing University of Technology, Chongqing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5189-8565","authenticated-orcid":false,"given":"Doudou","family":"Wu","sequence":"additional","affiliation":[{"name":"School of Artificial Intelligence, Chongqing University of Technology, Chongqing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2506-1286","authenticated-orcid":false,"given":"Wenming","family":"Yang","sequence":"additional","affiliation":[{"name":"Shenzhen International Graduate School, Department of Electronic Engineering, Tsinghua University, Shenzhen, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8785-5885","authenticated-orcid":false,"given":"Longbin","family":"Zhang","sequence":"additional","affiliation":[{"name":"School of Mechanical and Aerospace Engineering, Rehabilitation Research Institute of Singapore, Nanyang Technological University, Singapore"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00742"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00584"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2020.2979190"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2022.3186746"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2019.2891244"},{"key":"ref6","volume-title":"Human-Computer Interaction","author":"Preece","year":"1994"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2017.02.030"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00127"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2018.2818329"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1145\/3072959.3073596"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.288"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00794"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2022.3171102"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01145"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2022.3141231"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20065-6_27"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1145\/3530811"},{"key":"ref19","first-page":"4271","article-title":"Funnel-transformer: Filtering out sequential redundancy for efficient language processing","volume-title":"Proc. Annu. Conf. Neural Inf. Process. Syst.","author":"Dai","year":"2020"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2022.3152247"},{"key":"ref21","article-title":"An image is worth 16x16 words: Transformers for image recognition at scale","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Dosovitskiy","year":"2021"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58452-8_13"},{"key":"ref23","article-title":"BEiT: BERT pre-training of image transformers","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Bao","year":"2022"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.139"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01231-1_33"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00354"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2019.2894422"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00797"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01012"},{"key":"ref30","article-title":"GraphMLP: A graph MLP-like architecture for 3D human pose estimation","author":"Li","year":"2022"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00236"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00081"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58601-0_45"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01249-6_5"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2021.3057267"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00511"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1145\/3474085.3475219"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00060"},{"key":"ref39","article-title":"Do we really need explicit position encodings for vision transformers","volume-title":"Proc. 11th Int. Conf. Learn. Representations","author":"Chu","year":"2023"},{"key":"ref40","first-page":"15908","article-title":"Transformer in transformer","volume-title":"Proc. Annu. Conf. Neural Inf. Process. Syst.","author":"Han","year":"2021"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00061"},{"key":"ref42","first-page":"10347","article-title":"Training data-efficient image transformers & distillation through attention","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Touvron","year":"2021"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01288"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01280"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.2139\/ssrn.4213439"},{"key":"ref46","article-title":"Layer normalization","author":"Ba","year":"2016"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2013.248"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/3DV.2017.00064"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00098"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58568-6_30"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01124"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.5555\/3454287.3455008"},{"key":"ref53","article-title":"Adam: A method for stochastic optimization","volume-title":"Proc. 3rd Int. Conf. Learn. Representations","author":"Kingma","year":"2015"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1145\/3474085.3475504"},{"key":"ref55","article-title":"Trajectory space factorization for deep video-based 3D human pose estimation","volume-title":"BMVC","author":"Lin","year":"2019"}],"container-title":["IEEE Transactions on Multimedia"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6046\/10384483\/10269070.pdf?arnumber=10269070","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,3,2]],"date-time":"2024-03-02T07:34:07Z","timestamp":1709364847000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10269070\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024]]},"references-count":55,"URL":"https:\/\/doi.org\/10.1109\/tmm.2023.3321438","relation":{},"ISSN":["1520-9210","1941-0077"],"issn-type":[{"value":"1520-9210","type":"print"},{"value":"1941-0077","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024]]}}}