{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,22]],"date-time":"2026-04-22T18:22:04Z","timestamp":1776882124625,"version":"3.51.2"},"reference-count":27,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,4,6]],"date-time":"2025-04-06T00:00:00Z","timestamp":1743897600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,4,6]],"date-time":"2025-04-06T00:00:00Z","timestamp":1743897600000},"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","id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100006180","name":"Technology Development","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100006180","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,4,6]]},"DOI":"10.1109\/icassp49660.2025.10890155","type":"proceedings-article","created":{"date-parts":[[2025,3,12]],"date-time":"2025-03-12T17:15:02Z","timestamp":1741799702000},"page":"1-5","source":"Crossref","is-referenced-by-count":1,"title":["Semantic Attention and LLM-based Layout Guidance for Text-to-Image Generation"],"prefix":"10.1109","author":[{"given":"Yuxiang","family":"Song","sequence":"first","affiliation":[{"name":"East China Normal University,School of Computer Science and Technology,Shanghai,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhaoguang","family":"Long","sequence":"additional","affiliation":[{"name":"East China Normal University,School of Computer Science and Technology,Shanghai,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Man","family":"Lan","sequence":"additional","affiliation":[{"name":"East China Normal University,School of Computer Science and Technology,Shanghai,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Changzhi","family":"Sun","sequence":"additional","affiliation":[{"name":"Institute of Artificial Intelligence (TeleAI), China Telecom"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Aimin","family":"Zhou","sequence":"additional","affiliation":[{"name":"East China Normal University,School of Computer Science and Technology,Shanghai,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yuefeng","family":"Chen","sequence":"additional","affiliation":[{"name":"Shanghai Transsion Co., Ltd,Shanghai,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hao","family":"Yuan","sequence":"additional","affiliation":[{"name":"Shanghai Transsion Co., Ltd,Shanghai,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Fei","family":"Cao","sequence":"additional","affiliation":[{"name":"Shanghai Transsion Co., Ltd,Shanghai,China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"issue":"2","key":"ref1","first-page":"3","article-title":"Hierarchical text-conditional image generation with clip latents","volume":"1","author":"Ramesh","year":"2022"},{"key":"ref2","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"International conference on machine learning","author":"Radford"},{"key":"ref3","article-title":"Attention is all you need","author":"Vaswani","year":"2017","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref4","first-page":"25 278","article-title":"Laion-5b: An open large-scale dataset for training next generation image-text models","volume":"35","author":"Schuhmann","year":"2022","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01834"},{"key":"ref6","first-page":"36 479","article-title":"Photorealistic text-to-image diffusion models with deep language understanding","volume":"35","author":"Saharia","year":"2022","journal-title":"Advances in neural information processing systems"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00708"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"ref9","article-title":"Layoutgpt: Compositional visual planning and generation with large language models","volume":"36","author":"Feng","year":"2024","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref10","article-title":"Llm-grounded diffusion: Enhancing prompt understanding of text-to-image diffusion models with large language models","author":"Lian","year":"2023"},{"key":"ref11","article-title":"Prompt-to-prompt image editing with cross attention control.(2022)","author":"Hertz","year":"2022"},{"key":"ref12","article-title":"Multidiffusion: Fusing diffusion paths for controlled image generation","author":"Bar-Tal","year":"2023"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1145\/3592116"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/WACV57701.2024.00526"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02156"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02154"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01369"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00758"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00355"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i5.28226"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3611863"},{"key":"ref22","article-title":"Imagereward: Learning and evaluating human preferences for text-to-image generation","volume":"36","author":"Xu","year":"2024","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref23","first-page":"24 824","article-title":"Chain-of-thought prompting elicits reasoning in large language models","volume":"35","author":"Wei","year":"2022","journal-title":"Advances in neural information processing systems"},{"issue":"240","key":"ref24","first-page":"1","article-title":"Palm: Scaling language modeling with pathways","volume":"24","author":"Chowdhery","year":"2023","journal-title":"Journal of Machine Learning Research"},{"key":"ref25","article-title":"Llama: open and efficient foundation language models. arxiv","author":"Touvron","year":"2023"},{"key":"ref26","article-title":"Gpt-4 technical report","author":"Achiam","year":"2023"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00742"}],"event":{"name":"ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","location":"Hyderabad, India","start":{"date-parts":[[2025,4,6]]},"end":{"date-parts":[[2025,4,11]]}},"container-title":["ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/10887540\/10887541\/10890155.pdf?arnumber=10890155","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,25]],"date-time":"2026-03-25T05:25:56Z","timestamp":1774416356000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10890155\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,4,6]]},"references-count":27,"URL":"https:\/\/doi.org\/10.1109\/icassp49660.2025.10890155","relation":{},"subject":[],"published":{"date-parts":[[2025,4,6]]}}}