{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,18]],"date-time":"2026-08-18T00:35:32Z","timestamp":1787013332914,"version":"build-2736575974"},"reference-count":80,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"12","license":[{"start":{"date-parts":[[2024,12,1]],"date-time":"2024-12-01T00:00:00Z","timestamp":1733011200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2024,12,1]],"date-time":"2024-12-01T00:00:00Z","timestamp":1733011200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,12,1]],"date-time":"2024-12-01T00:00:00Z","timestamp":1733011200000},"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","award":["B07022"],"award-info":[{"award-number":["B07022"]}],"id":[{"id":"10.13039\/501100012226","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100012226","name":"Fundamental Research Funds for the Central Universities","doi-asserted-by":"publisher","award":["150633"],"award-info":[{"award-number":["150633"]}],"id":[{"id":"10.13039\/501100012226","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Shanghai Key Laboratory of Digital Media Processing and Transmissions, China"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Pattern Anal. Mach. Intell."],"published-print":{"date-parts":[[2024,12]]},"DOI":"10.1109\/tpami.2024.3409380","type":"journal-article","created":{"date-parts":[[2024,6,4]],"date-time":"2024-06-04T16:33:49Z","timestamp":1717518829000},"page":"8758-8770","source":"Crossref","is-referenced-by-count":11,"title":["Memories are One-to-Many Mapping Alleviators in Talking Face Generation"],"prefix":"10.1109","volume":"46","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-9772-3293","authenticated-orcid":false,"given":"Anni","family":"Tang","sequence":"first","affiliation":[{"name":"Institute of Image Communication and Network Engineering, Shanghai Jiao Tong University, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4828-3228","authenticated-orcid":false,"given":"Tianyu","family":"He","sequence":"additional","affiliation":[{"name":"Independent Contributors, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5631-0639","authenticated-orcid":false,"given":"Xu","family":"Tan","sequence":"additional","affiliation":[{"name":"Independent Contributors, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7260-7141","authenticated-orcid":false,"given":"Jun","family":"Ling","sequence":"additional","affiliation":[{"name":"Institute of Image Communication and Network Engineering, Shanghai Jiao Tong University, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Runnan","family":"Li","sequence":"additional","affiliation":[{"name":"Institute of Image Communication and Network Engineering, Shanghai Jiao Tong University, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Sheng","family":"Zhao","sequence":"additional","affiliation":[{"name":"Institute of Image Communication and Network Engineering, Shanghai Jiao Tong University, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jiang","family":"Bian","sequence":"additional","affiliation":[{"name":"Institute of Image Communication and Network Engineering, Shanghai Jiao Tong University, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"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"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1145\/3072959.3073640"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00802"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58517-4_42"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01386"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00573"},{"key":"ref6","first-page":"7137","article-title":"First order motion model for image animation","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Siarohin"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1145\/3478513.3480484"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1145\/3197517.3201283"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TVCG.2020.3023573"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1145\/3474085.3475280"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1145\/3394171.3413532"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00278"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i2.20102"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58545-7_3"},{"key":"ref15","article-title":"Audio-driven talking face video generation with learning-based personalized head pose","author":"Yi","year":"2020"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00384"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00416"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW50498.2020.00338"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01034"},{"key":"ref20","first-page":"1","article-title":"Memory networks","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Weston"},{"key":"ref21","first-page":"2440","article-title":"End-to-end memory networks","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Sukhbaatar"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1145\/311535.311556"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00366"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00366"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00360"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01357"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00339"},{"key":"ref28","first-page":"1","article-title":"Geneface: Generalized and high-fidelity audio-driven 3D talking face synthesis","volume-title":"Proc. 11th Int. Conf. Learn. Representations","author":"Ye"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00338"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2021\/152"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i2.25280"},{"issue":"6","key":"ref32","first-page":"1","article-title":"Makeittalk: Speaker-aware talking-head animation","volume":"39","author":"Zhou","year":"2020","journal-title":"ACM Trans. Graph."},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1145\/3550469.3555393"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00151"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00703"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2023.109865"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19775-8_39"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19836-6_7"},{"key":"ref39","article-title":"Real-time neural radiance talking portrait synthesis via audio-spatial decomposition","author":"Tang","year":"2022"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i3.16286"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1145\/3503250"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00854"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00696"},{"key":"ref44","article-title":"Deep speech: Scaling up end-to-end speech recognition","author":"Hannun","year":"2014"},{"key":"ref45","first-page":"1378","article-title":"Ask me anything: Dynamic memory networks for natural language processing","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Kumar"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00153"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/d16-1147"},{"key":"ref48","first-page":"4885","article-title":"Generalization through memorization: Nearest neighbor language models","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Khandelwal"},{"key":"ref49","first-page":"1","article-title":"Nearest neighbor machine translation","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Khandelwal"},{"key":"ref50","first-page":"1","article-title":"kNN-diffusion: Image generation via large-scale retrieval","volume-title":"Proc. 11th Int. Conf. Learn. Representations","author":"Sheynin"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00683"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01234"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58598-3_15"},{"key":"ref54","first-page":"15309","article-title":"Retrieval-augmented diffusion models","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Blattmann"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00482"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/ICME.2016.7552917"},{"key":"ref58","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"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2021.3108724"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2020.3004729"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref62","first-page":"2709","article-title":"Yourtts: Towards zero-shot multi-speaker TTS and zero-shot voice conversion for everyone","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Casanova"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-897"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-901"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-24574-4_28"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1603.08155"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.5555\/2969033.2969125"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01110"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01089"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i3.20162"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1109\/tpami.2024.3356232\/mm1"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D18-1326"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1109\/WACV45572.2020.9093622"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2021.3062849"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2022.3212915"},{"key":"ref76","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2022.3163183"},{"key":"ref77","first-page":"503","article-title":"Density estimation using real NVP","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Dinh"},{"key":"ref78","first-page":"1","article-title":"Auto-encoding variational bayes","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Kingma"},{"key":"ref79","doi-asserted-by":"publisher","DOI":"10.1121\/1.2229005"},{"issue":"11","key":"ref80","first-page":"2579","article-title":"Visualizing data using T-SNE","volume":"9","author":"Van der Maaten","year":"2008","journal-title":"J. Mach. Learn. Res."}],"container-title":["IEEE Transactions on Pattern Analysis and Machine Intelligence"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/34\/10746266\/10547422.pdf?arnumber=10547422","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,11,27]],"date-time":"2024-11-27T14:33:56Z","timestamp":1732718036000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10547422\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,12]]},"references-count":80,"journal-issue":{"issue":"12"},"URL":"https:\/\/doi.org\/10.1109\/tpami.2024.3409380","relation":{},"ISSN":["0162-8828","2160-9292","1939-3539"],"issn-type":[{"value":"0162-8828","type":"print"},{"value":"2160-9292","type":"electronic"},{"value":"1939-3539","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,12]]}}}