{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,11,28]],"date-time":"2024-11-28T00:10:12Z","timestamp":1732752612550,"version":"3.29.0"},"reference-count":29,"publisher":"IEEE","license":[{"start":{"date-parts":[[2024,8,4]],"date-time":"2024-08-04T00:00:00Z","timestamp":1722729600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,8,4]],"date-time":"2024-08-04T00:00:00Z","timestamp":1722729600000},"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":[[2024,8,4]]},"DOI":"10.1109\/ialp63756.2024.10661182","type":"proceedings-article","created":{"date-parts":[[2024,9,10]],"date-time":"2024-09-10T18:23:27Z","timestamp":1725992607000},"page":"210-215","source":"Crossref","is-referenced-by-count":0,"title":["MDG:Multilingual Co-speech Gesture Generation with Low-level Audio Representation and Diffusion Models"],"prefix":"10.1109","author":[{"given":"Jie","family":"Yang","sequence":"first","affiliation":[{"name":"Inner Mongolia University,Hohhot,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Feilong","family":"Bao","sequence":"additional","affiliation":[{"name":"Inner Mongolia University,Hohhot,China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1111\/cgf.14776"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1145\/3536221.3558058"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20071-7_36"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/iccv.2019.00085"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2022.3188113"},{"key":"ref6","first-page":"1298","article-title":"Data2vec: A general framework for self-supervised learning in speech, vision and language","volume-title":"International Conference on Machine Learning","author":"Baevski"},{"key":"ref7","first-page":"6840","article-title":"Denoising diffusion probabilistic models","volume":"33","author":"Ho","year":"2020","journal-title":"Advances in neural information processing systems"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1145\/3267851.3267898"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00361"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.143"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2023\/650"},{"key":"ref12","doi-asserted-by":"crossref","DOI":"10.1109\/CVPR52733.2024.00702","article-title":"Diffsheg: A diffusion-based approach for real-time speech-driven holistic 3d expression and gesture generation","author":"Chen","year":"2024"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3122291"},{"key":"ref14","first-page":"8780","article-title":"Diffusion models beat gans on image synthesis","volume":"34","author":"Dhariwal","year":"2021","journal-title":"Advances in neural information processing systems"},{"key":"ref15","first-page":"8633","article-title":"Video diffusion models","volume":"35","author":"Ho","year":"2022","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2024.3355414"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01016"},{"key":"ref18","first-page":"6840","article-title":"Denoising diffusion probabilistic models","volume":"33","author":"Ho","year":"2020","journal-title":"Advances in neural information processing systems"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1007\/978-1-4612-4380-9_35"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1145\/3414685.3417838"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/TSA.2005.851998"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1145\/3536221.3558060"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1145\/3308532.3329472"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.25080\/majora-7b98e3ed-003"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1016\/j.wocn.2018.07.001"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01021"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1145\/3577190.3616114"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1145\/3536221.3558066"}],"event":{"name":"2024 International Conference on Asian Language Processing (IALP)","start":{"date-parts":[[2024,8,4]]},"location":"Hohhot, China","end":{"date-parts":[[2024,8,6]]}},"container-title":["2024 International Conference on Asian Language Processing (IALP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/10660661\/10660673\/10661182.pdf?arnumber=10661182","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,11,27]],"date-time":"2024-11-27T23:49:22Z","timestamp":1732751362000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10661182\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,8,4]]},"references-count":29,"URL":"https:\/\/doi.org\/10.1109\/ialp63756.2024.10661182","relation":{},"subject":[],"published":{"date-parts":[[2024,8,4]]}}}