{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,1]],"date-time":"2026-04-01T07:03:52Z","timestamp":1775027032470,"version":"3.50.1"},"reference-count":119,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"6","license":[{"start":{"date-parts":[[2024,6,1]],"date-time":"2024-06-01T00:00:00Z","timestamp":1717200000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2024,6,1]],"date-time":"2024-06-01T00:00:00Z","timestamp":1717200000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,6,1]],"date-time":"2024-06-01T00:00:00Z","timestamp":1717200000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100012166","name":"National Key Research and Development Program of China","doi-asserted-by":"publisher","award":["2021ZD0140407"],"award-info":[{"award-number":["2021ZD0140407"]}],"id":[{"id":"10.13039\/501100012166","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"NSFC","doi-asserted-by":"publisher","award":["62022048"],"award-info":[{"award-number":["62022048"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"NSFC","doi-asserted-by":"publisher","award":["62276150"],"award-info":[{"award-number":["62276150"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100020721","name":"Guoqiang Institute of Tsinghua University","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100020721","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Circuits Syst. Video Technol."],"published-print":{"date-parts":[[2024,6]]},"DOI":"10.1109\/tcsvt.2023.3330920","type":"journal-article","created":{"date-parts":[[2023,11,7]],"date-time":"2023-11-07T19:26:24Z","timestamp":1699385184000},"page":"4270-4284","source":"Crossref","is-referenced-by-count":11,"title":["FaceCLIP: Facial Image-to-Video Translation via a Brief Text Description"],"prefix":"10.1109","volume":"34","author":[{"ORCID":"https:\/\/orcid.org\/0009-0005-7004-939X","authenticated-orcid":false,"given":"Jiayi","family":"Guo","sequence":"first","affiliation":[{"name":"Department of Automation, Tsinghua University, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0009-0004-4848-1656","authenticated-orcid":false,"given":"Hayk","family":"Manukyan","sequence":"additional","affiliation":[{"name":"PicsArt AI Research (PAIR), Eugene, Armenia"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9997-4929","authenticated-orcid":false,"given":"Chenyu","family":"Yang","sequence":"additional","affiliation":[{"name":"Institute for Interdisciplinary Information Sciences, Tsinghua University, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3678-691X","authenticated-orcid":false,"given":"Chaofei","family":"Wang","sequence":"additional","affiliation":[{"name":"Department of Automation, Tsinghua University, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5840-760X","authenticated-orcid":false,"given":"Levon","family":"Khachatryan","sequence":"additional","affiliation":[{"name":"PicsArt AI Research (PAIR), Eugene, Armenia"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1999-9999","authenticated-orcid":false,"given":"Shant","family":"Navasardyan","sequence":"additional","affiliation":[{"name":"PicsArt AI Research (PAIR), Eugene, Armenia"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0858-1770","authenticated-orcid":false,"given":"Shiji","family":"Song","sequence":"additional","affiliation":[{"name":"Department of Automation, Tsinghua University, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2922-5663","authenticated-orcid":false,"given":"Humphrey","family":"Shi","sequence":"additional","affiliation":[{"name":"PicsArt AI Research (PAIR), Eugene, Armenia"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7251-0988","authenticated-orcid":false,"given":"Gao","family":"Huang","sequence":"additional","affiliation":[{"name":"Department of Automation, Tsinghua University, Beijing, China"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-67070-2_17"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00524"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1145\/3474085.3475531"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01754"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00202"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.12277"},{"key":"ref7","article-title":"Geometry-contrastive GAN for facial expression transfer","author":"Qiao","year":"2018","journal-title":"arXiv:1802.01822"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1145\/3240508.3240612"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00507"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2021.3074032"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2023.3255243"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00453"},{"key":"ref13","first-page":"12104","article-title":"Training generative adversarial networks with limited data","volume-title":"Proc. NeurIPS","author":"Karras"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.2106.12423"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00232"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1145\/3450626.3459838"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00664"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2021.3089905"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00209"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1145\/3528223.3530164"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00813"},{"key":"ref22","first-page":"1","article-title":"Unsupervised learning for physical interaction through video prediction","volume-title":"Proc. NeurIPS","author":"Finn"},{"key":"ref23","first-page":"1","article-title":"PredRNN: Recurrent neural networks for predictive learning using spatiotemporal LSTMs","volume-title":"Proc. NeurIPS","author":"Wang"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01380"},{"key":"ref25","first-page":"1","article-title":"Few-shot video-to-video synthesis","volume-title":"Proc. NeurIPS","author":"Wang"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00955"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00520"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01246-5_37"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00802"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2019\/129"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-019-01251-8"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01261-8_41"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1145\/3306346.3323028"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.262"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1145\/3197517.3201283"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1145\/3272127.3275043"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1145\/3355089.3356500"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01413"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01350"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2021.3106047"},{"key":"ref41","first-page":"1","article-title":"First order motion model for image animation","volume-title":"Proc. NeurIPS","author":"Siarohin"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00248"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2021.3083257"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00991"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2023.3268062"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33019299"},{"key":"ref47","first-page":"1","article-title":"CogVideo: Large-scale pretraining for text-to-video generation via transformers","volume-title":"Proc. ICLR","author":"Hong"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19787-1_41"},{"key":"ref49","first-page":"1","article-title":"Make-a-video: Text-to-video generation without text-video data","volume-title":"Proc. ICLR","author":"Singer"},{"key":"ref50","article-title":"Video (language) modeling: A baseline for generative models of natural videos","author":"Ranzato","year":"2014","journal-title":"arXiv:1412.6604"},{"key":"ref51","first-page":"1","article-title":"Deep multi-scale video prediction beyond mean square error","volume-title":"Proc. ICLR","author":"Mathieu"},{"key":"ref52","first-page":"1","article-title":"Decomposing motion and content for natural video sequence prediction","volume-title":"Proc. ICLR","author":"Villegas"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33013510"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1145\/3343031.3350981"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01267-0_24"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-020-01328-9"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2019.2946475"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/WACV48630.2021.00312"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00374"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2020.3035281"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2020.2987141"},{"key":"ref62","first-page":"1","article-title":"Convolutional LSTM network: A machine learning approach for precipitation nowcasting","volume-title":"Proc. NeurIPS","author":"Shi"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19790-1_6"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/WACV45572.2020.9093492"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01768"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00365"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01769"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01228-1_8"},{"key":"ref69","first-page":"1","article-title":"Video-to-video synthesis","volume-title":"Proc. NeurIPS","author":"Wang"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01344"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.598"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2023.109902"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.244"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00532"},{"key":"ref75","first-page":"1","article-title":"Generative adversarial nets","volume-title":"Proc. NeurIPS","author":"Goodfellow"},{"key":"ref76","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2019.2916751"},{"key":"ref77","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2018.2869695"},{"key":"ref78","first-page":"6840","article-title":"Denoising diffusion probabilistic models","volume-title":"Proc. NeurIPS","author":"Ho"},{"key":"ref79","first-page":"1","article-title":"Denoising diffusion implicit models","volume-title":"Proc. ICLR","author":"Song"},{"key":"ref80","first-page":"8780","article-title":"Diffusion models beat GANs on image synthesis","volume-title":"Proc. NeurIPS","author":"Dhariwal"},{"key":"ref81","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"ref82","first-page":"1060","article-title":"Generative adversarial text to image synthesis","volume-title":"Proc. ICML","author":"Reed"},{"key":"ref83","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.629"},{"key":"ref84","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00143"},{"key":"ref85","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2018.2856256"},{"key":"ref86","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01245"},{"key":"ref87","doi-asserted-by":"publisher","DOI":"10.1109\/WACV48630.2021.00028"},{"key":"ref88","article-title":"T-person-GAN: Text-to-person image generation with identity-consistency and manifold mix-up","author":"Liu","year":"2022"},{"key":"ref89","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2022.3151631"},{"key":"ref90","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2020.3026728"},{"key":"ref91","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2021.3055062"},{"key":"ref92","first-page":"8821","article-title":"Zero-shot text-to-image generation","volume-title":"Proc. ICML","author":"Ramesh"},{"key":"ref93","article-title":"Hierarchical text-conditional image generation with CLIP latents","author":"Ramesh","year":"2022","journal-title":"arXiv:2204.06125"},{"key":"ref94","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.608"},{"key":"ref95","first-page":"1","article-title":"Text-adaptive generative adversarial networks: Manipulating images with natural language","volume-title":"Proc. NeurIPS","author":"Nam"},{"key":"ref96","doi-asserted-by":"publisher","DOI":"10.1145\/3394171.3413505"},{"key":"ref97","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00790"},{"key":"ref98","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00246"},{"key":"ref99","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.12233"},{"key":"ref100","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2019\/276"},{"key":"ref101","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2019\/307"},{"key":"ref102","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"Proc. ICML","author":"Radford"},{"key":"ref103","first-page":"4904","article-title":"Scaling up visual and vision-language representation learning with noisy text supervision","volume-title":"Proc. ICML","author":"Jia"},{"key":"ref104","article-title":"CLIP-GEN: Language-free training of a text-to-image generator with CLIP","author":"Wang","year":"2022","journal-title":"arXiv:2203.00386"},{"key":"ref105","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20047-2_21"},{"key":"ref106","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01106"},{"key":"ref107","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW.2016.182"},{"key":"ref108","first-page":"94","article-title":"The extended: A complete dataset for action unit and emotion-specified expression","volume-title":"Proc. CVPR Workshops","author":"Lucey"},{"key":"ref109","doi-asserted-by":"publisher","DOI":"10.1037\/t27734-000"},{"key":"ref110","doi-asserted-by":"publisher","DOI":"10.1037\/t27734-000"},{"key":"ref111","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref112","article-title":"Grasping the arrow of time from the singularity: Decoding micromotion in low-dimensional latent spaces from StyleGAN","author":"Wu","year":"2022","journal-title":"arXiv:2204.12696"},{"key":"ref113","first-page":"1","article-title":"PyTorch: An imperative style, high-performance deep learning library","volume-title":"Proc. NeurIPS","author":"Paszke"},{"key":"ref114","volume-title":"Ranger\u2014A Synergistic Optimizer","author":"Wright","year":"2019"},{"key":"ref115","first-page":"1","article-title":"FVD: A new metric for video generation","volume-title":"Proc. ICLR Workshops","author":"Unterthiner"},{"key":"ref116","first-page":"1755","article-title":"Dlib-ml: A machine learning toolkit","volume":"10","author":"King","year":"2009","journal-title":"J. Mach. Learn. Res."},{"key":"ref117","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-540-74048-3_4"},{"key":"ref118","doi-asserted-by":"publisher","DOI":"10.1016\/0022-2836(70)90057-4"},{"key":"ref119","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00482"}],"container-title":["IEEE Transactions on Circuits and Systems for Video Technology"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/76\/10550083\/10310257.pdf?arnumber=10310257","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,1,9]],"date-time":"2025-01-09T20:10:37Z","timestamp":1736453437000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10310257\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,6]]},"references-count":119,"journal-issue":{"issue":"6"},"URL":"https:\/\/doi.org\/10.1109\/tcsvt.2023.3330920","relation":{},"ISSN":["1051-8215","1558-2205"],"issn-type":[{"value":"1051-8215","type":"print"},{"value":"1558-2205","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,6]]}}}