{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,5]],"date-time":"2026-06-05T06:02:59Z","timestamp":1780639379082,"version":"3.54.1"},"reference-count":49,"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":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62325206"],"award-info":[{"award-number":["62325206"]}],"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":["62301276"],"award-info":[{"award-number":["62301276"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Key Research and Development Program of Jiangsu Province","award":["BE2023016-4"],"award-info":[{"award-number":["BE2023016-4"]}]},{"name":"Opening Foundation of the State Key Laboratory of Tibetan Intelligence"},{"name":"Key Laboratory of Tibetan Information Processing"},{"DOI":"10.13039\/100010449","name":"Ministry of Education","doi-asserted-by":"publisher","award":["2024-2-003"],"award-info":[{"award-number":["2024-2-003"]}],"id":[{"id":"10.13039\/100010449","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Postgraduate Research & Practice Innovation Program of Jiangsu Province","award":["KYCX23_1033"],"award-info":[{"award-number":["KYCX23_1033"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Multimedia"],"published-print":{"date-parts":[[2026]]},"DOI":"10.1109\/tmm.2026.3654435","type":"journal-article","created":{"date-parts":[[2026,1,20]],"date-time":"2026-01-20T20:40:43Z","timestamp":1768941643000},"page":"3893-3904","source":"Crossref","is-referenced-by-count":0,"title":["FoodDiff: A Collaborative Relationship Perception Framework for Food Image Synthesis Using Diffusion Models"],"prefix":"10.1109","volume":"28","author":[{"ORCID":"https:\/\/orcid.org\/0009-0002-4809-9129","authenticated-orcid":false,"given":"Mengling","family":"Xu","sequence":"first","affiliation":[{"name":"Nanjing University of Posts and Telecommunications, Nanjing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0004-2173-1694","authenticated-orcid":false,"given":"Sisi","family":"You","sequence":"additional","affiliation":[{"name":"Nanjing University of Posts and Telecommunications, Nanjing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5956-831X","authenticated-orcid":false,"given":"Bing-Kun","family":"Bao","sequence":"additional","affiliation":[{"name":"Nanjing University of Posts and Telecommunications, Nanjing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01174"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1145\/3394171.3413636"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00556"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2024.3377540"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2020.2972856"},{"issue":"3","key":"ref6","first-page":"1","article-title":"Improving image generation with better captions","volume-title":"Comput. Sci.","volume":"2","author":"Betker","year":"2023"},{"key":"ref7","first-page":"10144","article-title":"Pixart-$\\alpha$: Fast training of diffusion transformer for photorealistic text-to-image synthesis","volume-title":"Proc. 12th Int. Conf. Learn. Representations","author":"Chen","year":"2024"},{"key":"ref8","first-page":"1060","article-title":"Generative adversarial text to image synthesis","volume-title":"Proc. 33rd Int. Conf. Mach. Learn.","volume":"48","author":"Reed","year":"2016"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1145\/3554738"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"ref11","first-page":"12606","article-title":"Scaling rectified flow transformers for high-resolution image synthesis","volume-title":"Proc. 41st Int. Conf. Mach. Learn.","author":"Esser","year":"2024"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00977"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1145\/3607828.3617796"},{"key":"ref14","article-title":"Foodfusion: A Novel Approach for Food Image Composition via Diffusion Models","author":"Chaohua","year":"2023","journal-title":"IEEE Trans. Multimedia"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-24574-4_28"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.327"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1145\/2964284.2964315"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10599-4_29"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2023.3278992"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2021.3060291"},{"key":"ref21","first-page":"22275","article-title":"SDXL: Improving latent diffusion models for high-resolution image synthesis","volume-title":"Proc. 12th Int. Conf. Learn. Representations","author":"Podell","year":"2024"},{"key":"ref22","article-title":"Latent consistency models: Synthesizing high-resolution images with few-step inference","author":"Luo","year":"2023"},{"key":"ref23","first-page":"12513","article-title":"LORA: Low-rank adaptation of large language models","volume-title":"Proc. 10th Int. Conf. Learn. Representations","author":"Hu","year":"2022"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00673"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00390"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02155"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00191"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2024.111203"},{"key":"ref29","first-page":"1","article-title":"Auto-encoding variational Bayes","volume-title":"Proc. 2nd Int. Conf. Learn. Representations","author":"Kingma","year":"2014"},{"key":"ref30","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"Proc. 38th Int. Conf. Mach. Learn.","volume":"139","author":"Radford","year":"2021"},{"key":"ref31","article-title":"GPT-4 technical report","author":"Achiam","year":"2023"},{"key":"ref32","article-title":"Empirical evaluation of gated recurrent neural networks on sequence modeling","author":"Chung","year":"2014"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.52202\/075280-0700"},{"key":"ref34","first-page":"52604","article-title":"Directly fine-tuning diffusion models on differentiable rewards","volume-title":"Proc. 12th Int. Conf. Learn. Representations","author":"Clark","year":"2024"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.52202\/075280-1594"},{"key":"ref36","first-page":"12888","article-title":"BLIP: Bootstrapping language-image pre-training for unified vision-language understanding and generation","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Li","year":"2022"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2024.3410672"},{"key":"ref38","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":"ref39","first-page":"2234","article-title":"Improved techniques for training GANs","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"29","author":"Salimans"},{"key":"ref40","first-page":"8821","article-title":"Zero-shot text-to-image generation","volume-title":"Proc. 38th Int. Conf. Mach. Learn.","volume":"139","author":"Ramesh","year":"2021"},{"key":"ref41","first-page":"1692","article-title":"One transformer fits all distributions in multi-modal diffusion at scale","volume-title":"Proc. 40th Int. Conf. Mach. Learn.","volume":"202","author":"Bao","year":"2023"},{"key":"ref42","first-page":"31456","article-title":"Lumina-T2x: Scalable flow-based large diffusion transformer for flexible resolution generation","volume-title":"Proc. 13th Int. Conf. Learn. Representations","author":"Gao","year":"2025"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2025.3531907"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.52202\/075280-0410"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72652-1_23"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1145\/3592116"},{"key":"ref47","article-title":"The dawn of LMMs: Preliminary explorations with GPT-4V (ision)","author":"Yang","year":"2023"},{"key":"ref48","first-page":"40652","article-title":"MiniGPT-4: Enhancing vision-language understanding with advanced large language models","volume-title":"Proc. 12th Int. Conf. Learn. Representations","author":"Zhu","year":"2024"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72643-9_22"}],"container-title":["IEEE Transactions on Multimedia"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/6046\/11342315\/11359532.pdf?arnumber=11359532","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,6,5]],"date-time":"2026-06-05T05:22:28Z","timestamp":1780636948000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11359532\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"references-count":49,"URL":"https:\/\/doi.org\/10.1109\/tmm.2026.3654435","relation":{},"ISSN":["1520-9210","1941-0077"],"issn-type":[{"value":"1520-9210","type":"print"},{"value":"1941-0077","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026]]}}}