{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,6]],"date-time":"2026-05-06T06:19:20Z","timestamp":1778048360385,"version":"3.51.4"},"reference-count":50,"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\/wacv61042.2026.00609","type":"proceedings-article","created":{"date-parts":[[2026,5,5]],"date-time":"2026-05-05T19:59:32Z","timestamp":1778011172000},"page":"6298-6308","source":"Crossref","is-referenced-by-count":0,"title":["MoSCo: Real-time and Efficient Text-to-Motion Synthesis via Delta Training"],"prefix":"10.1109","author":[{"given":"Zhiyuan","family":"Zhang","sequence":"first","affiliation":[{"name":"The University of Adelaide"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Lingqiao","family":"Liu","sequence":"additional","affiliation":[{"name":"The University of Adelaide"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2018.8460608"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/3DV.2019.00084"},{"key":"ref3","article-title":"Towards principled methods for training generative adversarial networks","author":"Arjovsky","year":"2017"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2023.3288409"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01216-8_23"},{"key":"ref6","article-title":"Pay attention and move better: Harnessing attention for interactive motion generation and training-free editing","author":"Chen","year":"2024"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01726"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72640-8_22"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00143"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1145\/3394171.3413635"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00509"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19833-5_34"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00186"},{"key":"ref14","article-title":"Semanticboost: Elevating motion generation with augmented textual cues","author":"He","year":"2023"},{"key":"ref15","article-title":"Bipo: Bidirectional partial occlusion network for text-to-motion synthesis","author":"Hong","year":"2024"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49660.2025.10889942"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73397-0_11"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1145\/3664647.3681657"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.52202\/075280-0880"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICME55011.2023.00014"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i7.25996"},{"key":"ref22","article-title":"Human motion modeling using dvgans","author":"Lin","year":"2018"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00554"},{"key":"ref24","article-title":"Stacked quantizers for compositional vector compression","author":"Martinez","year":"2014"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.497"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52734.2025.02594"},{"key":"ref27","article-title":"Quaternet: A quaternion-based recurrent model for human motion","author":"Pavllo","year":"2018"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20047-2_28"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW63382.2024.00197"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72633-0_10"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1089\/big.2016.0028"},{"key":"ref32","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"International conference on machine learning","author":"Radford"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/3DV53792.2021.00069"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20047-2_21"},{"key":"ref35","article-title":"Human motion diffusion model","author":"Tevet","year":"2022"},{"key":"ref36","first-page":"30","article-title":"Neural discrete representation learning","author":"Van Den Oord","year":"2017","journal-title":"Advances in neural information processing systems"},{"key":"ref37","article-title":"Attention is all you need","author":"Vaswani","year":"2017","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.02593"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00125"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/iros60139.2025.11247385"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.52202\/079017-4155"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3129994"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01415"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00040"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.52202\/075280-0616"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2024.3355414"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73232-4_15"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00053"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2023.3330935"},{"key":"ref50","first-page":"126","article-title":"Parco: Part-coordinating text-to-motion synthesis","volume-title":"European Conference on Computer Vision","author":"Zou"}],"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\/11492083.pdf?arnumber=11492083","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,6]],"date-time":"2026-05-06T05:54:08Z","timestamp":1778046848000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11492083\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,3,6]]},"references-count":50,"URL":"https:\/\/doi.org\/10.1109\/wacv61042.2026.00609","relation":{},"subject":[],"published":{"date-parts":[[2026,3,6]]}}}