{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,11]],"date-time":"2026-03-11T03:35:40Z","timestamp":1773200140792,"version":"3.50.1"},"reference-count":77,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"6","license":[{"start":{"date-parts":[[2023,11,1]],"date-time":"2023-11-01T00:00:00Z","timestamp":1698796800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2023,11,1]],"date-time":"2023-11-01T00:00:00Z","timestamp":1698796800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,11,1]],"date-time":"2023-11-01T00:00:00Z","timestamp":1698796800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100012226","name":"Fundamental Research Funds for the Central Universities","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100012226","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100003399","name":"Science and Technology Commission of Shanghai Municipality","doi-asserted-by":"publisher","award":["22DZ2229005"],"award-info":[{"award-number":["22DZ2229005"]}],"id":[{"id":"10.13039\/501100003399","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100013314","name":"Higher Education Discipline Innovation Project","doi-asserted-by":"publisher","award":["BP0719010"],"award-info":[{"award-number":["BP0719010"]}],"id":[{"id":"10.13039\/501100013314","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100004318","name":"Microsoft","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100004318","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE J. Sel. Top. Signal Process."],"published-print":{"date-parts":[[2023,11]]},"DOI":"10.1109\/jstsp.2023.3333552","type":"journal-article","created":{"date-parts":[[2023,11,16]],"date-time":"2023-11-16T19:02:26Z","timestamp":1700161346000},"page":"1232-1247","source":"Crossref","is-referenced-by-count":11,"title":["StableFace: Analyzing and Improving Motion Stability for Talking Face Generation"],"prefix":"10.1109","volume":"17","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-7260-7141","authenticated-orcid":false,"given":"Jun","family":"Ling","sequence":"first","affiliation":[{"name":"Institute of Image Communication and Network Engineering, Shanghai Jiao Tong University, Shanghai, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5631-0639","authenticated-orcid":false,"given":"Xu","family":"Tan","sequence":"additional","affiliation":[{"name":"Microsoft Research Asia (MSRA), Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6985-8281","authenticated-orcid":false,"given":"Liyang","family":"Chen","sequence":"additional","affiliation":[{"name":"Tsinghua University, Shenzhen, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0922-003X","authenticated-orcid":false,"given":"Runnan","family":"Li","sequence":"additional","affiliation":[{"name":"Microsoft Cloud+AI, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0009-0006-0191-3612","authenticated-orcid":false,"given":"Yuchao","family":"Zhang","sequence":"additional","affiliation":[{"name":"Microsoft Cloud+AI, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9624-5381","authenticated-orcid":false,"given":"Sheng","family":"Zhao","sequence":"additional","affiliation":[{"name":"Microsoft Cloud+AI, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7124-5182","authenticated-orcid":false,"given":"Li","family":"Song","sequence":"additional","affiliation":[{"name":"Institute of Image Communication and Network Engineering, Shanghai Jiao Tong University, Shanghai, China"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00802"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00278"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1145\/3394171.3413532"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-019-01251-8"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58517-4_42"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00573"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1145\/3478513.3480484"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19836-6_7"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01386"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1145\/3528233.3530745"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2003.819861"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/tmm.2022.3207606"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1145\/3474085.3475196"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/TVCG.2020.3023573"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00384"},{"key":"ref16","first-page":"1","article-title":"Geneface: Generalized and high-fidelity audio-driven 3D talking face synthesis","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Ye","year":"2023"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2022.3142387"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1145\/3450626.3459936"},{"key":"ref19","first-page":"5998","article-title":"Attention is all you need","volume-title":"Proc. Adv. Neural Inform. Process. Syst","author":"Vaswani","year":"2017"},{"key":"ref20","first-page":"1","article-title":"An image is worth 16x16 words: Transformers for image recognition at scale","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Dosovitskiy","year":"2021"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.262"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01261-8_41"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1145\/3197517.3201283"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1145\/3272127.3275075"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ICIP40778.2020.9190699"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ICME52920.2022.9859867"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1145\/3306346.3323028"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1145\/3449063"},{"key":"ref29","first-page":"109.1","article-title":"You said that?","volume-title":"Proc. Brit. Mach. Vis. Conf","author":"Chung","year":"2017"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01234-2_32"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33019299"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1145\/3394171.3413623"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00416"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1145\/3072959.3073640"},{"key":"ref35","first-page":"7137","article-title":"First order motion model for image animation","volume-title":"Proc. Adv. Neural Inform. Process. Syst.","author":"Siarohin","year":"2019"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2023.3262357"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1145\/311535.311556"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1145\/3474085.3475280"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01413"},{"key":"ref40","first-page":"4171","article-title":"Bert: Pre-training of deep bidirectional transformers for language understanding","volume-title":"Proc. North Amer. Chapter Assoc. Comput. Linguistics-Hum. Lang. Technol. (NAACL-HLT)","author":"Devlin","year":"2019"},{"key":"ref41","first-page":"3171","article-title":"Fastspeech: Fast, robust and controllable text to speech","volume-title":"Proc. Adv. Neural Inform. Process. Syst.","author":"Ren","year":"2019"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01821"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9747495"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01378"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00350"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58452-8_13"},{"key":"ref47","first-page":"1","article-title":"Deformable DETR: Deformable transformers for end-to-end object detection","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Zhu","year":"2021"},{"key":"ref48","first-page":"21125","article-title":"Improving visual quality of image synthesis by a token-based generator with transformers","volume-title":"Proc. Adv. Neural Inform. Process. Syst.","author":"Zeng","year":"2021"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01460"},{"key":"ref50","article-title":"Learning to generate diverse dance motions with transformer","author":"Li","year":"2020"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2020.2973374"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01267-0_11"},{"key":"ref53","first-page":"1083","article-title":"Blind video temporal consistency via deep video prior","volume-title":"Proc. Adv. Neural Inform. Process. Syst.","author":"Lei","year":"2020"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2006.141"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1145\/1531326.1531350"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2018.2884280"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2022.3142429"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1017\/ATSIP.2013.5"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/ICPR.2014.153"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1007\/s11432-019-2757-1"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.3390\/app11104661"},{"key":"ref62","first-page":"1","article-title":"Impact of jitter and jerkiness on perceived video quality","volume-title":"Proc. Worksh. Video Process. Qual. Metrics","author":"Huynh-Thu","year":"2006"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1145\/319878.319909"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2014.2332304"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1145\/3343031.3351028"},{"key":"ref66","first-page":"173","article-title":"Deep speech 2: End-to-end speech recognition in english and mandarin","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Amodei","year":"2016"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1007\/0-387-28831-7_15"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.457"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00366"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46475-6_43"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1121\/1.2229005"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1109\/QOMEX.2009.5246972"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-54427-4_19"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.116"},{"key":"ref76","doi-asserted-by":"publisher","DOI":"10.1145\/3130800.3130813"},{"key":"ref77","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2020.3001719"}],"container-title":["IEEE Journal of Selected Topics in Signal Processing"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/4200690\/10378961\/10319685.pdf?arnumber=10319685","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,2,8]],"date-time":"2024-02-08T18:40:45Z","timestamp":1707417645000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10319685\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,11]]},"references-count":77,"journal-issue":{"issue":"6"},"URL":"https:\/\/doi.org\/10.1109\/jstsp.2023.3333552","relation":{},"ISSN":["1932-4553","1941-0484"],"issn-type":[{"value":"1932-4553","type":"print"},{"value":"1941-0484","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,11]]}}}