{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,7]],"date-time":"2026-08-07T14:36:49Z","timestamp":1786113409988,"version":"build-2736575974"},"reference-count":48,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"TCL Science and Technology Innovation Fund","award":["20231752"],"award-info":[{"award-number":["20231752"]}]},{"name":"Guangdong Provincial Science and Technology Program","award":["2025A0505080003"],"award-info":[{"award-number":["2025A0505080003"]}]},{"DOI":"10.13039\/501100021171","name":"Basic and Applied Basic Research Foundation of Guangdong Province","doi-asserted-by":"crossref","award":["2024A1515011437"],"award-info":[{"award-number":["2024A1515011437"]}],"id":[{"id":"10.13039\/501100021171","id-type":"DOI","asserted-by":"crossref"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Multimedia"],"published-print":{"date-parts":[[2026]]},"DOI":"10.1109\/tmm.2026.3668641","type":"journal-article","created":{"date-parts":[[2026,2,27]],"date-time":"2026-02-27T20:50:03Z","timestamp":1772225403000},"page":"6593-6604","source":"Crossref","is-referenced-by-count":0,"title":["ClassBooth: Boost Class Semantics With Bidirectional Feature Fusion in Text-to-Image Diffusion Models"],"prefix":"10.1109","volume":"28","author":[{"given":"Yunfei","family":"Zhang","sequence":"first","affiliation":[{"name":"South China University of Technology"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jie","family":"Wang","sequence":"additional","affiliation":[{"name":"South China University of Technology","place":["Guangzhou, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9136-195X","authenticated-orcid":false,"given":"Yan","family":"Huang","sequence":"additional","affiliation":[{"name":"South China University of Technology","place":["Guangzhou, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9708-8939","authenticated-orcid":false,"given":"Tianyi","family":"Chen","sequence":"additional","affiliation":[{"name":"City University of Hong Kong","place":["Kowloon, Hong Kong"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1530-7529","authenticated-orcid":false,"given":"Hau-San","family":"Wong","sequence":"additional","affiliation":[{"name":"City University of Hong Kong","place":["Kowloon, Hong Kong"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4022-0852","authenticated-orcid":false,"given":"Si","family":"Wu","sequence":"additional","affiliation":[{"name":"South China University of Technology","place":["Guangzhou, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1145\/3592116"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02155"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00816"},{"key":"ref4","first-page":"1069","article-title":"An image is worth one word: Personalizing text-to-image generation using textual inversion","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Gal","year":"2023"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.02077"},{"key":"ref6","first-page":"8821","article-title":"Zero-shot text-to-image generation","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Ramesh","year":"2021"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2025.3535343"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.5555\/2969033.2969125"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00813"},{"key":"ref10","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":"ref11","first-page":"217","article-title":"Learning what and where to draw","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"29","author":"Reed","year":"2016"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01602"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00976"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00229"},{"key":"ref15","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":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2025.3535304"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2023.3278992"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19784-0_6"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.52202\/068431-1229"},{"key":"ref20","article-title":"Scaling autoregressive models for content-rich text-to-image generation","author":"Yu","year":"2022","journal-title":"Trans. Mach. Learn. Res."},{"key":"ref21","first-page":"6840","article-title":"Denoising diffusion probabilistic models","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"33","author":"Ho","year":"2020"},{"key":"ref22","first-page":"14205","article-title":"Denoising diffusion implicit models","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Song","year":"2021"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"ref24","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":"ref25","article-title":"Hierarchical text-conditional image generation with clip latents","author":"Ramesh","year":"2022"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.52202\/068431-2643"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02171"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2010.11929"},{"key":"ref29","first-page":"13753","article-title":"Composer: Creative and controllable image synthesis with composable conditions","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Huang","year":"2023"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00355"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02156"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.52202\/075280-0491"},{"key":"ref33","article-title":"IP-Adapter: Text compatible image prompt adapter for text-to-image diffusion models","author":"Ye","year":"2023"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i5.28226"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2024.3399075"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2024.3415357"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00387"},{"key":"ref38","article-title":"The Caltech-UCSD Birds-200-2011 dataset","author":"Wah","year":"2011"},{"key":"ref39","first-page":"1","article-title":"Novel datasets for fine-grained image categorization","volume-title":"Proc. 1st Workshop Fine Grained Vis. Categorization","author":"Khosla","year":"2011"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/ICVGIP.2008.47"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00453"},{"key":"ref43","first-page":"6626","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","year":"2017"},{"key":"ref44","first-page":"742","article-title":"BLIP-2: Bootstrapping language-image pre-training with frozen image encoders and large language models","volume-title":"Proc. Int. Conf. Mach. Learn.","volume":"19","author":"Li","year":"2023"},{"key":"ref45","first-page":"653","article-title":"PPR10 k: A large-scale portrait photo retouching dataset with human-region mask and group-level consistency","volume-title":"Proc. IEEE\/CVF Conf. Comput. Vis. Pattern Recognit.","author":"Liang","year":"2021"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00714"},{"key":"ref47","first-page":"46618","article-title":"ClassDiffusion: More aligned personalization tuning with explicit class guidance","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Huang","year":"2025"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.01711"}],"container-title":["IEEE Transactions on Multimedia"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/6046\/11342315\/11417238.pdf?arnumber=11417238","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,8,5]],"date-time":"2026-08-05T19:07:26Z","timestamp":1785956846000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11417238\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"references-count":48,"URL":"https:\/\/doi.org\/10.1109\/tmm.2026.3668641","relation":{},"ISSN":["1520-9210","1941-0077"],"issn-type":[{"value":"1520-9210","type":"print"},{"value":"1941-0077","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026]]}}}