{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,6]],"date-time":"2026-05-06T06:18:25Z","timestamp":1778048305536,"version":"3.51.4"},"reference-count":63,"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"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100004608","name":"Natural Science Foundation of Jiangsu Province","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100004608","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2026,3,6]]},"DOI":"10.1109\/wacv61042.2026.00663","type":"proceedings-article","created":{"date-parts":[[2026,5,5]],"date-time":"2026-05-05T19:59:32Z","timestamp":1778011172000},"page":"6862-6872","source":"Crossref","is-referenced-by-count":0,"title":["ATM: Enhanced Alignment for Text-to-Motion Generation"],"prefix":"10.1109","author":[{"given":"Ke","family":"Han","sequence":"first","affiliation":[{"name":"University of Trento"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yueming","family":"Lyu","sequence":"additional","affiliation":[{"name":"Nanjing University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Weichen","family":"Yu","sequence":"additional","affiliation":[{"name":"Carnegie Mellon University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Nicu","family":"Sebe","sequence":"additional","affiliation":[{"name":"University of Trento"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01726"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72630-9_2"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.01636"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72640-8_22"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.18653\/vl\/N19-142"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73242-3_6"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1145\/3394171.3413635"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00509"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00186"},{"key":"ref10","first-page":"22066","article-title":"Clothing-change feature augmentation for person re-identification","volume-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","author":"Han"},{"key":"ref11","article-title":"In defense of the triplet loss for person re-identification","author":"Hermans","year":"2017"},{"key":"ref12","first-page":"6840","article-title":"Denoising diffusion probabilistic models","volume":"33","author":"Ho","year":"2020","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.00671"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73397-0_11"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.52202\/075280-0880"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72698-9_23"},{"key":"ref17","article-title":"Act as you wish: Fine-grained control of motion diffusion model with hierarchical semantic graphs","volume":"36","author":"Jin","year":"2024","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.02119"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00053"},{"key":"ref20","first-page":"722","article-title":"Spatio-temporal graph diffusion for text-driven human motion generation","volume-title":"British Machine Vision Conference","author":"Liu"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00139"},{"key":"ref22","article-title":"Plan, posture and go: Towards open-world text-to-motion generation","author":"Liu","year":"2023"},{"key":"ref23","article-title":"Humantomato: Text-aligned whole-body motion generation","volume-title":"International Conference on Machine Learning","author":"Lu"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00554"},{"key":"ref25","article-title":"Language models are few-shot learners","author":"Mann","year":"2020","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.02594"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.52202\/068431-2011"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20047-2_28"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00870"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72633-0_10"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00153"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1089\/big.2016.0028"},{"key":"ref33","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"International conference on machine learning","author":"Radford"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D19-1410"},{"key":"ref35","doi-asserted-by":"crossref","DOI":"10.1007\/978-3-031-72661-3_20","article-title":"Realistic human motion generation with cross-diffusion models","volume-title":"European Conference on Computer Vision","author":"Ren"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298682"},{"key":"ref38","article-title":"Human motion diffusion as a generative prior","volume-title":"International Conference on Learning Representations","author":"Shafir"},{"key":"ref39","article-title":"Denoising diffusion implicit models","volume-title":"International Conference on Learning Representations","author":"Song"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2021.3137005"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20047-2_21"},{"key":"ref42","article-title":"Human motion diffusion model","volume-title":"International Conference on Learning Representations","author":"Tevet"},{"key":"ref43","article-title":"Llama: Open and efficient foundation language models","author":"Touvron","year":"2023"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW67362.2025.00274"},{"key":"ref45","article-title":"Neural discrete representation learning","volume":"30","author":"Oord","year":"2017","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.02014"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00049"},{"key":"ref48","article-title":"Nerm: Learning neural representations for high-framerate human motion synthesis","volume-title":"International Conference on Learning Representations","author":"Wei"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2022.3184415"},{"key":"ref50","article-title":"Omnicontrol: Control any joint at any time for human motion generation","volume-title":"International Conference on Learning Representations","author":"Xie"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1145\/3595916.3626459"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52733.2024.00158"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2025.3556868"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v39i9.33062"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52729.2023.01415"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/tpami.2024.3355414\/mm2"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00040"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72624-8_23"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73232-4_15"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2020.2972125"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72627-9_2"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00135"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72992-8_8"}],"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\/11492039.pdf?arnumber=11492039","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,6]],"date-time":"2026-05-06T05:53:56Z","timestamp":1778046836000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11492039\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,3,6]]},"references-count":63,"URL":"https:\/\/doi.org\/10.1109\/wacv61042.2026.00663","relation":{},"subject":[],"published":{"date-parts":[[2026,3,6]]}}}