{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,1]],"date-time":"2026-07-01T21:11:26Z","timestamp":1782940286913,"version":"3.54.5"},"reference-count":63,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"7","license":[{"start":{"date-parts":[[2026,7,1]],"date-time":"2026-07-01T00:00:00Z","timestamp":1782864000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2026,7,1]],"date-time":"2026-07-01T00:00:00Z","timestamp":1782864000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,7,1]],"date-time":"2026-07-01T00:00:00Z","timestamp":1782864000000},"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":["72572090"],"award-info":[{"award-number":["72572090"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62436010"],"award-info":[{"award-number":["62436010"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62172421"],"award-info":[{"award-number":["62172421"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62441617"],"award-info":[{"award-number":["62441617"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62572474"],"award-info":[{"award-number":["62572474"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100004826","name":"Beijing Natural Science Foundation","doi-asserted-by":"publisher","award":["4254100"],"award-info":[{"award-number":["4254100"]}],"id":[{"id":"10.13039\/501100004826","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100002858","name":"China Postdoctoral Science Foundation","doi-asserted-by":"publisher","award":["2024M764093"],"award-info":[{"award-number":["2024M764093"]}],"id":[{"id":"10.13039\/501100002858","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Visual. Comput. Graphics"],"published-print":{"date-parts":[[2026,7]]},"DOI":"10.1109\/tvcg.2026.3679469","type":"journal-article","created":{"date-parts":[[2026,4,1]],"date-time":"2026-04-01T20:12:20Z","timestamp":1775074340000},"page":"6305-6318","source":"Crossref","is-referenced-by-count":2,"title":["ExGes: Expressive Human Motion Retrieval and Modulation for Audio-Driven Gesture Synthesis"],"prefix":"10.1109","volume":"32","author":[{"ORCID":"https:\/\/orcid.org\/0009-0005-5478-1791","authenticated-orcid":false,"given":"Xukun","family":"Zhou","sequence":"first","affiliation":[{"name":"School of Digital Technology and Innovation Design, Jiangnan University, Wuxi, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8828-2767","authenticated-orcid":false,"given":"Fengxin","family":"Li","sequence":"additional","affiliation":[{"name":"School of Information, Renmin University of China, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ming","family":"Chen","sequence":"additional","affiliation":[{"name":"Kuaishou Technology, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0002-0564-0915","authenticated-orcid":false,"given":"Yan","family":"Zhou","sequence":"additional","affiliation":[{"name":"Kuaishou Technology, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7225-565X","authenticated-orcid":false,"given":"Pengfei","family":"Wan","sequence":"additional","affiliation":[{"name":"Kuaishou Technology, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7818-9534","authenticated-orcid":false,"given":"Yeying","family":"Jin","sequence":"additional","affiliation":[{"name":"National University of Singapore, Singapore"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4274-7332","authenticated-orcid":false,"given":"Hongyuan","family":"Zhang","sequence":"additional","affiliation":[{"name":"TeleAI (Institute of Artificial Intelligence), China Telecom, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4902-1078","authenticated-orcid":false,"given":"Hongyan","family":"Liu","sequence":"additional","affiliation":[{"name":"School of Economics and Management, Tsinghua University, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6324-1712","authenticated-orcid":false,"given":"Zhaoxin","family":"Fan","sequence":"additional","affiliation":[{"name":"Beijing Advanced Innovation Center for Future Blockchain and Privacy Computing, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1511-7554","authenticated-orcid":false,"given":"Jun","family":"He","sequence":"additional","affiliation":[{"name":"School of Information, Renmin University of China, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xuelong","family":"Li","sequence":"additional","affiliation":[{"name":"National University of Singapore, Singapore"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1145\/3592458"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1145\/3550454.3555435"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1145\/3592097"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW.2018.00191"},{"key":"ref5","first-page":"413","article-title":"Rule-based generation of facial expression, gesture & spoken intonation for multiple conversational agents","volume-title":"Proc. 21st Annu. Conf. Compu. Graph. Interactive Techn.","author":"Cassell"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1145\/383259.383315"},{"key":"ref7","article-title":"Text-to-motion synthesis using discrete diffusion model","volume-title":"Proc. 34th Brit. Mach. Vis. Conf.","author":"Chemburkar","year":"2023"},{"key":"ref8","first-page":"6774","article-title":"Enabling synergistic full-body control in prompt-based co-speech motion generation","volume-title":"Proc. ACM Int. Conf. Multimedia","author":"Chen"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00702"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1145\/3450626.3459932"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1145\/3680528.3687677"},{"key":"ref12","doi-asserted-by":"crossref","DOI":"10.1109\/CVPR52733.2024.00190","article-title":"Emotional speech-driven 3D body animation via disentangled latent diffusion","author":"Chhatre","year":"2024"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.52202\/068431-1862"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1145\/3641519.3657414"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1002\/cav.2016"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00071"},{"key":"ref17","article-title":"ZeroEGGS: Zero-shot example-based gesture generation from speech","author":"Ghorbani","year":"2022"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00361"},{"key":"ref19","article-title":"Mamba: Linear-time sequence modeling with selective state spaces","author":"Gu","year":"2023"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1145\/3472306.3478335"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1145\/3528233.3530750"},{"key":"ref22","article-title":"An efficient framework for reliable and personalized motion planner in autonomous driving","author":"Jiang","year":"2022","journal-title":"IEEE Robot. Automat. Lett."},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.2139\/ssrn.4092912"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00205"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01360"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01110"},{"key":"ref27","first-page":"9694","article-title":"Align before fuse: Vision and language representation learning with momentum distillation","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Li"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00151"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01315"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1007\/s10514-023-10131-7"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3548400"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20071-7_36"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52733.2024.00115"},{"key":"ref34","doi-asserted-by":"crossref","DOI":"10.1109\/CVPR52688.2022.01106","article-title":"Reduce information loss in transformers for pluralistic image inpainting","author":"Liu","year":"2022"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/TVCG.2024.3397868"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01021"},{"key":"ref37","doi-asserted-by":"crossref","DOI":"10.1109\/CVPR52688.2022.01117","article-title":"RePaint: Inpainting using denoising diffusion probabilistic models","author":"Lugmayr","year":"2022"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1016\/j.cag.2021.09.014"},{"key":"ref39","doi-asserted-by":"crossref","DOI":"10.1109\/CVPR52734.2025.01545","article-title":"Retrieving semantics from the deep: An RAG solution for gesture synthesis","author":"Mughal","year":"2025"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00138"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00101"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1111\/cgf.14776"},{"key":"ref43","article-title":"Co3Gesture: Towards coherent concurrent co-speech 3D gesture generation with interactive diffusion","author":"Qi","year":"2025"},{"key":"ref44","article-title":"Learning transferable visual models from natural language supervision","author":"Radford","year":"2021"},{"key":"ref45","article-title":"Robust speech recognition via large-scale weak supervision","author":"Radford","year":"2022"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/TVCG.2024.3363457"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1145\/3458380.3458428"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/TVCG.2023.3320216"},{"key":"ref50","first-page":"6309","article-title":"Neural discrete representation learning","volume-title":"Proc. Adv. Neural Inf. Process. Systems","author":"Van Den"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.52202\/079017-0633"},{"key":"ref52","doi-asserted-by":"crossref","DOI":"10.24963\/ijcai.2023\/650","article-title":"DiffuseStyleGesture: Stylized audio-driven co-speech gesture generation with diffusion models","author":"Yang","year":"2023"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00230"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00053"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1145\/3414685.3417838"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/TVCG.2025.3529611"},{"key":"ref57","doi-asserted-by":"crossref","DOI":"10.1109\/ICCV51701.2025.01277","article-title":"SemTalk: Holistic co-speech motion generation with frame-level semantic emphasis","author":"Zhang","year":"2025"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/TVCG.2025.3568880"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1145\/3658134"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01902"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00053"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73232-4_23"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01016"}],"container-title":["IEEE Transactions on Visualization and Computer Graphics"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/2945\/11575570\/11460242.pdf?arnumber=11460242","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,6,25]],"date-time":"2026-06-25T19:44:36Z","timestamp":1782416676000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11460242\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,7]]},"references-count":63,"journal-issue":{"issue":"7"},"URL":"https:\/\/doi.org\/10.1109\/tvcg.2026.3679469","relation":{},"ISSN":["1077-2626","1941-0506","2160-9306"],"issn-type":[{"value":"1077-2626","type":"print"},{"value":"1941-0506","type":"electronic"},{"value":"2160-9306","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,7]]}}}