{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,30]],"date-time":"2026-04-30T17:34:41Z","timestamp":1777570481932,"version":"3.51.4"},"reference-count":44,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,6,30]],"date-time":"2025-06-30T00:00:00Z","timestamp":1751241600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,6,30]],"date-time":"2025-06-30T00:00:00Z","timestamp":1751241600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,6,30]]},"DOI":"10.1109\/icme59968.2025.11210189","type":"proceedings-article","created":{"date-parts":[[2025,10,30]],"date-time":"2025-10-30T17:57:42Z","timestamp":1761847062000},"page":"1-6","source":"Crossref","is-referenced-by-count":3,"title":["Object Isolated Attention for Consistent Story Visualization"],"prefix":"10.1109","author":[{"given":"Xiangyang","family":"Luo","sequence":"first","affiliation":[{"name":"Guangdong Laboratory of Artificial Intelligence and Digital Economy (SZ),Shenzhen,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Junhao","family":"Cheng","sequence":"additional","affiliation":[{"name":"Sun Yat-sen University,Shenzhen,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yifan","family":"Xie","sequence":"additional","affiliation":[{"name":"Guangdong Laboratory of Artificial Intelligence and Digital Economy (SZ),Shenzhen,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xin","family":"Zhang","sequence":"additional","affiliation":[{"name":"Guangdong Laboratory of Artificial Intelligence and Digital Economy (SZ),Shenzhen,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Tao","family":"Feng","sequence":"additional","affiliation":[{"name":"Guangdong Laboratory of Artificial Intelligence and Digital Economy (SZ),Shenzhen,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhou","family":"Liu","sequence":"additional","affiliation":[{"name":"Guangdong Laboratory of Artificial Intelligence and Digital Economy (SZ),Shenzhen,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Fei","family":"Ma","sequence":"additional","affiliation":[{"name":"Guangdong Laboratory of Artificial Intelligence and Digital Economy (SZ),Shenzhen,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Fei","family":"Yu","sequence":"additional","affiliation":[{"name":"Guangdong Laboratory of Artificial Intelligence and Digital Economy (SZ),Shenzhen,China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00649"},{"issue":"15","key":"ref2","first-page":"169","article-title":"Using storybooks as a character education tools","volume":"7","author":"Turan","year":"2016","journal-title":"Journal of education and practice"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v39i8.32946"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1145\/950566.950585"},{"key":"ref5","article-title":"Masked generative story transformer with character guidance and caption augmentation","author":"Papadimitriou","year":"2024"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.emnlp-main.565"},{"key":"ref7","article-title":"Generative adversarial nets","volume":"27","author":"Goodfellow","year":"2014","journal-title":"Advances in neural information processing systems"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00246"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/WACV57701.2024.00290"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72992-8_27"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1145\/3610548.3618184"},{"key":"ref12","first-page":"6840","article-title":"Denoising diffusion probabilistic models","volume":"33","author":"Ho","year":"2020","journal-title":"Advances in neural information processing systems"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"ref14","article-title":"Ip-adapter: Text compatible image prompt adapter for text-to-image diffusion models","author":"Ye","year":"2023"},{"key":"ref15","article-title":"Theatergen: Character management with llm for consistent multi-turn image generation","author":"Cheng","year":"2024"},{"key":"ref16","article-title":"Autostudio: Crafting consistent subjects in multi-turn interactive image generation","author":"Cheng","year":"2024"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00868"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1145\/3658157"},{"key":"ref19","article-title":"Storydiffusion: Consistent self-attention for long-range image and video generation","year":"2024","journal-title":"NeurIPS"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/tpami.2025.3600149"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1145\/3664647.3681120"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00648"},{"key":"ref23","article-title":"Attention is all you need","author":"Vaswani","year":"2017","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref24","first-page":"6840","article-title":"Denoising diffusion probabilistic models","volume":"33","author":"Ho","year":"2020","journal-title":"Advances in neural information processing systems"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"ref26","article-title":"Sdxl: Improving latent diffusion models for high-resolution image synthesis","author":"Podell","year":"2023"},{"issue":"2","key":"ref27","first-page":"3","article-title":"Hierarchical text-conditional image generation with clip latents","volume":"1","author":"Ramesh","year":"2022"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00387"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1145\/3579371.3589115"},{"key":"ref30","article-title":"Grid: Visual layout generation","author":"Wan","year":"2024"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/tpami.2025.3594034"},{"key":"ref32","article-title":"Chatgpt: Gpt-4","year":"2024"},{"issue":"285-296","key":"ref33","first-page":"23","article-title":"A threshold selection method from gray-level histograms","volume":"11","author":"Otsu","year":"1975","journal-title":"Automatica"},{"key":"ref34","article-title":"Hd-painter: high-resolution and prompt-faithful text-guided image inpainting with diffusion models","author":"Manukyan","year":"2023"},{"key":"ref35","article-title":"Mix-of-show: Decentralized low-rank adaptation for multi-concept customization of diffusion models","volume":"36","author":"Gu","year":"2024","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00651"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/wacv61041.2025.00385"},{"key":"ref38","article-title":"Classifier-free diffusion guidance","author":"Ho","year":"2022"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00592"},{"key":"ref40","article-title":"Mini-dalle3: Interactive text to image by prompting large language models","author":"Lai","year":"2023"},{"key":"ref41","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"International conference on machine learning","author":"Radford"},{"key":"ref42","article-title":"Improved aesthetic predictor","author":"Schuhmann","year":"2024"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72970-6_3"},{"key":"ref44","article-title":"Dreamsim: Learning new dimensions of human visual similarity using synthetic data","author":"Fu","year":"2023"}],"event":{"name":"2025 IEEE International Conference on Multimedia and Expo (ICME)","location":"Nantes, France","start":{"date-parts":[[2025,6,30]]},"end":{"date-parts":[[2025,7,4]]}},"container-title":["2025 IEEE International Conference on Multimedia and Expo (ICME)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11208895\/11208897\/11210189.pdf?arnumber=11210189","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,31]],"date-time":"2025-10-31T05:33:50Z","timestamp":1761888830000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11210189\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,6,30]]},"references-count":44,"URL":"https:\/\/doi.org\/10.1109\/icme59968.2025.11210189","relation":{},"subject":[],"published":{"date-parts":[[2025,6,30]]}}}