{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,7]],"date-time":"2026-03-07T17:47:02Z","timestamp":1772905622797,"version":"3.50.1"},"reference-count":58,"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\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62072141"],"award-info":[{"award-number":["62072141"]}],"id":[{"id":"10.13039\/501100001809","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":[[2024,12]]},"DOI":"10.1109\/tcsvt.2024.3436900","type":"journal-article","created":{"date-parts":[[2024,8,1]],"date-time":"2024-08-01T18:36:02Z","timestamp":1722537362000},"page":"12862-12872","source":"Crossref","is-referenced-by-count":5,"title":["Toward Open-World Text-Driven Face Generation and Manipulation via StyleGAN3"],"prefix":"10.1109","volume":"34","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-4181-310X","authenticated-orcid":false,"given":"Zonglin","family":"Li","sequence":"first","affiliation":[{"name":"School of Computer Science and Technology, Harbin Institute of Technology, Weihai, China"}]},{"given":"Zhaoxin","family":"Zhang","sequence":"additional","affiliation":[{"name":"School of Computer Science and Technology, Harbin Institute of Technology, Weihai, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4774-7094","authenticated-orcid":false,"given":"Peiqiang","family":"Liu","sequence":"additional","affiliation":[{"name":"School of Computer Science and Technology, Shandong Technology and Business University, Yantai, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2408-3344","authenticated-orcid":false,"given":"Qinglin","family":"Liu","sequence":"additional","affiliation":[{"name":"School of Computer Science and Technology, Harbin Institute of Technology, Weihai, China"}]},{"given":"Xin","family":"Sun","sequence":"additional","affiliation":[{"name":"School of Computer Science and Technology, Harbin Institute of Technology, Weihai, China"}]}],"member":"263","reference":[{"key":"ref1","article-title":"Towards open-world text-guided face image generation and manipulation","author":"Xia","year":"2021","journal-title":"arXiv:2104.08910"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00209"},{"key":"ref3","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"Proc. Int. Conf. Mach. Learn.","volume":"139","author":"Radford"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00813"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1145\/3544777"},{"key":"ref6","article-title":"Predict, prevent, and evaluate: Disentangled text-driven image manipulation empowered by pre-trained vision-language model","author":"Xu","year":"2021","journal-title":"arXiv:2111.13333"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00229"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.2106.12423"},{"key":"ref9","first-page":"1060","article-title":"Generative adversarial text to image synthesis","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Reed"},{"key":"ref10","article-title":"DF-GAN: A simple and effective baseline for Text-to-Image synthesis","author":"Tao","year":"2020","journal-title":"arXiv:2008.05865"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2023.3274228"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2021.3136857"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.629"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2018.2856256"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00143"},{"key":"ref16","first-page":"1","article-title":"Text-adaptive generative adversarial networks: Manipulating images with natural language","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"31","author":"Nam"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00790"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2022.3213662"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/WACV51458.2022.00350"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2020.3034267"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1016\/j.neunet.2021.10.017"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2022.3222456"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2022.3207310"},{"key":"ref24","first-page":"9841","article-title":"GANSpace: Discovering interpretable GAN controls","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"33","author":"H\u00e4rk\u00f6nen"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00618"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01400"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00232"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1145\/3450626.3459838"},{"key":"ref29","article-title":"Improved StyleGAN embedding: Where are the good latents?","author":"Zhu","year":"2020","journal-title":"arXiv:2012.09036"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00453"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01267"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-25063-7_13"},{"key":"ref33","first-page":"1755","article-title":"Dlib-ml: A machine learning toolkit","volume":"10","author":"King","year":"2009","journal-title":"J. Mach. Learn. Res."},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01796"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00664"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01110"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00068"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00482"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2016.2603342"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00544"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2021.3068825"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00453"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00559"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1145\/3474085.3475391"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref46","first-page":"1","article-title":"ImageNet classification with deep convolutional neural networks","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"25","author":"Krizhevsky"},{"key":"ref47","article-title":"On the variance of the adaptive learning rate and beyond","author":"Liu","year":"2019","journal-title":"arXiv:1908.03265"},{"key":"ref48","first-page":"9597","article-title":"Lookahead optimizer: K steps forward, 1 step back","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"32","author":"Zhang"},{"key":"ref49","article-title":"Adam: A method for stochastic optimization","author":"Kingma","year":"2014","journal-title":"arXiv:1412.6980"},{"key":"ref50","article-title":"Very deep convolutional networks for large-scale image recognition","author":"Simonyan","year":"2014","journal-title":"arXiv:1409.1556"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/ACSSC.2003.1292216"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00594"},{"key":"ref53","first-page":"2065","article-title":"Controllable text-to-image generation","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"32","author":"Li"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00595"},{"key":"ref55","first-page":"6629","article-title":"GANs trained by a two time-scale update rule converge to a local nash equilibrium","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"30","author":"Heusel"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00666"},{"key":"ref57","volume-title":"Clip-score: CLIP Score for PyTorch Version 0.1.1","author":"Zhengwentai","year":"2023"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01015"}],"container-title":["IEEE Transactions on Circuits and Systems for Video Technology"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/76\/10811772\/10620351.pdf?arnumber=10620351","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,1,15]],"date-time":"2025-01-15T20:20:31Z","timestamp":1736972431000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10620351\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,12]]},"references-count":58,"journal-issue":{"issue":"12"},"URL":"https:\/\/doi.org\/10.1109\/tcsvt.2024.3436900","relation":{},"ISSN":["1051-8215","1558-2205"],"issn-type":[{"value":"1051-8215","type":"print"},{"value":"1558-2205","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,12]]}}}