{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,8]],"date-time":"2026-07-08T17:03:57Z","timestamp":1783530237584,"version":"3.55.0"},"reference-count":82,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"8","license":[{"start":{"date-parts":[[2024,8,1]],"date-time":"2024-08-01T00:00:00Z","timestamp":1722470400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2024,8,1]],"date-time":"2024-08-01T00:00:00Z","timestamp":1722470400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,8,1]],"date-time":"2024-08-01T00:00:00Z","timestamp":1722470400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100001809","name":"NSFC","doi-asserted-by":"publisher","award":["U20A20183"],"award-info":[{"award-number":["U20A20183"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"NSFC","doi-asserted-by":"publisher","award":["62021001"],"award-info":[{"award-number":["62021001"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Graphics Processing Unit (GPU) Cluster Built by Multimedia Computing and Communication (MCC) Laboratory of Information Science and Technology Institution, University of Science and Technology of China"},{"name":"Supercomputing Center of USTC"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Circuits Syst. Video Technol."],"published-print":{"date-parts":[[2024,8]]},"DOI":"10.1109\/tcsvt.2023.3294261","type":"journal-article","created":{"date-parts":[[2023,7,11]],"date-time":"2023-07-11T17:28:48Z","timestamp":1689096528000},"page":"6847-6859","source":"Crossref","is-referenced-by-count":15,"title":["CLIP2GAN: Toward Bridging Text With the Latent Space of GANs"],"prefix":"10.1109","volume":"34","author":[{"given":"Yixuan","family":"Wang","sequence":"first","affiliation":[{"name":"Department of Electronic Engineering and Information Science, CAS Key Laboratory of Technology in Geo-Spatial Information Processing and Application System, University of Science and Technology of China (USTC), Hefei, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1690-9836","authenticated-orcid":false,"given":"Wengang","family":"Zhou","sequence":"additional","affiliation":[{"name":"Department of Electronic Engineering and Information Science, CAS Key Laboratory of Technology in Geo-Spatial Information Processing and Application System, University of Science and Technology of China (USTC), Hefei, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jianmin","family":"Bao","sequence":"additional","affiliation":[{"name":"Microsoft Research Asia, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0037-4147","authenticated-orcid":false,"given":"Weilun","family":"Wang","sequence":"additional","affiliation":[{"name":"Department of Electronic Engineering and Information Science, CAS Key Laboratory of Technology in Geo-Spatial Information Processing and Application System, University of Science and Technology of China (USTC), Hefei, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7163-6263","authenticated-orcid":false,"given":"Li","family":"Li","sequence":"additional","affiliation":[{"name":"Department of Electronic Engineering and Information Science, CAS Key Laboratory of Technology in Geo-Spatial Information Processing and Application System, University of Science and Technology of China (USTC), Hefei, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2188-3028","authenticated-orcid":false,"given":"Houqiang","family":"Li","sequence":"additional","affiliation":[{"name":"Department of Electronic Engineering and Information Science, CAS Key Laboratory of Technology in Geo-Spatial Information Processing and Application System, University of Science and Technology of China (USTC), Hefei, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","first-page":"1","article-title":"Generative adversarial networks","volume-title":"Proc. NeurIPS","author":"GoodFellow"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00232"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2021.3065230"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2020.3001267"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00832"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01114"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/tcsvt.2023.3244786"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2021.3111648"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00453"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00813"},{"key":"ref11","first-page":"852","article-title":"Alias-free generative adversarial networks","volume-title":"Proc. NeurlPS","volume":"34","author":"Karras"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2022.3177238"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00453"},{"issue":"3","key":"ref14","first-page":"4","article-title":"Inverting layers of a large generator","volume-title":"Proc. ICLR Workshop","volume":"2","author":"Bau"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58520-4_35"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2020.3034267"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00926"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00581"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01267"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2022.3222456"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/tmm.2022.3160360"},{"key":"ref22","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"Proc. ICML","author":"Radford"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00152"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.629"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2018.2856256"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00143"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00229"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00089"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01602"},{"key":"ref30","first-page":"19822","article-title":"CogView: Mastering text-to-image generation via transformers","volume-title":"Proc. NeurlPS","volume":"34","author":"Ding"},{"key":"ref31","first-page":"8821","article-title":"Zero-shot text-to-image generation","volume-title":"Proc. ICML","author":"Ramesh"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00595"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00209"},{"key":"ref34","first-page":"1","article-title":"Progressive growing of GANs for improved quality, stability, and variation","volume-title":"Proc. ICLR","author":"Karras"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00821"},{"key":"ref36","article-title":"LSUN: Construction of a large-scale image dataset using deep learning with humans in the loop","author":"Yu","year":"2015","journal-title":"arXiv:1506.03365"},{"key":"ref37","first-page":"5967","article-title":"Fader networks: Manipulating images by sliding attributes","volume-title":"Proc. NeurIPS","volume":"30","author":"Lample"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.19"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00457"},{"key":"ref40","article-title":"Video-to-video synthesis","author":"Wang","year":"2018","journal-title":"arXiv:1808.06601"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2021.08.085"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2020.3015015"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2022.04.126"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.5555\/3045118.3045336"},{"key":"ref45","first-page":"1889","article-title":"Deep fragment embeddings for bidirectional image sentence mapping","volume-title":"Proc. NeurIPS","volume":"27","author":"Karpathy"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298935"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.279"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.10"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.767"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref51","article-title":"BERT: Pre-training of deep bidirectional transformers for language understanding","author":"Devlin","year":"2018","journal-title":"arXiv:1810.04805"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/tmm.2023.3238554"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2020.2972856"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2021.3116416"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2021.3055062"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1145\/3123266.3127905"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.12233"},{"key":"ref58","article-title":"LAFITE: Towards language-free training for text-to-image generation","author":"Zhou","year":"2021","journal-title":"arXiv:2111.13792"},{"key":"ref59","article-title":"FuseDream: Training-free text-to-image generation with improved CLIP+GAN space optimization","author":"Liu","year":"2021","journal-title":"arXiv:2112.01573"},{"key":"ref60","article-title":"GLIDE: Towards photorealistic image generation and editing with text-guided diffusion models","author":"Nichol","year":"2021","journal-title":"arXiv:2112.10741"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"ref62","first-page":"36479","article-title":"Photorealistic text-to-image diffusion models with deep language understanding","volume-title":"Proc. NeurIPS","volume":"35","author":"Saharia"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.608"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00790"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2022.3213662"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01754"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1109\/WACV51458.2022.00350"},{"issue":"1","key":"ref68","first-page":"3","article-title":"Rectifier nonlinearities improve neural network acoustic models","volume-title":"Proc. ICML","volume":"30","author":"Maas"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00068"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1145\/3065386"},{"key":"ref71","first-page":"214","article-title":"Wasserstein generative adversarial networks","volume-title":"Proc. ICML","author":"Arjovsky"},{"key":"ref72","first-page":"5767","article-title":"Improved training of Wasserstein GANs","volume-title":"Proc. NeurIPS","volume":"30","author":"Gulrajani"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00482"},{"key":"ref74","first-page":"2063","article-title":"Controllable text-to-image generation","volume-title":"Proc. NeurIPS","volume":"32","author":"Li"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.425"},{"key":"ref76","article-title":"Adam: A method for stochastic optimization","author":"Kingma","year":"2014","journal-title":"arXiv:1412.6980"},{"key":"ref77","article-title":"GANs trained by a two time-scale update rule converge to a local nash equilibrium","volume-title":"Proc. NeurlPS","volume":"30","author":"Heusel"},{"key":"ref78","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":"ref79","first-page":"12888","article-title":"BLIP: Bootstrapping language-image pre-training for unified vision-language understanding and generation","volume-title":"Proc. ICML","author":"Li"},{"key":"ref80","article-title":"Unsupervised representation learning with deep convolutional generative adversarial networks","author":"Radford","year":"2015","journal-title":"arXiv:1511.06434"},{"key":"ref81","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01764"},{"key":"ref82","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00582"}],"container-title":["IEEE Transactions on Circuits and Systems for Video Technology"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/76\/10634006\/10178013.pdf?arnumber=10178013","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,1,9]],"date-time":"2025-01-09T20:13:11Z","timestamp":1736453591000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10178013\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,8]]},"references-count":82,"journal-issue":{"issue":"8"},"URL":"https:\/\/doi.org\/10.1109\/tcsvt.2023.3294261","relation":{},"ISSN":["1051-8215","1558-2205"],"issn-type":[{"value":"1051-8215","type":"print"},{"value":"1558-2205","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,8]]}}}