{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,11]],"date-time":"2026-07-11T18:18:52Z","timestamp":1783793932315,"version":"3.55.0"},"reference-count":46,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"12","license":[{"start":{"date-parts":[[2024,12,1]],"date-time":"2024-12-01T00:00:00Z","timestamp":1733011200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2024,12,1]],"date-time":"2024-12-01T00:00:00Z","timestamp":1733011200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,12,1]],"date-time":"2024-12-01T00:00:00Z","timestamp":1733011200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"National Key Research and Development Program of China","award":["2018AAA0102500"],"award-info":[{"award-number":["2018AAA0102500"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Visual. Comput. Graphics"],"published-print":{"date-parts":[[2024,12]]},"DOI":"10.1109\/tvcg.2024.3352002","type":"journal-article","created":{"date-parts":[[2024,1,15]],"date-time":"2024-01-15T21:09:11Z","timestamp":1705352951000},"page":"7518-7530","source":"Crossref","is-referenced-by-count":28,"title":["GUESS: GradUally Enriching SyntheSis for Text-Driven Human Motion Generation"],"prefix":"10.1109","volume":"30","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-3168-5770","authenticated-orcid":false,"given":"Xuehao","family":"Gao","sequence":"first","affiliation":[{"name":"Xi’an Jiaotong University, Xi’an, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8687-4427","authenticated-orcid":false,"given":"Yang","family":"Yang","sequence":"additional","affiliation":[{"name":"Xi’an Jiaotong University, Xi’an, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9207-1014","authenticated-orcid":false,"given":"Zhenyu","family":"Xie","sequence":"additional","affiliation":[{"name":"School of Intelligent Systems Engineering, Sun Yat-sen University, Guangzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7092-0596","authenticated-orcid":false,"given":"Shaoyi","family":"Du","sequence":"additional","affiliation":[{"name":"Xi’an Jiaotong University, Xi’an, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1812-6085","authenticated-orcid":false,"given":"Zhongqian","family":"Sun","sequence":"additional","affiliation":[{"name":"Tencent AI Lab., Shenzhen, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8010-6857","authenticated-orcid":false,"given":"Yang","family":"Wu","sequence":"additional","affiliation":[{"name":"Tencent AI Lab., Shenzhen, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/3DV.2019.00084"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TVCG.2022.3163676"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/VR50410.2021.00037"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TVCG.2018.2831233"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1016\/j.cub.2018.05.016"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19790-1_22"},{"key":"ref7","first-page":"64","article-title":"","author":"Chang","year":"2023"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01726"},{"key":"ref9","article-title":"Mocap dataset","year":"2015"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00941"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.3758\/s13421-017-0716-1"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/TVCG.2011.73"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00143"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00509"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19833-5_34"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1145\/3394171.3413635"},{"key":"ref17","article-title":"Imagen video: High definition video generation with diffusion models","author":"Ho","year":"2022"},{"key":"ref18","first-page":"47:1","article-title":"Cascaded diffusion models for high fidelity image generation","volume":"23","author":"Ho","year":"2022","journal-title":"J. Mach. Learn. Res."},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/tvcg.2023.3284402"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1145\/3240508.3240675"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/TVCG.2008.22"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.4135\/9781446251409.n4"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i2.20014"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01315"},{"key":"ref25","first-page":"32","article-title":"Generating animated videos of human activities from natural language descriptions","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Lin"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00554"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ICAR.2015.7251476"},{"key":"ref28","article-title":"Official pre-trained clip models","year":"2021"},{"key":"ref29","article-title":"Chatgpt introduction","year":"2023"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1038\/s41583-019-0202-9"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01080"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20047-2_28"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1089\/big.2016.0028"},{"key":"ref34","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Radford"},{"key":"ref35","first-page":"1","article-title":"Hierarchical text-conditional image generation with clip latents","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Ramesh"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"ref37","article-title":"Photorealistic text-to-image diffusion models with deep language understanding","author":"Saharia","year":"2022"},{"key":"ref38","first-page":"2256","article-title":"Deep unsupervised learning using nonequilibrium thermodynamics","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Sohl-Dickstein"},{"key":"ref39","first-page":"12438","article-title":"Improved techniques for training score-based generative models","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Song"},{"key":"ref40","first-page":"1","article-title":"Human motion diffusion model","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Tevet"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00165"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/TVCG.2019.2938520"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1002\/9781118818565.ch2"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/iccv51070.2023.01467"},{"key":"ref45","first-page":"14730","article-title":"T2M-GPT: Generating human motion from textual descriptions with discrete representations","volume-title":"Proc. IEEE\/CVF Conf. Comput. Vis. Pattern Recognit.","author":"Zhang"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/tpami.2024.3355414\/mm1"}],"container-title":["IEEE Transactions on Visualization and Computer Graphics"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/2945\/10737249\/10399852.pdf?arnumber=10399852","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,11,26]],"date-time":"2024-11-26T22:48:08Z","timestamp":1732661288000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10399852\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,12]]},"references-count":46,"journal-issue":{"issue":"12"},"URL":"https:\/\/doi.org\/10.1109\/tvcg.2024.3352002","relation":{},"ISSN":["1077-2626","1941-0506","2160-9306"],"issn-type":[{"value":"1077-2626","type":"print"},{"value":"1941-0506","type":"electronic"},{"value":"2160-9306","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,12]]}}}