{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,4]],"date-time":"2026-08-04T15:24:11Z","timestamp":1785857051676,"version":"3.56.0"},"reference-count":77,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100012166","name":"\u201cLeading Goose\u201d Research and Development Program of Zhejiang Province","doi-asserted-by":"publisher","award":["2024C01101"],"award-info":[{"award-number":["2024C01101"]}],"id":[{"id":"10.13039\/501100012166","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62025101"],"award-info":[{"award-number":["62025101"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62088102"],"award-info":[{"award-number":["62088102"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"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"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. on Image Process."],"published-print":{"date-parts":[[2024]]},"DOI":"10.1109\/tip.2024.3518100","type":"journal-article","created":{"date-parts":[[2024,12,20]],"date-time":"2024-12-20T19:13:41Z","timestamp":1734722021000},"page":"6850-6864","source":"Crossref","is-referenced-by-count":4,"title":["Ultra-Low Bitrate Face Video Compression Based on Conversions From 3D Keypoints to 2D Motion Map"],"prefix":"10.1109","volume":"33","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-7500-5584","authenticated-orcid":false,"given":"Zhao","family":"Wang","sequence":"first","affiliation":[{"name":"School of Computer Science, Peking University, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0009-7076-4739","authenticated-orcid":false,"given":"Bolin","family":"Chen","sequence":"additional","affiliation":[{"name":"School of Computer Science, City University of Hong Kong, Hong Kong, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0758-9175","authenticated-orcid":false,"given":"Shurun","family":"Wang","sequence":"additional","affiliation":[{"name":"Damo Academy, Alibaba Group, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3583-959X","authenticated-orcid":false,"given":"Shiqi","family":"Wang","sequence":"additional","affiliation":[{"name":"School of Computer Science, City University of Hong Kong, Hong Kong, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7278-0822","authenticated-orcid":false,"given":"Yan","family":"Ye","sequence":"additional","affiliation":[{"name":"Damo Academy, Alibaba Group, Sunnyvale, CA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2731-5403","authenticated-orcid":false,"given":"Siwei","family":"Ma","sequence":"additional","affiliation":[{"name":"School of Computer Science, Peking University, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2003.815165"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2012.2221191"},{"key":"ref3","volume-title":"Versatile Video Coding (Draft 10)","author":"Bross","year":"2020"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1007\/3-540-60268-2_327"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/76.305867"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICPR.1992.201932"},{"key":"ref7","first-page":"14","article-title":"Auto-encoding variational Bayes","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Kingma"},{"key":"ref8","first-page":"1","article-title":"Generative adversarial nets","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"27","author":"Goodfellow"},{"key":"ref9","first-page":"8780","article-title":"Diffusion models beat GANs on image synthesis","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"34","author":"Dhariwal"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01261-8_41"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00955"},{"key":"ref12","article-title":"Few-shot video-to-video synthesis","author":"Wang","year":"2019","journal-title":"arXiv:1910.12713"},{"key":"ref13","first-page":"1","article-title":"First order motion model for image animation","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"32","author":"Siarohin"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01344"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW53098.2021.00271"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414731"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICMEW53276.2021.9455985"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00991"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/DCC52660.2022.00009"},{"key":"ref20","article-title":"Interactive face video coding: A generative compression framework","author":"Chen","year":"2023","journal-title":"arXiv:2302.09919"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2023.3271130"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/DCC58796.2024.00019"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/DCC58796.2024.00018"},{"key":"ref24","volume-title":"Non-EE2: Intra Template-Matching Prediction Fusion","author":"Zhang","year":"2023"},{"key":"ref25","volume-title":"Non-EE2: AMVP Mode With Subblock-Based Temporal Motion Vector Prediction","author":"Liao","year":"2023"},{"key":"ref26","volume-title":"AHG12\u2014Dynamic Cabac Models","author":"Bianco","year":"2023"},{"key":"ref27","volume-title":"Algorithm Description of Enhanced Compression Model 7 (ECM 7)","author":"Coban","year":"2022"},{"key":"ref28","volume-title":"JVET AHG Report: ECM Software Development (AHG6)","author":"Seregin","year":"2023"},{"key":"ref29","article-title":"End-to-end optimized image compression","author":"Ball\u00e9","year":"2016","journal-title":"arXiv:1611.01704"},{"key":"ref30","first-page":"1141","article-title":"Soft-to-hard vector quantization for end-to-end learning compressible representations","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"30","author":"Agustsson"},{"key":"ref31","article-title":"Variational image compression with a scale hyperprior","author":"Ball\u00e9","year":"2018","journal-title":"arXiv:1802.01436"},{"key":"ref32","first-page":"1","article-title":"Joint autoregressive and hierarchical priors for learned image compression","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"31","author":"Minnen"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00796"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01126"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00155"},{"key":"ref36","first-page":"18114","article-title":"Deep contextual video compression","volume-title":"Proc. Adv. Neural Inf. Process. Syst. (NIPS)","volume":"34","author":"Li"},{"key":"ref37","first-page":"9283","article-title":"Deep generative video compression","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"32","author":"Lombardo"},{"key":"ref38","article-title":"Towards generative video compression","author":"Mentzer","year":"2021","journal-title":"arXiv:2107.12038"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/AVSS.2009.58"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/TVCG.2013.249"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.598"},{"issue":"6","key":"ref42","first-page":"1","article-title":"Learning a model of facial shape and expression from 4D scans","volume":"36","author":"Li","year":"2017","journal-title":"ACM Trans. Graph."},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1145\/311535.311556"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.244"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00916"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.580"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01249-6_50"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00618"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01005"},{"key":"ref50","article-title":"HeadGAN: Video-and-audio-driven talking head synthesis","author":"Christos Doukas","year":"2020","journal-title":"arXiv:2012.08261"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-020-01338-7"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00785"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00453"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1145\/3272127.3275043"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i07.6717"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00248"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01380"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/5.364463"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/PROC.1985.13202"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.1991.150969"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00244"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-24574-4_28"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.01020"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1007\/3-540-45103-X_50"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1603.08155"},{"key":"ref66","article-title":"Very deep convolutional networks for large-scale image recognition","author":"Simonyan","year":"2014","journal-title":"arXiv:1409.1556"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00482"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.304"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00285"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-950"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW.2015.126"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2020.3045810"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00068"},{"key":"ref74","first-page":"1","article-title":"FVD: A new metric for video generation","volume-title":"Proc. 7th Int. Conf. Learn. Represent. Workshop","author":"Unterthiner"},{"key":"ref75","article-title":"Calculation of average PSNR differences between RD-curves","author":"Bj\u00f8ntegaard","year":"2001"},{"key":"ref76","volume-title":"Algorithm Description for Versatile Video Coding and Test Model 10 (VTM 10)","author":"Chen","year":"2020"},{"key":"ref77","volume-title":"JVET Common Test Conditions and Software Reference Configurations for SDR Video","author":"Bossen","year":"2019"}],"container-title":["IEEE Transactions on Image Processing"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/83\/10346232\/10811831.pdf?arnumber=10811831","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,12,30]],"date-time":"2024-12-30T19:46:08Z","timestamp":1735587968000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10811831\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024]]},"references-count":77,"URL":"https:\/\/doi.org\/10.1109\/tip.2024.3518100","relation":{},"ISSN":["1057-7149","1941-0042"],"issn-type":[{"value":"1057-7149","type":"print"},{"value":"1941-0042","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024]]}}}