{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,6]],"date-time":"2026-05-06T06:20:26Z","timestamp":1778048426102,"version":"3.51.4"},"reference-count":43,"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\/wacv61042.2026.00541","type":"proceedings-article","created":{"date-parts":[[2026,5,5]],"date-time":"2026-05-05T19:59:32Z","timestamp":1778011172000},"page":"5581-5590","source":"Crossref","is-referenced-by-count":0,"title":["Food Image Generation on Multi-Noun Categories"],"prefix":"10.1109","author":[{"given":"Xinyue","family":"Pan","sequence":"first","affiliation":[{"name":"Purdue University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yuhao","family":"Chen","sequence":"additional","affiliation":[{"name":"University of Waterloo"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jiangpeng","family":"He","sequence":"additional","affiliation":[{"name":"Purdue University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Fengqing","family":"Zhu","sequence":"additional","affiliation":[{"name":"Purdue University"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.52202\/075280-2571"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.3390\/nu9010086"},{"key":"ref3","article-title":"Scaling rectified flow transformers for high-resolution image synthesis","volume-title":"Forty-first international conference on machine learning","author":"Esser"},{"key":"ref4","article-title":"Trainingfree structured diffusion guidance for compositional text-toimage synthesis","volume-title":"The Eleventh International Conference on Learning Representations","author":"Feng"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1145\/3607828.3617796"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/tmm.2025.3632640"},{"key":"ref7","article-title":"Prompt-to-prompt image editing with cross-attention control","volume-title":"Internal Conference on Learning Representation","author":"Hertz"},{"key":"ref8","article-title":"Gans trained by a two time-scale update rule converge to a local nash equilibrium","author":"Heusel","year":"2017","journal-title":"Advances in neural information processing systems"},{"key":"ref9","article-title":"Denoising diffusion probabilistic models","volume-title":"Proceedings of the 34th International Conference on Neural Information Processing Systems","author":"Ho"},{"key":"ref10","article-title":"Classifier-free diffusion guidance","author":"Ho","year":"2022","journal-title":"NeurIPS 2021 Workshop on Deep Generative Models and Downstream Applications"},{"key":"ref11","article-title":"LoRA: Low-rank adaptation of large language models","volume-title":"International Conference on Learning Representations","author":"Hu"},{"key":"ref12","article-title":"Gpt-4o system card","author":"Hurst","year":"2024"},{"key":"ref13","article-title":"Yolo by ultralytics","author":"Jocher","year":"2023"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2020.2970919"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-16199-0_1"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1145\/3627673.3679885"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00763"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.3390\/app14188347"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-68821-9_47"},{"key":"ref20","article-title":"Glide: Towards photorealistic image generation and editing with text-guided diffusion models","volume-title":"Proceedings of the 39 th International Conference on Machine Learning","author":"Nichol"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00387"},{"key":"ref22","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"International conference on machine learning","author":"Radford"},{"issue":"140","key":"ref23","first-page":"1","article-title":"Exploring the limits of transfer learning with a unified text-to-text transformer","volume":"21","author":"Raffel","year":"2020","journal-title":"Journal of Machine Learning Research"},{"key":"ref24","first-page":"3","article-title":"Hierarchical text-conditional image generation with clip latents","author":"Ramesh","year":"2022"},{"key":"ref25","article-title":"Linguistic binding in diffusion models: Enhancing attribute correspondence through attention map alignment","author":"Rassin","year":"2024","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref26","first-page":"1278","article-title":"Stochastic backpropagation and approximate inference in deep generative models","volume-title":"International conference on machine learning","author":"Rezende"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02155"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.52202\/068431-2643"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.52202\/068431-1833"},{"key":"ref31","article-title":"Box it to bind it: Unified layout control and attribute binding in t2i diffusion models","author":"Taghipour","year":"2024"},{"key":"ref32","article-title":"Object-attribute binding in textto-image generation: Evaluation and control","author":"Trusca","year":"2024"},{"key":"ref33","article-title":"Archef: An ios-based augmented reality cooking assistant powered by multimodal gemini llm","author":"Vir","year":"2024"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00596"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00397"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3547821"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1145\/3552484.3555751"},{"key":"ref38","article-title":"FILIP: Fine-grained interactive language-image pre-training","volume-title":"International Conference on Learning Representations","author":"Yao"},{"key":"ref39","article-title":"Towards understanding the working mechanism of text-to-image diffusion model","volume-title":"The Thirty-eighth Annual Conference on Neural Information Processing Systems","author":"Yi"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1145\/3730588"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00355"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02154"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3611863"}],"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\/11492241.pdf?arnumber=11492241","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,6]],"date-time":"2026-05-06T06:05:05Z","timestamp":1778047505000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11492241\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,3,6]]},"references-count":43,"URL":"https:\/\/doi.org\/10.1109\/wacv61042.2026.00541","relation":{},"subject":[],"published":{"date-parts":[[2026,3,6]]}}}