{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,2]],"date-time":"2026-06-02T09:26:59Z","timestamp":1780392419352,"version":"3.54.1"},"reference-count":82,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,10,19]],"date-time":"2025-10-19T00:00:00Z","timestamp":1760832000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,10,19]],"date-time":"2025-10-19T00:00:00Z","timestamp":1760832000000},"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":[],"published-print":{"date-parts":[[2025,10,19]]},"DOI":"10.1109\/iccv51701.2025.01094","type":"proceedings-article","created":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T19:45:49Z","timestamp":1777491949000},"page":"11766-11776","source":"Crossref","is-referenced-by-count":1,"title":["GENMO: A GENeralist Model for Human MOtion"],"prefix":"10.1109","author":[{"given":"Jiefeng","family":"Li","sequence":"first","affiliation":[{"name":"NVIDIA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jinkun","family":"Cao","sequence":"additional","affiliation":[{"name":"NVIDIA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Haotian","family":"Zhang","sequence":"additional","affiliation":[{"name":"NVIDIA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Davis","family":"Rempe","sequence":"additional","affiliation":[{"name":"NVIDIA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jan","family":"Kautz","sequence":"additional","affiliation":[{"name":"NVIDIA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Umar","family":"Iqbal","sequence":"additional","affiliation":[{"name":"NVIDIA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ye","family":"Yuan","sequence":"additional","affiliation":[{"name":"NVIDIA"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1145\/3592458"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/3DV57658.2022.00053"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW.2018.00191"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v39i2.32183"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00843"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46454-1_34"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19790-1_22"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01726"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00200"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/FG52635.2021.9667071"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1145\/3641519.3657414"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72640-8_22"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00143"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01358"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1145\/3394171.3413635"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00509"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00509"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19833-5_34"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00186"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.5244\/C.31.119"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01118"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.52202\/068431-0307"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1145\/3414685.3417836"},{"key":"ref24","first-page":"6840","article-title":"Denoising diffusion probabilistic models","volume":"33","author":"Ho","year":"2020","journal-title":"Advances in neural information processing systems"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01292"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2013.248"},{"key":"ref27","article-title":"Act as you wish: Fine-grained control of motion diffusion model with hierarchical semantic graphs","volume-title":"NeurIPs","author":"Jin","year":"2023"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00744"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01345"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00530"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/3DV62453.2024.00103"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01360"},{"key":"ref33","article-title":"NIFTY: Neural object interaction fields for guided human motion synthesis","author":"Kulkarni","year":"2023","journal-title":"arXiv:2307.07511"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00110"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00339"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01243"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72640-8_24"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01315"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20065-6_34"},{"key":"ref40","article-title":"Motion-x: A largescale 3d expressive whole-body human motion dataset","volume-title":"NeurIPS","author":"Lin","year":"2023"},{"key":"ref41","article-title":"Gcdance: Genre-controlled 3d full body dance generation driven by music","author":"Liu","year":"2025","journal-title":"arXiv preprint"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1145\/2816795.2818013"},{"key":"ref43","article-title":"M3 gpt: An advanced multimodal, multitask framework for motion comprehension and generation","volume-title":"NeurIPs","author":"Luo","year":"2024"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00554"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW63382.2024.00197"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00153"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1145\/3625264"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00219"},{"key":"ref49","article-title":"Guibas","author":"Rempe","year":"2021","journal-title":"Humor: 3d human motion model for robust pose estimation. In ICCV"},{"key":"ref50","author":"S\u00e1r\u00e1ndi","year":"2024","journal-title":"Neural localizer fields for continuous 3d human pose and shape e stimation"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1145\/3680528.3687565"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00202"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1145\/3458380.3458428"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01077"},{"key":"ref55","article-title":"Denoising diffusion implicit models","volume-title":"International Conference on Learning Representations","author":"Song","year":"2020"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2023.127063"},{"key":"ref57","article-title":"You never stop dancing: Nonfreezing dance generation via bank-constrained manifold projection","volume-title":"NeurIPS","author":"Sun","year":"2022"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00855"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1145\/3240508.3240526"},{"key":"ref60","article-title":"Human motion diffusion model","volume-title":"ICLR","author":"Tevet","year":"2023"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00051"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1145\/3478513.3480570"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01249-6_37"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01346"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73247-8_27"},{"key":"ref66","article-title":"HUMANISE: Language-conditioned human motion generation in 3d scenes","author":"Wang","year":"2022","journal-title":"Neural Information Processing Systems (NeurIPS)"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00212"},{"key":"ref68","author":"Xu","year":"2024","journal-title":"Motionbank: A large-scale video motion benchmark with disentangled rule-based annotations"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02033"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73235-5_14"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1145\/3450626.3459786"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01076"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1109\/tpami.2024.3355414"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00040"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72624-8_23"},{"key":"ref76","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00982"},{"key":"ref77","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01384"},{"key":"ref78","doi-asserted-by":"publisher","DOI":"10.1109\/3dv66043.2025.00139"},{"key":"ref79","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72627-9_2"},{"key":"ref80","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00545"},{"key":"ref81","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01016"},{"key":"ref82","doi-asserted-by":"publisher","DOI":"10.1109\/tpami.2023.3330935"}],"event":{"name":"2025 IEEE\/CVF International Conference on Computer Vision (ICCV)","location":"Honolulu, HI, USA","start":{"date-parts":[[2025,10,19]]},"end":{"date-parts":[[2025,10,25]]}},"container-title":["2025 IEEE\/CVF International Conference on Computer Vision (ICCV)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11443115\/11443287\/11444630.pdf?arnumber=11444630","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T05:06:47Z","timestamp":1777612007000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11444630\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":82,"URL":"https:\/\/doi.org\/10.1109\/iccv51701.2025.01094","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}