{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,17]],"date-time":"2026-07-17T08:06:46Z","timestamp":1784275606406,"version":"3.55.0"},"reference-count":85,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"6","license":[{"start":{"date-parts":[[2024,6,1]],"date-time":"2024-06-01T00:00:00Z","timestamp":1717200000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2024,6,1]],"date-time":"2024-06-01T00:00:00Z","timestamp":1717200000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,6,1]],"date-time":"2024-06-01T00:00:00Z","timestamp":1717200000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Pattern Anal. Mach. Intell."],"published-print":{"date-parts":[[2024,6]]},"DOI":"10.1109\/tpami.2024.3355414","type":"journal-article","created":{"date-parts":[[2024,1,29]],"date-time":"2024-01-29T18:40:10Z","timestamp":1706553610000},"page":"4115-4128","source":"Crossref","is-referenced-by-count":298,"title":["MotionDiffuse: Text-Driven Human Motion Generation With Diffusion Model"],"prefix":"10.1109","volume":"46","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-8212-715X","authenticated-orcid":false,"given":"Mingyuan","family":"Zhang","sequence":"first","affiliation":[{"name":"S-Lab, Nanyang Technological University, Singapore"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1810-3855","authenticated-orcid":false,"given":"Zhongang","family":"Cai","sequence":"additional","affiliation":[{"name":"S-Lab, Nanyang Technological University, Singapore"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1821-4296","authenticated-orcid":false,"given":"Liang","family":"Pan","sequence":"additional","affiliation":[{"name":"S-Lab, Nanyang Technological University, Singapore"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2412-1141","authenticated-orcid":false,"given":"Fangzhou","family":"Hong","sequence":"additional","affiliation":[{"name":"S-Lab, Nanyang Technological University, Singapore"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0005-3635-4278","authenticated-orcid":false,"given":"Xinying","family":"Guo","sequence":"additional","affiliation":[{"name":"S-Lab, Nanyang Technological University, Singapore"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0571-5924","authenticated-orcid":false,"given":"Lei","family":"Yang","sequence":"additional","affiliation":[{"name":"SenseTime Research and Shanghai AI Laboratory, Shenzhen, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4220-5958","authenticated-orcid":false,"given":"Ziwei","family":"Liu","sequence":"additional","affiliation":[{"name":"S-Lab, Nanyang Technological University, Singapore"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1145\/3394171.3413635"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01080"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19790-1_22"},{"key":"ref4","article-title":"Dance revolution: Long-term dance generation with music via curriculum learning","author":"Huang","year":"2020"},{"key":"ref5","article-title":"Learning to generate diverse dance motions with transformer","author":"Li","year":"2020"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01315"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1145\/3485664"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01077"},{"key":"ref9","article-title":"Generating animated videos of human activities from natural language descriptions","volume-title":"Proc. Visually Grounded Interaction Lang. Workshop Neural Inf. Process. Syst. Workshop","author":"Lin"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/3DV.2019.00084"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00143"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20047-2_28"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1089\/big.2016.0028"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20047-2_21"},{"key":"ref15","article-title":"Diffusion models beat GANs on image synthesis","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Dhariwal"},{"key":"ref16","first-page":"8162","article-title":"Improved denoising diffusion probabilistic models","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Nichol"},{"key":"ref17","first-page":"16 784","article-title":"GLIDE: Towards photorealistic image generation and editing with text-guided diffusion models","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Nichol"},{"key":"ref18","article-title":"Hierarchical text-conditional image generation with clip latents","author":"Ramesh","year":"2022"},{"key":"ref19","first-page":"6840","article-title":"Denoising diffusion probabilistic models","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Ho"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/38.708559"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1145\/1477926.1477927"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1145\/1186822.1073313"},{"key":"ref23","first-page":"405","article-title":"Extraction of motion data by interactive processing","volume-title":"Proc. IEEE Conf. Pattern Recognit. Image Process.","author":"Futrelle"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1006\/cviu.1998.0716"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.1980.6447699"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1016\/j.imavis.2005.09.004"},{"issue":"6","key":"ref27","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1145\/2366145.2366172","article-title":"Motion graphs a compact generative model for semantic motion analysis and synthesis","volume":"31","author":"Min","year":"2012","journal-title":"ACM Trans. Graph."},{"key":"ref28","article-title":"Auto-encoding variational Bayes","author":"Kingma","year":"2013"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01228-1_17"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00527"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1145\/3528223.3530094"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.5555\/2969033.2969125"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW.2018.00191"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1145\/3386569.3392480"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i07.6911"},{"key":"ref37","article-title":"Nice: Non-linear independent components estimation","author":"Dinh","year":"2014"},{"key":"ref38","article-title":"Density estimation using real NVP","author":"Dinh","year":"2016"},{"key":"ref39","first-page":"10236","article-title":"Glow: Generative flow with invertible 1x1 convolutions","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Kingma"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1145\/3414685.3417836"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1997.9.8.1735"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58452-8_24"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00583"},{"key":"ref44","article-title":"Human motion diffusion model","volume-title":"Proc. 11th Int. Conf. Learn. Representations","author":"Tevet"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i7.25996"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.4135\/9781446251409.n4"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2020.2981989"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00509"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2013.396"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00542"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2013.248"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.381"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/3DV.2017.00064"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.5244\/C.31.14"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00306"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01326"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58452-8_23"},{"key":"ref58","article-title":"Playing for 3D human recovery","author":"Cai","year":"2021"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20071-7_33"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2011.6126543"},{"key":"ref61","article-title":"UCF101: A dataset of 101 human actions classes from videos in the wild","author":"Soomro","year":"2012"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.223"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00633"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00269"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01321"},{"key":"ref66","article-title":"A short note on the kinetics-700 human action dataset","author":"Carreira","year":"2019"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2019.2901464"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00876"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2019.2916873"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1145\/3240508.3240675"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1038\/s41597-020-00635-7"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00078"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00554"},{"key":"ref74","first-page":"12 104","article-title":"Training generative adversarial networks with limited data","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Karras"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.1145\/3446374"},{"key":"ref76","article-title":"Gaussian error linear units (GELUs)","author":"Hendrycks","year":"2016"},{"key":"ref77","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Radford"},{"key":"ref78","first-page":"3531","article-title":"Efficient attention: Attention with linear complexities","volume-title":"Proc. IEEE\/CVF winter Conf. Appl. Comput. Vis.","author":"Shen"},{"key":"ref79","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00589"},{"key":"ref80","doi-asserted-by":"publisher","DOI":"10.1109\/VR50410.2021.00037"},{"key":"ref81","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00165"},{"key":"ref82","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58568-6_21"},{"key":"ref83","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00530"},{"key":"ref84","doi-asserted-by":"publisher","DOI":"10.1145\/2816795.2818013"},{"key":"ref85","doi-asserted-by":"publisher","DOI":"10.1109\/3DV57658.2022.00053"}],"container-title":["IEEE Transactions on Pattern Analysis and Machine Intelligence"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/34\/10522060\/10416192.pdf?arnumber=10416192","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,5,8]],"date-time":"2024-05-08T04:43:24Z","timestamp":1715143404000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10416192\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,6]]},"references-count":85,"journal-issue":{"issue":"6"},"URL":"https:\/\/doi.org\/10.1109\/tpami.2024.3355414","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":[[2024,6]]}}}