{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,8,22]],"date-time":"2025-08-22T05:16:09Z","timestamp":1755839769052,"version":"3.28.0"},"reference-count":23,"publisher":"IEEE","license":[{"start":{"date-parts":[[2024,7,15]],"date-time":"2024-07-15T00:00:00Z","timestamp":1721001600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,7,15]],"date-time":"2024-07-15T00:00:00Z","timestamp":1721001600000},"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":[[2024,7,15]]},"DOI":"10.1109\/icme57554.2024.10687922","type":"proceedings-article","created":{"date-parts":[[2024,9,30]],"date-time":"2024-09-30T17:24:16Z","timestamp":1727717056000},"page":"1-6","source":"Crossref","is-referenced-by-count":3,"title":["ExpGest: Expressive Speaker Generation Using Diffusion Model and Hybrid Audio-Text Guidance"],"prefix":"10.1109","author":[{"given":"Yongkang","family":"Cheng","sequence":"first","affiliation":[{"name":"Tencent AILab,Shenzhen,China"}]},{"given":"Mingjiang","family":"Liang","sequence":"additional","affiliation":[{"name":"Tencent AILab,Shenzhen,China"}]},{"given":"Shaoli","family":"Huang","sequence":"additional","affiliation":[{"name":"Tencent AILab,Shenzhen,China"}]},{"given":"Jifeng","family":"Ning","sequence":"additional","affiliation":[{"name":"Northwest A&F University,Xianyan,China"}]},{"given":"Wei","family":"Liu","sequence":"additional","affiliation":[{"name":"University of Technology Sydney,Sydney,Australia"}]}],"member":"263","reference":[{"volume-title":"Gesture generation by imitation: From human behavior to computer character animation","year":"2005","author":"Kipp","key":"ref1"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1145\/3528233.3530750"},{"article-title":"Auto-encoding variational bayes","year":"2013","author":"Kingma","key":"ref3"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20065-6_41"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1145\/3550454.3555435"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2023\/650"},{"article-title":"Emog: Synthesizing emotive co-speech 3d gesture with diffusion model","year":"2023","author":"Yin","key":"ref7"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20071-7_36"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/3DV.2017.00059"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20047-2_28"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1089\/big.2016.0028"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00509"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52729.2023.01415"},{"article-title":"Human motion diffusion model","year":"2022","author":"Tevet","key":"ref14"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01726"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1145\/3592097"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1145\/2816795.2818013"},{"key":"ref18","first-page":"6840","article-title":"Denoising diffusion probabilistic models","volume":"33","author":"Ho","year":"2020"},{"article-title":"Bert: Pre-training of deep bidirectional transformers for language understanding","year":"2018","author":"Devlin","key":"ref19"},{"key":"ref20","first-page":"1597","article-title":"A simple framework for contrastive learning of visual representations","volume-title":"International conference on machine learning. PMLR","author":"Chen"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00554"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1111\/cgf.13555"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1145\/3414685.3417838"}],"event":{"name":"2024 IEEE International Conference on Multimedia and Expo (ICME)","start":{"date-parts":[[2024,7,15]]},"location":"Niagara Falls, ON, Canada","end":{"date-parts":[[2024,7,19]]}},"container-title":["2024 IEEE International Conference on Multimedia and Expo (ICME)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/10685847\/10687354\/10687922.pdf?arnumber=10687922","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,10,1]],"date-time":"2024-10-01T06:21:22Z","timestamp":1727763682000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10687922\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,7,15]]},"references-count":23,"URL":"https:\/\/doi.org\/10.1109\/icme57554.2024.10687922","relation":{},"subject":[],"published":{"date-parts":[[2024,7,15]]}}}