{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,2]],"date-time":"2026-06-02T18:27:11Z","timestamp":1780424831291,"version":"3.54.1"},"reference-count":54,"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\/501100010909","name":"Young Scientists Fund","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100010909","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["624B2110"],"award-info":[{"award-number":["624B2110"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100012166","name":"National Key Research and Development Program of China","doi-asserted-by":"publisher","award":["2024YFC3015600"],"award-info":[{"award-number":["2024YFC3015600"]}],"id":[{"id":"10.13039\/501100012166","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\/iccv51701.2025.01277","type":"proceedings-article","created":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T19:45:49Z","timestamp":1777491949000},"page":"13761-13771","source":"Crossref","is-referenced-by-count":1,"title":["SemTalk: Holistic Co-Speech Motion Generation with Frame-Level Semantic Emphasis"],"prefix":"10.1109","author":[{"given":"Xiangyue","family":"Zhang","sequence":"first","affiliation":[{"name":"Wuhan University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jianfang","family":"Li","sequence":"additional","affiliation":[{"name":"Tongyi Lab, Alibaba Group"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jiaxu","family":"Zhang","sequence":"additional","affiliation":[{"name":"Wuhan University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ziqiang","family":"Dang","sequence":"additional","affiliation":[{"name":"Tongyi Lab, Alibaba Group"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jianqiang","family":"Ren","sequence":"additional","affiliation":[{"name":"Tongyi Lab, Alibaba Group"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Liefeng","family":"Bo","sequence":"additional","affiliation":[{"name":"Tongyi Lab, Alibaba Group"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zhigang","family":"Tu","sequence":"additional","affiliation":[{"name":"Wuhan University"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52688.2022.01991"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1145\/3592458"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1145\/3592097"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2023.3288409"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1145\/192161.192272"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1075\/pc.7.1.03cas"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1145\/383259.383315"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1145\/3664647.3680847"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00702"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00190"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2009.2017438"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1145\/3610548.3618183"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01821"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1016\/S1364-6613(99)01397-2"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00912"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00186"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1145\/3472306.3478335"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3122291"},{"key":"ref19","first-page":"25","article-title":"Robot behavior toolkit: generating effective social behaviors for robots","volume-title":"Proceedings of the seventh annual ACM\/ IEEE international conference on Human-Robot Interaction","author":"Huang","year":"2012"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1017\/CBO9780511807572"},{"key":"ref21","article-title":"Gesture generation by imitation: From human behavior to computer character animation","author":"Kipp","year":"2005","journal-title":"UniversalPublishers"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1007\/11821830_17"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1145\/3382507.3418815"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1145\/3397481.3450692"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1093\/jos\/ffp004"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01110"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01315"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01022"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3548400"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20071-7_36"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00115"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52688.2022.01021"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00155"},{"key":"ref34","article-title":"Humantomato: Text-aligned whole-body motion generation","author":"Lu","year":"2023","journal-title":"arXiv preprint"},{"key":"ref35","article-title":"emotion2vec: Selfsupervised pre-training for speech emotion representation","author":"Ma","year":"2023","journal-title":"arXiv preprint"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1145\/2485895.2485900"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00101"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1162\/jocn.2007.19.4.605"},{"key":"ref39","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"International conference on machine learning","author":"Radford","year":"2021"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1145\/3411763.3451554"},{"issue":"4","key":"ref41","article-title":"Difftalk: Crafting diffusion models for generalized talking head synthesis","volume-title":"arXiv preprint","volume":"2","author":"Shen","year":"2023"},{"key":"ref42","article-title":"Neural discrete representation learning","author":"Van","year":"2017","journal-title":"Advances in neural information processing systems"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/GlobalSIP45357.2019.8969272"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01229"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i6.28458"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3612503"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2023\/650"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00053"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2019.8793720"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1145\/3414685.3417838"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3129994"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/TVCG.2025.3529611"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01902"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52729.2023.01016"}],"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\/11445149.pdf?arnumber=11445149","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T05:18:44Z","timestamp":1777612724000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11445149\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":54,"URL":"https:\/\/doi.org\/10.1109\/iccv51701.2025.01277","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}