{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T17:13:53Z","timestamp":1777655633011,"version":"3.51.4"},"reference-count":61,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"ARC-Discovery","award":["DP220100800"],"award-info":[{"award-number":["DP220100800"]}]},{"name":"ARC-DECRA","award":["DE230100477"],"award-info":[{"award-number":["DE230100477"]}]},{"name":"National Key R&D Program of China","award":["2022YFF09022303"],"award-info":[{"award-number":["2022YFF09022303"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Multimedia"],"published-print":{"date-parts":[[2024]]},"DOI":"10.1109\/tmm.2024.3407692","type":"journal-article","created":{"date-parts":[[2024,5,31]],"date-time":"2024-05-31T17:37:34Z","timestamp":1717177054000},"page":"10420-10430","source":"Crossref","is-referenced-by-count":28,"title":["EmotionGesture: Audio-Driven Diverse Emotional Co-Speech 3D Gesture Generation"],"prefix":"10.1109","volume":"26","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-9772-5707","authenticated-orcid":false,"given":"Xingqun","family":"Qi","sequence":"first","affiliation":[{"name":"Academy of Interdisciplinary Studies, The Hong Kong University of Science and Technology, Hong Kong"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3159-0034","authenticated-orcid":false,"given":"Chen","family":"Liu","sequence":"additional","affiliation":[{"name":"School of Electrical Engineering and Computer Science, The University of Queensland, St Lucia, QLD, Australia"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6047-0472","authenticated-orcid":false,"given":"Lincheng","family":"Li","sequence":"additional","affiliation":[{"name":"NetEase Fuxi AI Lab, Hangzhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jie","family":"Hou","sequence":"additional","affiliation":[{"name":"NetEase Fuxi AI Lab, Hangzhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Haoran","family":"Xin","sequence":"additional","affiliation":[{"name":"NetEase Fuxi AI Lab, Hangzhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0269-5649","authenticated-orcid":false,"given":"Xin","family":"Yu","sequence":"additional","affiliation":[{"name":"School of Electrical Engineering and Computer Science, The University of Queensland, St Lucia, QLD, Australia"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1075\/pc.7.1.03cas"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1016\/j.specom.2013.09.008"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1111\/j.1756-8765.2012.01183.x"},{"key":"ref4","first-page":"25","article-title":"Robot behavior toolkit: Generating effective social behaviors for robots","volume-title":"Proc. 7th Annu. ACM\/IEEE Int. Conf. Hum.-Robot Interaction","author":"Huang","year":"2012"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01443"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i2.20097"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/THMS.2022.3149173"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1016\/j.rcim.2022.102404"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01022"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01021"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01016"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00053"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3548400"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1145\/3592097"},{"key":"ref15","first-page":"21386","article-title":"Audio-driven co-speech gesture video generation","volume":"35","author":"Liu","year":"2022","journal-title":"Proc. Adv. Neural Inf. Process. Syst."},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1145\/3550454.3555435"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20071-7_36"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2023\/650"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/TSA.2005.851998"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2019.8793720"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1145\/3414685.3417838"},{"key":"ref22","article-title":"Distilling the knowledge in a neural network","author":"Hinton","year":"2015"},{"key":"ref23","article-title":"Towards understanding ensemble, knowledge distillation and self-distillation in deep learning","volume-title":"arXiv:2012.09816","author":"Allen-Zhu"},{"key":"ref24","first-page":"3483","article-title":"Learning structured output representation using deep conditional generative models","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Sohn","year":"2015"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2013.6696634"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1145\/3491102.3517593"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1007\/s12369-011-0124-9"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00755"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2018.2856281"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1145\/2984511.2984517"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1145\/192161.192272"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1145\/2485895.2485900"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1007\/1-4020-3051-7_1"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01110"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/3DV.2019.00084"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/WACV48630.2021.00092"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00634"},{"key":"ref38","first-page":"7356","article-title":"Contact-aware human motion forecasting","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Mao","year":"2022"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00798"},{"key":"ref40","first-page":"41","article-title":"Nonrigid structure from motion in trajectory space","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Akhter","year":"2008"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/3DV.2017.00055"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00958"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00857"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01145"},{"key":"ref45","article-title":"Human motion diffusion model","author":"Tevet","year":"2022"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3551574"},{"key":"ref47","article-title":"Efficient estimation of word representations in vector space","author":"Mikolov","year":"2013"},{"key":"ref48","article-title":"Representation learning with contrastive predictive coding","author":"Oord","year":"2018"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01169"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00361"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58607-2_2"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00763"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2020-1064"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20065-6_26"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00589"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00448"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.4135\/9781446251409.n4"},{"key":"ref59","first-page":"6840","article-title":"Denoising diffusion probabilistic models","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Ho","year":"2020"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01975"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00925"}],"container-title":["IEEE Transactions on Multimedia"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/6046\/10384483\/10543093.pdf?arnumber=10543093","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,11,27]],"date-time":"2024-11-27T00:23:59Z","timestamp":1732667039000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10543093\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024]]},"references-count":61,"URL":"https:\/\/doi.org\/10.1109\/tmm.2024.3407692","relation":{},"ISSN":["1520-9210","1941-0077"],"issn-type":[{"value":"1520-9210","type":"print"},{"value":"1941-0077","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024]]}}}