{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,4]],"date-time":"2026-05-04T03:28:44Z","timestamp":1777865324564,"version":"3.51.4"},"reference-count":55,"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"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62320106007,62032022"],"award-info":[{"award-number":["62320106007,62032022"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,10,19]]},"DOI":"10.1109\/iccv51701.2025.01201","type":"proceedings-article","created":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T19:45:49Z","timestamp":1777491949000},"page":"12926-12936","source":"Crossref","is-referenced-by-count":0,"title":["Text-to-Any-Skeleton Motion Generation Without Retargeting"],"prefix":"10.1109","author":[{"given":"Qingyuan","family":"Liu","sequence":"first","affiliation":[{"name":"University of Chinese Academy of Sciences"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ke","family":"Lu","sequence":"additional","affiliation":[{"name":"University of Chinese Academy of Sciences"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Kun","family":"Dong","sequence":"additional","affiliation":[{"name":"University of Chinese Academy of Sciences"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jian","family":"Xue","sequence":"additional","affiliation":[{"name":"University of Chinese Academy of Sciences"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zehai","family":"Niu","sequence":"additional","affiliation":[{"name":"University of Chinese Academy of Sciences"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jinbao","family":"Wang","sequence":"additional","affiliation":[{"name":"Shenzhen University"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1145\/3386569.3392462"},{"key":"ref2","article-title":"Mixamo","volume-title":"Online Animation Library","year":"2023"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2018.8460608"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/3DV.2019.00084"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1145\/3267851.3267867"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/3DV57658.2022.00053"},{"key":"ref7","article-title":"Explicitly minimizing the blur error of variational autoencoders","author":"Bredell","year":"2023","journal-title":"arXiv preprint"},{"key":"ref8","article-title":"How attentive are graph attention networks?","volume-title":"International Conference on Learning Representations","author":"Brody"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01216-8_23"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01726"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1002\/1099-1778(200012)11:5<223::AID-VIS236>3.0.CO;2-5"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/TVCG.2024.3352002"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00143"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1145\/280814.280820"},{"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":"10.1007\/978-3-031-19833-5_34"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00186"},{"key":"ref19","article-title":"Motiongpt: Human motion as a foreign language","author":"Jiang","year":"2023","journal-title":"arXiv preprint"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00159"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i7.25996"},{"key":"ref22","first-page":"792","article-title":"Learning spatiotemporal structure from rgb-d videos for human activity detection and anticipation","volume-title":"International conference on machine learning","author":"Koppula"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1145\/311535.311539"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1145\/3610548.3618206"},{"key":"ref25","article-title":"PMnet: learning of disentangled pose and movement for unsupervised motion retargeting","author":"Lim","year":"2019","journal-title":"Proc. BMVC"},{"key":"ref26","article-title":"Generating animated videos of human activities from natural language descriptions","volume":"1","author":"Lin","year":"2018","journal-title":"Learning"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02224"},{"key":"ref28","first-page":"32939","article-title":"Humantomato: Text-aligned whole-body motion generation","volume-title":"International Conference on Machine Learning","author":"Lu"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00554"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1145\/1821748.1821760"},{"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":"10.1109\/ICCV51070.2023.00870"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72633-0_10"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00153"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1016\/j.robot.2018.07.006"},{"key":"ref37","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"International Conference on Machine Learning","author":"Radford"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1145\/3641519.3657422"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1145\/1037957.1037963"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20047-2_21"},{"key":"ref41","article-title":"Human motion diffusion model","author":"Tevet","year":"2022","journal-title":"arXiv preprint"},{"key":"ref42","article-title":"Neural discrete representation learning","volume":"30","author":"Van Den Oord","year":"2017","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.14711\/thesis-991012757468803412"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00901"},{"key":"ref45","article-title":"T2m-hifigpt: generating high quality human motion from textual descriptions with residual discrete representations","author":"Wang","year":"2023","journal-title":"arXiv preprint"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i07.6911"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2004.827514"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00210"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01332"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52729.2023.01415"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/tpami.2024.3355414"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00040"},{"key":"ref53","article-title":"Motiongpt: Finetuned 11 ms are general-purpose motion generators","author":"Zhang","year":"2023","journal-title":"arXiv preprint"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00053"},{"key":"ref55","article-title":"Parco: Partcoordinating text-to-motion synthesis","volume-title":"arXiv preprint","author":"Zou","year":"2024"}],"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\/11445560.pdf?arnumber=11445560","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,30]],"date-time":"2026-04-30T06:15:05Z","timestamp":1777529705000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11445560\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":55,"URL":"https:\/\/doi.org\/10.1109\/iccv51701.2025.01201","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}