{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,5]],"date-time":"2026-06-05T20:14:44Z","timestamp":1780690484026,"version":"3.54.1"},"reference-count":54,"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":["62471168"],"award-info":[{"award-number":["62471168"]}],"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":["62422204"],"award-info":[{"award-number":["62422204"]}],"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":["61802100"],"award-info":[{"award-number":["61802100"]}],"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":["62372147"],"award-info":[{"award-number":["62372147"]}],"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":["U21B2040"],"award-info":[{"award-number":["U21B2040"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Zhejiang Provincial Natural Science Foundation of China","award":["LDT23F02025F02"],"award-info":[{"award-number":["LDT23F02025F02"]}]},{"name":"Zhejiang Provincial Natural Science Foundation of China","award":["LY21F020019"],"award-info":[{"award-number":["LY21F020019"]}]},{"DOI":"10.13039\/100022963","name":"Key Research and Development Program of Zhejiang Province","doi-asserted-by":"publisher","award":["2025C01026"],"award-info":[{"award-number":["2025C01026"]}],"id":[{"id":"10.13039\/100022963","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Zhejiang Province Leading Geese Science and Technology Program","award":["2025C02155"],"award-info":[{"award-number":["2025C02155"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Multimedia"],"published-print":{"date-parts":[[2026]]},"DOI":"10.1109\/tmm.2026.3668676","type":"journal-article","created":{"date-parts":[[2026,2,27]],"date-time":"2026-02-27T20:50:03Z","timestamp":1772225403000},"page":"4169-4180","source":"Crossref","is-referenced-by-count":0,"title":["Compositional Text-to-Image Synthesis With Training-Free Layout-Guided Diffusion"],"prefix":"10.1109","volume":"28","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-2876-1771","authenticated-orcid":false,"given":"Xiaoling","family":"Gu","sequence":"first","affiliation":[{"name":"Zhejiang Key Laboratory of Space Information Sensing and Transmission, Hangzhou Dianzi University, Hangzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Lingwei","family":"Luo","sequence":"additional","affiliation":[{"name":"Zhejiang Key Laboratory of Space Information Sensing and Transmission, Hangzhou Dianzi University, Hangzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Shengqi","family":"Wu","sequence":"additional","affiliation":[{"name":"Zhejiang Key Laboratory of Space Information Sensing and Transmission, Hangzhou Dianzi University, Hangzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2103-5037","authenticated-orcid":false,"given":"Zizhao","family":"Wu","sequence":"additional","affiliation":[{"name":"Zhejiang Key Laboratory of Space Information Sensing and Transmission, Hangzhou Dianzi University, Hangzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9813-7037","authenticated-orcid":false,"given":"Zhenzhong","family":"Kuang","sequence":"additional","affiliation":[{"name":"Zhejiang Key Laboratory of Space Information Sensing and Transmission, Hangzhou Dianzi University, Hangzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8407-1137","authenticated-orcid":false,"given":"Zhou","family":"Yu","sequence":"additional","affiliation":[{"name":"Zhejiang Key Laboratory of Space Information Sensing and Transmission, Hangzhou Dianzi University, Hangzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2023.3238554"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2024.3358086"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2023.3266607"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2023.3278992"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2025.128178"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2020.3009500"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"ref8","first-page":"8162","article-title":"Improved denoising diffusion probabilistic models","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Nichol","year":"2021"},{"key":"ref9","first-page":"8780","article-title":"Denoising diffusion implicit models","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Song","year":"2021"},{"key":"ref10","first-page":"8780","article-title":"Diffusion models beat GANs on image synthesis","volume-title":"Proc. NeurIPS","author":"Dhariwal","year":"2021"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00191"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1145\/3592116"},{"key":"ref13","first-page":"3536","article-title":"Linguistic binding in diffusion models: Enhancing attribute correspondence through attention map alignment","volume-title":"Proc. NeurIPS","author":"Rassin","year":"2023"},{"key":"ref14","first-page":"289","article-title":"Training-free structured diffusion guidance for compositional text-to-image synthesis","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Feng","year":"2023"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/WACV56688.2023.00037"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02156"},{"key":"ref17","first-page":"16784","article-title":"GLIDE: Towards photorealistic image generation and editing with text-guided diffusion models","volume-title":"Proc. Proc. Int. Conf. Mach. Learn.","volume":"162","author":"Nichol","year":"2022"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00355"},{"key":"ref19","article-title":"Hierarchical text-conditional image generation with clip latents","author":"Ramesh","year":"2022"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.52202\/068431-2643"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01762"},{"key":"ref22","first-page":"22500","article-title":"Score-based generative modeling through stochastic differential equations","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Song","year":"2021"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02155"},{"key":"ref24","article-title":"eDiff-I: Text-to-image diffusion models with an ensemble of expert denoisers","author":"Balaji","year":"2022"},{"key":"ref25","article-title":"Interactive data synthesis for systematic vision adaptation via llms-aigcs collaboration","author":"Yu","year":"2023"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW59228.2023.00091"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00708"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i6.28364"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00694"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.02107"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00714"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19790-1_26"},{"key":"ref33","article-title":"Llm-grounded diffusion: Enhancing prompt understanding of text-to-image diffusion models with large language models","volume":"2024","author":"Lian","year":"2024","journal-title":"Trans. Mach. Learn. Res."},{"key":"ref34","first-page":"9380","article-title":"Divide & bind your attention for improved generative semantic nursing","volume-title":"Proc. Brit. Mach. Vis. Conf.","author":"Li","year":"2023"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00896"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00860"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00633"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00852"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00605"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00817"},{"key":"ref41","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"Proc. Proc. Int. Conf. Mach. Learn.","volume":"139","author":"Radford","year":"2021"},{"key":"ref42","first-page":"3053","article-title":"Chain of code: Reasoning with a language model-augmented code emulator","volume-title":"Proc. Proc. Int. Conf. Mach. Learn.","author":"Li","year":"2024"},{"key":"ref43","article-title":"","author":"Chen","year":"2023"},{"key":"ref44","article-title":"FLUX","author":"Labs","year":"2024"},{"key":"ref45","article-title":"SD3.5","volume-title":"GitHub repository","year":"2024"},{"key":"ref46","first-page":"20041","article-title":"HRS-bench: Holistic, reliable and acalable benchmark for text-to-image models","volume-title":"Proc. IEEE\/CVF Int. Conf. Comput. Vis.","author":"Bakr","year":"2023"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.52202\/075280-3443"},{"key":"ref48","first-page":"12888","article-title":"Blip: Bootstrapping language-image pre-training for unified vision-language understanding and generation","volume-title":"Proc. Proc. Int. Conf. Mach. Learn.","author":"Li","year":"2022"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00742"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.emnlp-main.595"},{"key":"ref51","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"Proc. Proc. Int. Conf. Mach. Learn.","author":"Radford","year":"2021"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.52202\/075280-3101"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2025.111359"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2025.3531907"}],"container-title":["IEEE Transactions on Multimedia"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/6046\/11342315\/11417256.pdf?arnumber=11417256","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,6,5]],"date-time":"2026-06-05T19:39:53Z","timestamp":1780688393000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11417256\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"references-count":54,"URL":"https:\/\/doi.org\/10.1109\/tmm.2026.3668676","relation":{},"ISSN":["1520-9210","1941-0077"],"issn-type":[{"value":"1520-9210","type":"print"},{"value":"1941-0077","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026]]}}}