{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,13]],"date-time":"2025-11-13T18:55:06Z","timestamp":1763060106979,"version":"3.45.0"},"reference-count":48,"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":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["U22A2096","62036007"],"award-info":[{"award-number":["U22A2096","62036007"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Scientific and Technological Innovation Teams in Shaanxi Province","award":["2025RS-CXTD-011"],"award-info":[{"award-number":["2025RS-CXTD-011"]}]},{"name":"Shaanxi Province Core Technology Research and Development Project","award":["2024QY2-GJHX-11"],"award-info":[{"award-number":["2024QY2-GJHX-11"]}]},{"name":"Young Talent Fund of Association for Science and Technology, Shaanxi, China","award":["20230121"],"award-info":[{"award-number":["20230121"]}]},{"name":"CCF-Baidu Open Fund"},{"DOI":"10.13039\/501100012226","name":"Fundamental Research Funds for the Central Universities","doi-asserted-by":"publisher","award":["QTZX23042"],"award-info":[{"award-number":["QTZX23042"]}],"id":[{"id":"10.13039\/501100012226","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.2025.3607683","type":"journal-article","created":{"date-parts":[[2025,9,9]],"date-time":"2025-09-09T17:33:09Z","timestamp":1757439189000},"page":"8644-8655","source":"Crossref","is-referenced-by-count":0,"title":["Foodfusion: A Novel Approach for Food Image Composition via Diffusion Models"],"prefix":"10.1109","volume":"27","author":[{"given":"Chaohua","family":"Shi","sequence":"first","affiliation":[{"name":"State Key Laboratory of Integrated Services Networks (ISN), School of Telecommunications Engineering, Xidian University, Xi’an, Shaanxi, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xuan","family":"Wang","sequence":"additional","affiliation":[{"name":"Meituan Inc., Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Si","family":"Shi","sequence":"additional","affiliation":[{"name":"State Key Laboratory of Integrated Services Networks (ISN), School of Telecommunications Engineering, Xidian University, Xi’an, Shaanxi, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xule","family":"Wang","sequence":"additional","affiliation":[{"name":"Meituan Inc., Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4179-7701","authenticated-orcid":false,"given":"Mingrui","family":"Zhu","sequence":"additional","affiliation":[{"name":"State Key Laboratory of Integrated Services Networks (ISN), School of Telecommunications Engineering, Xidian University, Xi’an, Shaanxi, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4695-6134","authenticated-orcid":false,"given":"Nannan","family":"Wang","sequence":"additional","affiliation":[{"name":"State Key Laboratory of Integrated Services Networks (ISN), School of Telecommunications Engineering, Xidian University, Xi’an, Shaanxi, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7985-0037","authenticated-orcid":false,"given":"Xinbo","family":"Gao","sequence":"additional","affiliation":[{"name":"Chongqing Key Laboratory of Image Cognition, Chongqing University of Posts and Telecommunications, Chongqing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"doi-asserted-by":"publisher","key":"ref1","DOI":"10.1109\/TPAMI.2023.3237871"},{"doi-asserted-by":"publisher","key":"ref2","DOI":"10.1007\/978-3-319-10599-4_29"},{"doi-asserted-by":"publisher","key":"ref3","DOI":"10.1145\/2964284.2964315"},{"doi-asserted-by":"publisher","key":"ref4","DOI":"10.1145\/3394171.3414031"},{"doi-asserted-by":"publisher","key":"ref5","DOI":"10.1109\/TMM.2021.3083109"},{"year":"2023","author":"Ye","article-title":"IP-adapter: Text compatible image prompt adapter for text-to-image diffusion models","key":"ref6"},{"doi-asserted-by":"publisher","key":"ref7","DOI":"10.1007\/978-3-030-58601-0_34"},{"doi-asserted-by":"publisher","key":"ref8","DOI":"10.1109\/WACV45572.2020.9093632"},{"doi-asserted-by":"publisher","key":"ref9","DOI":"10.1109\/CVPR42600.2020.00842"},{"year":"2021","author":"Niu","article-title":"Making images real again: A comprehensive survey on deep image composition","key":"ref10"},{"key":"ref11","first-page":"8162","article-title":"Improved denoising diffusion probabilistic models","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Nichol","year":"2021"},{"doi-asserted-by":"publisher","key":"ref12","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"ref13","first-page":"1","article-title":"SDXL: Improving latent diffusion models for high-resolution image synthesis","volume-title":"Proc. Twelfth Int. Conf. Learn. Representations","author":"Podell","year":"2023"},{"year":"2022","author":"Ramesh","article-title":"Hierarchical text-conditional image generation with clip latents","key":"ref14"},{"doi-asserted-by":"publisher","key":"ref15","DOI":"10.1145\/3592116"},{"doi-asserted-by":"publisher","key":"ref16","DOI":"10.1109\/CVPRW63382.2024.00738"},{"doi-asserted-by":"publisher","key":"ref17","DOI":"10.1609\/aaai.v38i5.28204"},{"doi-asserted-by":"publisher","key":"ref18","DOI":"10.1609\/aaai.v38i5.28226"},{"doi-asserted-by":"publisher","key":"ref19","DOI":"10.1109\/TMM.2024.3382484"},{"doi-asserted-by":"publisher","key":"ref20","DOI":"10.1109\/TMM.2024.3359769"},{"doi-asserted-by":"publisher","key":"ref21","DOI":"10.1109\/CVPR52729.2023.02155"},{"doi-asserted-by":"publisher","key":"ref22","DOI":"10.1109\/CVPR52729.2023.01763"},{"key":"ref23","first-page":"1","article-title":"Training-free structured diffusion guidance for compositional text-to-image synthesis","volume-title":"Proc. Eleventh Int. Conf. Learn. Representations","author":"Feng","year":"2023"},{"doi-asserted-by":"publisher","key":"ref24","DOI":"10.1109\/ICCV51070.2023.00218"},{"year":"2022","author":"Song","article-title":"Objectstitch: Generative object compositing","key":"ref25"},{"doi-asserted-by":"publisher","key":"ref26","DOI":"10.1007\/978-3-030-01258-8_23"},{"doi-asserted-by":"publisher","key":"ref27","DOI":"10.1109\/ICCVW.2019.00386"},{"doi-asserted-by":"publisher","key":"ref28","DOI":"10.1145\/3343031.3350944"},{"doi-asserted-by":"publisher","key":"ref29","DOI":"10.1007\/978-3-031-20071-7_18"},{"doi-asserted-by":"publisher","key":"ref30","DOI":"10.1109\/CVPR52729.2023.00571"},{"doi-asserted-by":"publisher","key":"ref31","DOI":"10.1109\/ICCV51070.2023.00371"},{"doi-asserted-by":"publisher","key":"ref32","DOI":"10.1007\/978-3-031-19797-0_3"},{"year":"2023","author":"Shi","article-title":"Zero123: A single image to consistent multi-view diffusion base model","key":"ref33"},{"doi-asserted-by":"publisher","key":"ref34","DOI":"10.1007\/978-3-319-46448-0_40"},{"doi-asserted-by":"publisher","key":"ref35","DOI":"10.1109\/TMM.2021.3088639"},{"doi-asserted-by":"publisher","key":"ref36","DOI":"10.1109\/CVPR52688.2022.00754"},{"doi-asserted-by":"publisher","key":"ref37","DOI":"10.1109\/wacv57701.2024.00537"},{"doi-asserted-by":"publisher","key":"ref38","DOI":"10.1145\/3721238.3730702"},{"doi-asserted-by":"publisher","key":"ref39","DOI":"10.1109\/CVPR52733.2024.00998"},{"key":"ref40","first-page":"6840","article-title":"Denoising diffusion probabilistic models","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"33","author":"Ho","year":"2020"},{"key":"ref41","first-page":"1","article-title":"Denoising diffusion implicit models","volume-title":"Proc. Ninth Int. Conf. Learn. Representations","author":"Song","year":"2021"},{"key":"ref42","first-page":"1","article-title":"BERT: Pre-training of deep bidirectional transformers for language understanding","volume-title":"Proc. Conf. North Amer. Chapter Assoc. Comput. Linguistics: Human Lang. Technologies","volume":"1","author":"Devlin","year":"2019"},{"key":"ref43","first-page":"25278","article-title":"LAION-5B: An open large-scale dataset for training next generation image-text models","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"35","author":"Schuhmann","year":"2022"},{"key":"ref44","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Radford","year":"2021"},{"doi-asserted-by":"publisher","key":"ref45","DOI":"10.1109\/ICCV51070.2023.00355"},{"doi-asserted-by":"publisher","key":"ref46","DOI":"10.1109\/CVPR52688.2022.01767"},{"doi-asserted-by":"publisher","key":"ref47","DOI":"10.1145\/3592450"},{"doi-asserted-by":"publisher","key":"ref48","DOI":"10.1145\/3658150"}],"container-title":["IEEE Transactions on Multimedia"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/6046\/10844992\/11153867.pdf?arnumber=11153867","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,11,13]],"date-time":"2025-11-13T18:44:30Z","timestamp":1763059470000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11153867\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025]]},"references-count":48,"URL":"https:\/\/doi.org\/10.1109\/tmm.2025.3607683","relation":{},"ISSN":["1520-9210","1941-0077"],"issn-type":[{"type":"print","value":"1520-9210"},{"type":"electronic","value":"1941-0077"}],"subject":[],"published":{"date-parts":[[2025]]}}}