{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,6]],"date-time":"2026-05-06T07:20:06Z","timestamp":1778052006257,"version":"3.51.4"},"reference-count":33,"publisher":"IEEE","license":[{"start":{"date-parts":[[2026,3,6]],"date-time":"2026-03-06T00:00:00Z","timestamp":1772755200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,3,6]],"date-time":"2026-03-06T00:00:00Z","timestamp":1772755200000},"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":[[2026,3,6]]},"DOI":"10.1109\/wacv61042.2026.00671","type":"proceedings-article","created":{"date-parts":[[2026,5,5]],"date-time":"2026-05-05T19:59:32Z","timestamp":1778011172000},"page":"6946-6955","source":"Crossref","is-referenced-by-count":0,"title":["SegMo: Segment-aligned Text to 3D Human Motion Generation"],"prefix":"10.1109","author":[{"given":"Bowen","family":"Dang","sequence":"first","affiliation":[{"name":"University of Sheffield"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Lin","family":"Wu","sequence":"additional","affiliation":[{"name":"University of Glasgow"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xiaohang","family":"Yang","sequence":"additional","affiliation":[{"name":"Queen Mary University of London"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zheng","family":"Yuan","sequence":"additional","affiliation":[{"name":"University of Sheffield"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhixiang","family":"Chen","sequence":"additional","affiliation":[{"name":"University of Sheffield"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01103"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01726"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51701.2025.01355"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/n19\u20131423"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73636-0_19"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1145\/3394171.3413635"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00509"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19833-5_34"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00186"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73397-0_11"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.52202\/075280-0681"},{"key":"ref12","article-title":"Auto-encoding variational bayes","author":"Kingma","year":"2013"},{"key":"ref13","article-title":"Lamp: Language-motion pretraining for motion generation, retrieval, and captioning","volume-title":"The Thirteenth International Conference on Learning Representations","author":"Li"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/TIT.1982.1056489"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00554"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.02594"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00153"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1089\/big.2016.0028"},{"key":"ref19","article-title":"Improving language understanding by generative pre-training","author":"Radford","year":"2018"},{"key":"ref20","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"International conference on machine learning","author":"Radford"},{"key":"ref21","article-title":"Text-driven motion generation: Overview, challenges and directions","author":"Sahili","year":"2025"},{"key":"ref22","article-title":"Human motion diffusion model","volume-title":"The Eleventh International Conference on Learning Representations","author":"Tevet"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20047-2_21"},{"key":"ref24","article-title":"Neural discrete representation learning","volume":"30","author":"Van Den Oord","year":"2017","journal-title":"Advances in neural information processing systems"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2025.3624601"},{"key":"ref26","article-title":"Qwen3 technical report","author":"Yang","year":"2025"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00095"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1111\/j.1467-8721.2007.00480.x"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3129994"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01415"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00040"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2024.3355414"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2023.3330935"}],"event":{"name":"2026 IEEE\/CVF Winter Conference on Applications of Computer Vision (WACV)","location":"Tucson, AZ, USA","start":{"date-parts":[[2026,3,6]]},"end":{"date-parts":[[2026,3,10]]}},"container-title":["2026 IEEE\/CVF Winter Conference on Applications of Computer Vision (WACV)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11491838\/11491925\/11492103.pdf?arnumber=11492103","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,6]],"date-time":"2026-05-06T06:35:30Z","timestamp":1778049330000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11492103\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,3,6]]},"references-count":33,"URL":"https:\/\/doi.org\/10.1109\/wacv61042.2026.00671","relation":{},"subject":[],"published":{"date-parts":[[2026,3,6]]}}}