{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,3]],"date-time":"2026-03-03T05:07:59Z","timestamp":1772514479748,"version":"3.50.1"},"reference-count":59,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"111 Proiect","award":["B16009"],"award-info":[{"award-number":["B16009"]}]},{"DOI":"10.13039\/501100005047","name":"Natural Science Foundation of Liaoning Province","doi-asserted-by":"publisher","award":["2022-MS-123"],"award-info":[{"award-number":["2022-MS-123"]}],"id":[{"id":"10.13039\/501100005047","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61402092"],"award-info":[{"award-number":["61402092"]}],"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":["61374178"],"award-info":[{"award-number":["61374178"]}],"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":["61603182"],"award-info":[{"award-number":["61603182"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Multimedia"],"published-print":{"date-parts":[[2025]]},"DOI":"10.1109\/tmm.2025.3535304","type":"journal-article","created":{"date-parts":[[2025,1,27]],"date-time":"2025-01-27T18:54:42Z","timestamp":1738004082000},"page":"3702-3715","source":"Crossref","is-referenced-by-count":8,"title":["CLIP-GAN: Stacking CLIPs and GAN for Efficient and Controllable Text-to-Image Synthesis"],"prefix":"10.1109","volume":"27","author":[{"ORCID":"https:\/\/orcid.org\/0009-0002-0283-7640","authenticated-orcid":false,"given":"Yingli","family":"Hou","sequence":"first","affiliation":[{"name":"Software College, Northeastern University, Shenyang, China"}]},{"ORCID":"https:\/\/orcid.org\/0009-0000-7993-2430","authenticated-orcid":false,"given":"Wei","family":"Zhang","sequence":"additional","affiliation":[{"name":"Software College, Northeastern University, Shenyang, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3172-7600","authenticated-orcid":false,"given":"Zhiliang","family":"Zhu","sequence":"additional","affiliation":[{"name":"Software College, Northeastern University, Shenyang, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8024-1781","authenticated-orcid":false,"given":"Hai","family":"Yu","sequence":"additional","affiliation":[{"name":"Software College, Northeastern University, Shenyang, China"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01769"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19784-0_6"},{"key":"ref3","article-title":"Hierarchical text-conditional image generation with clip latents","author":"Ramesh","year":"2022"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"ref5","first-page":"36479","article-title":"Photorealistic text-to-image diffusion models with deep language understanding","volume-title":"Proc. Annu. Conf. Neural Inf. Process. Syst.","author":"Saharia","year":"2022"},{"key":"ref6","article-title":"Scaling autoregressive models for content-rich text-to-image generation","author":"Yu","year":"2022"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2021.3060291"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01738"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00595"},{"key":"ref10","first-page":"4055","article-title":"MUSE: Text-to-image generation via masked generative transformers","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Chang","year":"2023"},{"key":"ref11","first-page":"19822","article-title":"Cogview: Mastering text-to-image generation via transformers","volume-title":"Proc. Annu. Conf. Neural Inf. Process. Syst.","author":"Ding","year":"2021"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01245"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2020.2972856"},{"key":"ref14","article-title":"Clip-GEN: Language-free training of a text-to-image generator with clip","author":"Wang","year":"2022"},{"key":"ref15","first-page":"6594","article-title":"Modulating early visual processing by language","volume-title":"Proc. Annu. Conf. Neural Inf. Process. Syst.","author":"Vries","year":"2021"},{"key":"ref16","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Radford","year":"2021"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2010.11929"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01602"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/tmm.2023.3238554"},{"key":"ref20","article-title":"The Caltech-UCSD birds-200-2011 dataset","author":"Wah","year":"2011"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"ref22","article-title":"ADAM: A method for stochastic optimization","author":"Kingma","year":"2014"},{"key":"ref23","first-page":"6626","article-title":"GANs trained by a two time-scale update rule converge to a local nash equilibrium","volume-title":"Proc. Annu. Conf. Neural Inf. Process. Syst.","author":"Heusel","year":"2017"},{"key":"ref24","first-page":"8821","article-title":"Zero-shot text-to-image generation","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Ramesh","year":"2021"},{"key":"ref25","first-page":"16890","article-title":"Cogview2: Faster and better text-to-image generation via hierarchical transformers","volume-title":"Proc. Annu. Conf. Neural Inf. Process. Syst.","author":"Ding","year":"2022"},{"key":"ref26","first-page":"16784","article-title":"GLIDE: Towards photorealistic image generation and editing with text-guided diffusion models","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Nichol","year":"2022"},{"key":"ref27","first-page":"1691","article-title":"Generative pretraining from pixels","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Chen","year":"2020"},{"key":"ref28","article-title":"eDiff-I: Text-to-image diffusion models with an ensemble of expert denoisers","author":"Balaji","year":"2022"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01366"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01043"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00089"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01370"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00143"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1810.04805"},{"key":"ref35","first-page":"4904","article-title":"Scaling up visual and vision-language representation learning with noisy text supervision","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Jia","year":"2021"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.5555\/2969033.2969125"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.2106.12423"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00813"},{"key":"ref39","first-page":"30105","article-title":"StyleGAN-T: Unlocking the power of GANs for fast large-scale text-to-image synthesis","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Sauer","year":"2023"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.279"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00686"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00904"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00688"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2022.07.054"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-023-01891-x"},{"key":"ref47","first-page":"7354","article-title":"Self-attention generative adversarial networks","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Zhang","year":"2019"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.167"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00229"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr46437.2021.00229"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01766"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00200"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00889"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01866"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01372"},{"key":"ref56","first-page":"15903","article-title":"ImageReward: Learning and evaluating human preferences for text-to-image generation","volume-title":"Proc. Annu. Conf. Neural Inf. Process. Syst.","author":"Xu","year":"2023"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00976"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00694"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19827-4_41"}],"container-title":["IEEE Transactions on Multimedia"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/6046\/10844992\/10855452.pdf?arnumber=10855452","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,12]],"date-time":"2025-06-12T17:43:48Z","timestamp":1749750228000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10855452\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025]]},"references-count":59,"URL":"https:\/\/doi.org\/10.1109\/tmm.2025.3535304","relation":{},"ISSN":["1520-9210","1941-0077"],"issn-type":[{"value":"1520-9210","type":"print"},{"value":"1941-0077","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025]]}}}