{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,19]],"date-time":"2026-06-19T05:54:56Z","timestamp":1781848496763,"version":"3.54.5"},"reference-count":44,"publisher":"IEEE","license":[{"start":{"date-parts":[[2026,5,24]],"date-time":"2026-05-24T00:00:00Z","timestamp":1779580800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,5,24]],"date-time":"2026-05-24T00:00:00Z","timestamp":1779580800000},"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":[[2026,5,24]]},"DOI":"10.1109\/iscas66217.2026.11562012","type":"proceedings-article","created":{"date-parts":[[2026,6,18]],"date-time":"2026-06-18T20:06:41Z","timestamp":1781813201000},"page":"2599-2603","source":"Crossref","is-referenced-by-count":0,"title":["Audio-Visual Synergy for High-Fidelity Portrait Animation: A Two-Stage Framework with Identity-Motion Disentanglement"],"prefix":"10.1109","author":[{"given":"Yuzhi","family":"Lu","sequence":"first","affiliation":[{"name":"University of Electronic Science and Technology of China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yuanzong","family":"Mei","sequence":"additional","affiliation":[{"name":"Southwest China Research Institute of Electronic Equipment"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Wenyi","family":"Wang","sequence":"additional","affiliation":[{"name":"University of Electronic Science and Technology of China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xi","family":"Chen","sequence":"additional","affiliation":[{"name":"University of Electronic Science and Technology of China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xiaowen","family":"Chen","sequence":"additional","affiliation":[{"name":"University of Electronic Science and Technology of China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zhi","family":"Wang","sequence":"additional","affiliation":[{"name":"University of Electronic Science and Technology of China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Feng","family":"Xu","sequence":"additional","affiliation":[{"name":"University of Electronic Science and Technology of China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jianwen","family":"Chen","sequence":"additional","affiliation":[{"name":"University of Electronic Science and Technology of China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","article-title":"Contrastive audio-visual masked autoencoder[J]","author":"Gong","year":"2022"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr.2017.632"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr.2018.00359"},{"key":"ref4","first-page":"31","article-title":"Soft-gated warping-gan for pose-guided person image synthesis[J]","author":"Dong","year":"2018","journal-title":"Advances in neural information processing systems"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3548330"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00364"},{"key":"ref7","first-page":"32","article-title":"First order motion model for image animation[J]","author":"Siarohin","year":"2019","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01344"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v39i10.33195"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.116"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00927"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-24574-4_28"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00248"},{"key":"ref14","first-page":"28","article-title":"Deep generative image models using a laplacian pyramid of adversarial networks[J]","author":"Denton","year":"2015","journal-title":"Advances in neural information processing systems"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.618"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46475-6_43"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICMEW46912.2020.9105991"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr46437.2021.00991"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1111\/cgf.14062"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00603"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i07.6721"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00771"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.262"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00955"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01261-8_41"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00197"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00436"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00389"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00194"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00737"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.02133"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.00030"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.00027"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-12093-5_13"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v39i9.33002"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1145\/3394171.3413532"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01246-5_27"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01274"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00129"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-698"},{"key":"ref41","article-title":"An image is worth 16x16 words: Transformers for image recognition at scale[J]","author":"Dosovitskiy","year":"2020"},{"key":"ref42","article-title":"Adam: A method for stochastic optimization[J]","author":"Kingma","year":"2014"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-950"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1929"}],"event":{"name":"2026 IEEE International Symposium on Circuits and Systems (ISCAS)","location":"Shanghai, China","start":{"date-parts":[[2026,5,24]]},"end":{"date-parts":[[2026,5,28]]}},"container-title":["2026 IEEE International Symposium on Circuits and Systems (ISCAS)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11561899\/11561804\/11562012.pdf?arnumber=11562012","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,6,19]],"date-time":"2026-06-19T05:47:56Z","timestamp":1781848076000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11562012\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,5,24]]},"references-count":44,"URL":"https:\/\/doi.org\/10.1109\/iscas66217.2026.11562012","relation":{},"subject":[],"published":{"date-parts":[[2026,5,24]]}}}