{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,7]],"date-time":"2026-04-07T21:10:15Z","timestamp":1775596215460,"version":"3.50.1"},"reference-count":59,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"4","license":[{"start":{"date-parts":[[2026,4,1]],"date-time":"2026-04-01T00:00:00Z","timestamp":1775001600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2026,4,1]],"date-time":"2026-04-01T00:00:00Z","timestamp":1775001600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,4,1]],"date-time":"2026-04-01T00:00:00Z","timestamp":1775001600000},"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":["62172452"],"award-info":[{"award-number":["62172452"]}],"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":["62176223"],"award-info":[{"award-number":["62176223"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Project of Department of Education of Guangdong Province","award":["2025KTSCX111"],"award-info":[{"award-number":["2025KTSCX111"]}]},{"DOI":"10.13039\/501100001321","name":"Guangdong Basic and Applied Basic Research Foundation","doi-asserted-by":"publisher","award":["2023A1515011639"],"award-info":[{"award-number":["2023A1515011639"]}],"id":[{"id":"10.13039\/501100001321","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001321","name":"Guangdong Basic and Applied Basic Research Foundation","doi-asserted-by":"publisher","award":["2024A1515030025"],"award-info":[{"award-number":["2024A1515030025"]}],"id":[{"id":"10.13039\/501100001321","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":[[2026,4]]},"DOI":"10.1109\/tcsvt.2025.3628996","type":"journal-article","created":{"date-parts":[[2025,11,4]],"date-time":"2025-11-04T18:37:59Z","timestamp":1762281479000},"page":"5424-5436","source":"Crossref","is-referenced-by-count":0,"title":["Expressive Human Volumetric Video Generation With Rich Text"],"prefix":"10.1109","volume":"36","author":[{"ORCID":"https:\/\/orcid.org\/0009-0009-4106-4581","authenticated-orcid":false,"given":"Yi","family":"Yang","sequence":"first","affiliation":[{"name":"School of Artificial Intelligence, Sun Yat-sen University, Zhuhai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6761-8767","authenticated-orcid":false,"given":"Guanghui","family":"Yue","sequence":"additional","affiliation":[{"name":"School of Biomedical Engineering, Shenzhen University, Shenzhen, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3641-1429","authenticated-orcid":false,"given":"Wei","family":"Zhou","sequence":"additional","affiliation":[{"name":"School of Computer Science and Informatics, Cardiff University, Cardiff, U.K."}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xudong","family":"Mao","sequence":"additional","affiliation":[{"name":"School of Artificial Intelligence, Sun Yat-sen University, Zhuhai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2712-4412","authenticated-orcid":false,"given":"Ruomei","family":"Wang","sequence":"additional","affiliation":[{"name":"School of Software Engineering, Sun Yat-sen University, Zhuhai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0574-1663","authenticated-orcid":false,"given":"Baoquan","family":"Zhao","sequence":"additional","affiliation":[{"name":"School of Artificial Intelligence, Sun Yat-sen University, Zhuhai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2011.2105595"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2009.2022708"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2014.2372291"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2016.2556587"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2019.2958199"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1016\/B978-0-32-391755-1.00007-9"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2018.2874179"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2014.2334011"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2020.2966118"},{"key":"ref10","volume-title":"Blender\u2014A 3D Modeling and Rendering Software","author":"Foundation","year":"2024"},{"key":"ref11","volume-title":"Unreal Engine","author":"Games","year":"2024"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1145\/2816795.2818013"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1089\/big.2016.0028"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00509"},{"key":"ref15","first-page":"25268","article-title":"Motion-X: A large-scale 3D expressive whole-body human motion dataset","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Lin"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01726"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00040"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00186"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00153"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/D14-1162"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1810.04805"},{"key":"ref22","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"Proc. Int. Conf. Mach. Learn.","volume":"139","author":"Radford"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1145\/3610543.3626176"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/JIOT.2025.3535812"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1049\/iet-cvi.2019.0786"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1145\/3592433"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1145\/3503250"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2020.2985911"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/ICCPHOT.2011.5753118"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2024.3421359"},{"key":"ref31","first-page":"10516","article-title":"DreamHuman: Animatable 3D avatars from text","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Kolotouros"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00145"},{"key":"ref33","article-title":"PocoLoco: A point cloud diffusion model of human shape in loose clothing","author":"Seth","year":"2024","journal-title":"arXiv:2411.04249"},{"key":"ref34","article-title":"3DGS.Zip: A survey on 3D Gaussian splatting compression methods","author":"Bagdasarian","year":"2024","journal-title":"arXiv:2407.09510"},{"key":"ref35","article-title":"Fine feature reconstruction in point clouds by adversarial domain translation","author":"Raina","year":"2020","journal-title":"Proc. Graph. Interface"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20047-2_21"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2020.3034233"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2023.3261659"},{"key":"ref39","first-page":"6840","article-title":"Denoising diffusion probabilistic models","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Ho"},{"key":"ref40","first-page":"36479","article-title":"Photorealistic text-to-image diffusion models with deep language understanding","volume-title":"Proc. NIPS","volume":"35","author":"Saharia"},{"key":"ref41","article-title":"VideoGen: A reference-guided latent diffusion approach for high definition text-to-video generation","author":"Li","year":"2023","journal-title":"arXiv:2309.00398"},{"key":"ref42","article-title":"Human motion diffusion model","author":"Tevet","year":"2022","journal-title":"arXiv:2209.14916"},{"key":"ref43","first-page":"6309","article-title":"Neural discrete representation learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Vinyals"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-024-02271-9"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1145\/3394486.3403172"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3547911"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00694"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.52202\/079017-0202"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v39i7.32729"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1145\/3313761"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-20678-3_22"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.3108\/beej.2003.02000004"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00355"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1145\/3522618"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.494"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73232-4_23"},{"key":"ref57","first-page":"1181","article-title":"OmniControl: Control any joint at any time for human motion generation","volume-title":"Proc. ICLR","author":"Xie"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.emnlp-main.595"},{"key":"ref59","first-page":"4061","article-title":"Decoupled weight decay regularization","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Loshchilov"}],"container-title":["IEEE Transactions on Circuits and Systems for Video Technology"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/76\/11475579\/11224870.pdf?arnumber=11224870","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,7]],"date-time":"2026-04-07T20:03:13Z","timestamp":1775592193000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11224870\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,4]]},"references-count":59,"journal-issue":{"issue":"4"},"URL":"https:\/\/doi.org\/10.1109\/tcsvt.2025.3628996","relation":{},"ISSN":["1051-8215","1558-2205"],"issn-type":[{"value":"1051-8215","type":"print"},{"value":"1558-2205","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,4]]}}}