{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,24]],"date-time":"2026-06-24T16:17:55Z","timestamp":1782317875353,"version":"3.54.5"},"reference-count":66,"publisher":"IEEE","license":[{"start":{"date-parts":[[2026,3,6]],"date-time":"2026-03-06T00:00:00Z","timestamp":1772755200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,3,6]],"date-time":"2026-03-06T00:00:00Z","timestamp":1772755200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2026,3,6]]},"DOI":"10.1109\/wacv61042.2026.00282","type":"proceedings-article","created":{"date-parts":[[2026,5,5]],"date-time":"2026-05-05T19:59:32Z","timestamp":1778011172000},"page":"2879-2889","source":"Crossref","is-referenced-by-count":1,"title":["Conditional Text-to-Image Generation with Reference Guidance"],"prefix":"10.1109","author":[{"given":"Taewook","family":"Kim","sequence":"first","affiliation":[{"name":"Purdue University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ze","family":"Wang","sequence":"additional","affiliation":[{"name":"AMD"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zhengyuan","family":"Yang","sequence":"additional","affiliation":[{"name":"Microsoft"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jiang","family":"Wang","sequence":"additional","affiliation":[{"name":"Microsoft"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Lijuan","family":"Wang","sequence":"additional","affiliation":[{"name":"Microsoft"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zicheng","family":"Liu","sequence":"additional","affiliation":[{"name":"AMD"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Qiang","family":"Qiu","sequence":"additional","affiliation":[{"name":"Purdue University"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","volume-title":"Project gutenberg\u2019s adventures of sherlock holmes"},{"key":"ref7","author":"Arjovsky","year":"2017","journal-title":"Wasserstein generative adversarial networks"},{"key":"ref8","article-title":"Daniel Cohen-Or, and Dani Lischinski","author":"Avrahami","year":"2023","journal-title":"Break-a-scene: Extracting multiple concepts from a single image"},{"key":"ref9","article-title":"ediffi: Text-to-image diffusion models with an ensemble of expert denoisers","author":"Balaji","year":"2022"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20050-2_11"},{"key":"ref11","article-title":"Muse: Text-to-image generation via masked generative transformers","author":"Chang","year":"2023"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.52202\/075280-0410"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/tcsvt.2024.3369757"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICDAR.2019.00252"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr46437.2021.01268"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19784-0_6"},{"key":"ref17","article-title":"An image is worth one word: Personalizing text-to-image generation using textual inversion","volume-title":"ICLR","author":"Gal"},{"key":"ref18","author":"Goodfellow","year":"2014","journal-title":"Generative adversarial nets"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01043"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.322"},{"key":"ref21","author":"Ho","year":"2022","journal-title":"Classifier-free diffusion guidance"},{"key":"ref22","author":"Ho","year":"2020","journal-title":"Denoising diffusion probabilistic models"},{"key":"ref23","article-title":"LoRA: Low-rank adaptation of large language models","volume-title":"ICLR","author":"Hu"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00455"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01786"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1145\/1991996.1992016"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00453"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.52202\/068431-1926"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01461"},{"key":"ref30","author":"Kingma","year":"2013","journal-title":"Auto-encoding variational bayes"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00192"},{"key":"ref32","volume-title":"Flux","year":"2023"},{"key":"ref33","author":"Larsen","year":"2016","journal-title":"Autoencoding beyond pixels using a learned similarity metric"},{"key":"ref34","article-title":"Blip-diffusion: Pretrained subject representation for controllable text-to-image generation and editing","author":"Li","year":"2023","journal-title":"NeurIPS"},{"key":"ref35","article-title":"Blip-diffusion: Pretrained subject representation for controllable text-to-image generation and editing","volume":"36","author":"Li","year":"2024","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref36","doi-asserted-by":"crossref","DOI":"10.1007\/978-3-031-72667-5_8","article-title":"Controlnet ++: Improving conditional controls with efficient consistency feedback","volume-title":"ECCV","author":"Li"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02156"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58621-8_41"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.acl-long.900"},{"key":"ref40","author":"Loshchilov","year":"2017","journal-title":"Decoupled weight decay regularization"},{"key":"ref41","author":"Ma","year":"2023","journal-title":"Glyphdraw: Learning to draw chinese characters in image synthesis models coherently"},{"key":"ref42","author":"Nichol","year":"2022","journal-title":"Glide: Towards photorealistic image generation and editing with text-guided diffusion models"},{"key":"ref43","author":"Podell","year":"2023","journal-title":"Sdxl: Improving latent diffusion models for high-resolution image synthesis"},{"key":"ref44","author":"Radford","year":"2016","journal-title":"Unsupervised representation learning with deep convolutional generative adversarial networks"},{"key":"ref45","article-title":"Learning transferable visual models from natural language supervision","volume-title":"ICLR","author":"Radford"},{"issue":"1","key":"ref46","first-page":"5485","volume":"21","author":"Raffel","year":"2020","journal-title":"Exploring the limits of transfer learning with a unified text-to-text transformer"},{"key":"ref47","author":"Rezende","year":"2015","journal-title":"Variational inference with normalizing flows"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1145\/1991996.1992021"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-24574-4_28"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02155"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.52202\/068431-2643"},{"key":"ref53","author":"Schuhmann","journal-title":"400m: Open dataset of clip-filtered 400 million image-text pairs"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.52202\/068431-1833"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00816"},{"key":"ref56","author":"Sohl-Dickstein","year":"2015","journal-title":"Deep unsupervised learning using nonequilibrium thermodynamics"},{"key":"ref57","author":"Sohn","year":"2015","journal-title":"Learning structured output representation using deep conditional generative models"},{"key":"ref58","article-title":"Denoising diffusion implicit models","volume-title":"ICLR","author":"Song"},{"key":"ref59","article-title":"Score-based generative modeling through stochastic differential equations","volume-title":"ICLR","author":"Song"},{"key":"ref60","article-title":"Anytext: Multilingual visual text generation and editing","volume-title":"ICLR","author":"Tuo"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.5220\/0006614602840292"},{"key":"ref62","volume":"30","author":"Oord","year":"2017","journal-title":"Neural discrete representation learning"},{"key":"ref63","article-title":"Ms-diffusion: Multi-subject zero-shot image personalization with layout guidance","volume-title":"ICLR","author":"Wang"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02162"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01461"},{"key":"ref66","author":"Xue","year":"2024","journal-title":"Raphael: Text-to-image generation via large mixture of diffusion paths"},{"key":"ref67","author":"Yang","year":"2024","journal-title":"Glyphcontrol: Glyph conditional control for visual text generation"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01369"},{"key":"ref69","author":"Ye","year":"2023","journal-title":"Ipadapter: Text compatible image prompt adapter for text-to-image diffusion models"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01854"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00355"}],"event":{"name":"2026 IEEE\/CVF Winter Conference on Applications of Computer Vision (WACV)","location":"Tucson, AZ, USA","start":{"date-parts":[[2026,3,6]]},"end":{"date-parts":[[2026,3,10]]}},"container-title":["2026 IEEE\/CVF Winter Conference on Applications of Computer Vision (WACV)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11491838\/11491925\/11492260.pdf?arnumber=11492260","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,6]],"date-time":"2026-05-06T06:30:11Z","timestamp":1778049011000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11492260\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,3,6]]},"references-count":66,"URL":"https:\/\/doi.org\/10.1109\/wacv61042.2026.00282","relation":{},"subject":[],"published":{"date-parts":[[2026,3,6]]}}}