{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,16]],"date-time":"2026-06-16T04:42:36Z","timestamp":1781584956740,"version":"3.54.5"},"reference-count":80,"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":[{"name":"Australian Research Council (ARC) Discovery Projects","award":["DP220102197"],"award-info":[{"award-number":["DP220102197"]}]},{"name":"Australian Research Council (ARC) Discovery Projects","award":["DP210101682"],"award-info":[{"award-number":["DP210101682"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Multimedia"],"published-print":{"date-parts":[[2025]]},"DOI":"10.1109\/tmm.2025.3607759","type":"journal-article","created":{"date-parts":[[2025,9,9]],"date-time":"2025-09-09T17:33:09Z","timestamp":1757439189000},"page":"8393-8407","source":"Crossref","is-referenced-by-count":1,"title":["Box It to Bind It: Unified Layout Control and Attribute Binding in Text-to-Image Diffusion Models"],"prefix":"10.1109","volume":"27","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-1950-5143","authenticated-orcid":false,"given":"Ashkan","family":"Taghipour","sequence":"first","affiliation":[{"name":"Department of Computer Science and Software Engineering, The University of Western Australia, Crawley, WA, Australia"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6423-6475","authenticated-orcid":false,"given":"Morteza","family":"Ghahremani","sequence":"additional","affiliation":[{"name":"Munich Center for Machine Learning (MCML), München, Germany"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6603-3257","authenticated-orcid":false,"given":"Mohammed","family":"Bennamoun","sequence":"additional","affiliation":[{"name":"Department of Computer Science and Software Engineering, The University of Western Australia, Crawley, WA, Australia"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9542-759X","authenticated-orcid":false,"given":"Aref Miri","family":"Rekavandi","sequence":"additional","affiliation":[{"name":"University of Melbourne, Parkville, VIC, Australia"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4758-7510","authenticated-orcid":false,"given":"Hamid","family":"Laga","sequence":"additional","affiliation":[{"name":"School of Information Technology, Murdoch University, Murdoch, WA, Australia"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7250-7407","authenticated-orcid":false,"given":"Farid","family":"Boussaid","sequence":"additional","affiliation":[{"name":"Department of Electrical, Electronics and Computer Engineering, The University of Western Australia, Crawley, WA, Australia"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","article-title":"A variational perspective on solving inverse problems with diffusion models","author":"Mardani","year":"2023"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2025.naacl-long.304"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1016\/j.media.2024.103325"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00255"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2023.3318297"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2024.3382484"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2024.3359769"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00758"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2023.3334019"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2024.3362149"},{"key":"ref11","article-title":"Creativesynth: Creative blending and synthesis of visual arts based on multimodal diffusion","author":"Huang","year":"2024"},{"key":"ref12","article-title":"Mastering text-to-image diffusion: Recaptioning, planning, and generating with multimodal llms","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Yang","year":"2024"},{"key":"ref13","article-title":"Scaling autoregressive models for content-rich text-to-image generation","author":"Yu","year":"2022","journal-title":"Trans. Mach. Learn. Res."},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/WACV57701.2024.00526"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00708"},{"key":"ref16","article-title":"Compose and conquer: Diffusion-based 3D depth aware composable image synthesis","author":"Lee","year":"2024"},{"key":"ref17","article-title":"InstantID: Zero-shot identity-preserving generation in seconds","author":"Wang","year":"2024"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02156"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72920-1_26"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00355"},{"key":"ref21","article-title":"Training-free structured diffusion guidance for compositional text-to-image synthesis","volume-title":"Proc. 11th Int. Conf. Learn. Representations","author":"Feng","year":"2023"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00713"},{"key":"ref23","article-title":"LoCo: Locally constrained training-free layout-to-image synthesis","author":"Zhao","year":"2023"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.02118"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1145\/3592116"},{"key":"ref27","first-page":"78723","article-title":"T2i-compbench: A comprehensive benchmark for open-world compositional text-to-image generation","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"36","author":"Huang"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00685"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02154"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01866"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72986-7_23"},{"key":"ref32","article-title":"Controllable generation with text-to-image diffusion models: A survey","author":"Cao","year":"2024"},{"key":"ref33","article-title":"EditVal: Benchmarking diffusion based text-guided image editing methods","author":"Basu","year":"2023"},{"key":"ref34","article-title":"Cocktail: Mixing multi-modality control for text-conditional image generation","volume-title":"Proc. 37th Conf. Neural Inf. Process. Syst.","author":"Hu","year":"2023"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2023.3326649"},{"key":"ref36","first-page":"37491","article-title":"Is this loss informative? Faster text-to-image customization by tracking objective dynamics","volume-title":"Proc. 37th Conf. Neural Inf. Process. Syst.","author":"Voronov","year":"2023"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1145\/3610548.3618249"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-024-02227-z"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00823"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00457"},{"key":"ref41","article-title":"LayoutDiffuse: Adapting foundational diffusion models for layout-to-image generation","author":"Cheng","year":"2023"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i7.28596"},{"key":"ref43","article-title":"LLM-grounded diffusion: Enhancing prompt understanding of text-to-image diffusion models with large language models","volume-title":"Trans. Mach. Learn. Res.","author":"Lian","year":"2024"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02152"},{"key":"ref45","article-title":"LLM blueprint: Enabling text-to-image generation with complex and detailed prompts","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Gani","year":"2024"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00605"},{"key":"ref47","article-title":"Controllable text-to-image generation with GPT-4","author":"Zhang","year":"2023"},{"key":"ref48","article-title":"Divide & bind your attention for improved generative semantic nursing","volume-title":"Proc. Brit. Mach. Vis. Conf.","author":"Li","year":"2023"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00710"},{"key":"ref50","first-page":"18225","article-title":"LayoutGPT: Compositional visual planning and generation with large language models","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"36","author":"Feng","year":"2024"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i5.28270"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19790-1_26"},{"key":"ref53","article-title":"Linguistic binding in diffusion models: Enhancing attribute correspondence through attention map alignment","volume-title":"Proc. 37th Conf. Neural Inf. Process. Syst.","author":"Rassin","year":"2023"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52733.2024.00738"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i5.28204"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00885"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/WACV57701.2024.00526"},{"key":"ref58","article-title":"Divide and conquer: Language models can plan and self-correct for compositional text-to-image generation","author":"Wang","year":"2024"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v39i10.33139"},{"key":"ref60","article-title":"Multidiffusion: Fusing diffusion paths for controlled image generation","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Bar-Tal","year":"2023"},{"key":"ref61","article-title":"SyncDreamer: Generating multiview-consistent images from a single-view image","author":"Liu","year":"2023"},{"key":"ref62","article-title":"VisorGPT: Learning visual prior via generative pre-training","author":"Xie","year":"2023"},{"key":"ref63","article-title":"R&B: Region and boundary aware zero-shot grounded text-to-image generation","volume-title":"Proc. 12th Int. Conf. Learn. Representations","author":"Xiao","year":"2024"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"ref65","first-page":"6840","article-title":"Denoising diffusion probabilistic models","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"33","author":"Ho"},{"key":"ref66","first-page":"60599","article-title":"Reward-directed conditional diffusion: Provable distribution estimation and reward improvement","volume-title":"Proc. 37th Conf. Neural Inf. Process. Syst.","author":"Yuan","year":"2023"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72946-1_27"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72970-6_3"},{"key":"ref69","article-title":"The LLAMA 3 herd of models","author":"Dubey","year":"2024"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"ref71","first-page":"78723","article-title":"T2i-compbench: A comprehensive benchmark for open-world compositional text-to-image generation","volume-title":"Proc. 37th Conf. Neural Inf. Process. Syst. Datasets and Benchmarks Track","author":"Huang","year":"2023"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01834"},{"key":"ref73","article-title":"LLM-grounded diffusion: Enhancing prompt understanding of text-to-image diffusion models with large language models","author":"Lian","year":"2023"},{"key":"ref74","first-page":"19730","article-title":"Blip-2: Bootstrapping language-image pre-training with frozen image encoders and large language models","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Li","year":"2023"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00742"},{"key":"ref76","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00591"},{"key":"ref77","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2023.3331738"},{"key":"ref78","doi-asserted-by":"publisher","DOI":"10.1109\/WACV.2018.00048"},{"key":"ref79","article-title":"SDXL: Improving latent diffusion models for high-resolution image synthesis","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Podell","year":"2024"},{"key":"ref80","first-page":"6629","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.","author":"Heusel","year":"2017"}],"container-title":["IEEE Transactions on Multimedia"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/6046\/10844992\/11153996.pdf?arnumber=11153996","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,11,13]],"date-time":"2025-11-13T18:44:50Z","timestamp":1763059490000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11153996\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025]]},"references-count":80,"URL":"https:\/\/doi.org\/10.1109\/tmm.2025.3607759","relation":{},"ISSN":["1520-9210","1941-0077"],"issn-type":[{"value":"1520-9210","type":"print"},{"value":"1941-0077","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025]]}}}