{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,14]],"date-time":"2026-07-14T12:28:31Z","timestamp":1784032111848,"version":"3.55.0"},"reference-count":62,"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\/iccv51701.2025.01117","type":"proceedings-article","created":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T19:45:49Z","timestamp":1777491949000},"page":"12012-12022","source":"Crossref","is-referenced-by-count":3,"title":["You Think, You ACT: the New Task of Arbitrary Text to Motion Generation"],"prefix":"10.1109","author":[{"given":"Runqi","family":"Wang","sequence":"first","affiliation":[{"name":"Wuhan University,National Engineering Research Center for Multimedia Software"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Caoyuan","family":"Ma","sequence":"additional","affiliation":[{"name":"Wuhan University,National Engineering Research Center for Multimedia Software"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Guopeng","family":"Li","sequence":"additional","affiliation":[{"name":"StepFun"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hanrui","family":"Xu","sequence":"additional","affiliation":[{"name":"School of Computer Science, Wuhan University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yuke","family":"Li","sequence":"additional","affiliation":[{"name":"University of Maryland College Park"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zheng","family":"Wang","sequence":"additional","affiliation":[{"name":"Wuhan University,National Engineering Research Center for Multimedia Software"}],"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\/CVPR52729.2023.01726"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/WACV51458.2022.00281"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01880"},{"key":"ref6","article-title":"Singleshot motion completion with transformer","author":"Duan","year":"2021","journal-title":"arXiv preprint arXiv"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72764-1_24"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1145\/3394171.3413635"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00509"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19833-5_34"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00186"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1145\/3386569.3392480"},{"key":"ref13","article-title":"LoRA: Low-rank adaptation of large language models","volume-title":"International Conference on Learning Representations","author":"Hu"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1145\/3726302.3730108"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1145\/3240508.3240675"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00171"},{"key":"ref17","article-title":"Act as you wish: Fine-grained control of motion diffusion model with hierarchical semantic graphs","author":"Jin","year":"2024","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00205"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01360"},{"key":"ref20","article-title":"Dancing to music","author":"Lee","year":"2019","journal-title":"Advances in neural information processing systems"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i2.20014"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.02719"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01934"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01315"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00053"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-024-02042-6"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/tpami.2019.2916873"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73383-3_26"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3548287"},{"key":"ref30","article-title":"Humantomato: Text-aligned whole-body motion generation","author":"Lu","year":"2023","journal-title":"arXiv preprint arXiv"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20068-7_24"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i5.28206"},{"key":"ref33","article-title":"Follow-your-motion: Video motion transfer via efficient spatial-temporal decoupled finetuning","author":"Ma","year":"2025","journal-title":"arXiv preprint arXiv"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00554"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/iccv48922.2021.01080"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20047-2_28"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01383"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1089\/big.2016.0028"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00078"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01129"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.115"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.52202\/068431-0726"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01466"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20047-2_21"},{"key":"ref45","article-title":"Human motion diffusion model","author":"Tevet","year":"2022","journal-title":"arXiv preprint arXiv"},{"key":"ref46","article-title":"Expressiveness is effectiveness: selfsupervised fashion-aware clip for video-to-shop retrieval","volume-title":"Proceedings of the Thirty-Third International Joint Conference on Artificial Intelligence","author":"Tian"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.00376"},{"key":"ref48","article-title":"Neural discrete representation learning","author":"Van Den Oord","year":"2017","journal-title":"Advances in neural information processing systems"},{"key":"ref49","article-title":"Leader and follower: Interactive motion generation under trajectory constraints","author":"Wang","year":"2025","journal-title":"arXiv preprint arXiv"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.02014"},{"key":"ref51","article-title":"Intercontrol: Generate human motion interactions by controlling every joint","author":"Wang","year":"2023","journal-title":"arXiv preprint arXiv"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00049"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3611797"},{"key":"ref54","article-title":"Inter-x: Towards versatile humanhuman interaction analysis","author":"Xu","year":"2024","journal-title":"CVPR"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01371"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58577-8_2"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01415"},{"key":"ref58","article-title":"Motiondiffuse: Text-driven human motion generation with diffusion model","author":"Zhang","year":"2022","journal-title":"arXiv preprint arXiv"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i7.28567"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1145\/3746027.3755031"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00053"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00135"}],"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\/11443517.pdf?arnumber=11443517","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,30]],"date-time":"2026-04-30T06:10:33Z","timestamp":1777529433000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11443517\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":62,"URL":"https:\/\/doi.org\/10.1109\/iccv51701.2025.01117","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}