{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,2]],"date-time":"2026-07-02T16:25:27Z","timestamp":1783009527481,"version":"3.54.5"},"reference-count":99,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"12","license":[{"start":{"date-parts":[[2025,12,1]],"date-time":"2025-12-01T00:00:00Z","timestamp":1764547200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/legalcode"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["U1911203"],"award-info":[{"award-number":["U1911203"]}],"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":["U2001211"],"award-info":[{"award-number":["U2001211"]}],"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":["U22B2060"],"award-info":[{"award-number":["U22B2060"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100021171","name":"Basic and Applied Basic Research Foundation of Guangdong Province","doi-asserted-by":"publisher","award":["2019B1515130001"],"award-info":[{"award-number":["2019B1515130001"]}],"id":[{"id":"10.13039\/501100021171","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Key-Area Research and Development Program of Guangdong Province","award":["2020B0101100001"],"award-info":[{"award-number":["2020B0101100001"]}]},{"name":"Key-Area Research and Development Program of Guangdong Province","award":["2024B0101050005"],"award-info":[{"award-number":["2024B0101050005"]}]},{"name":"Research Foundation of Science and Technology Plan Project of Guangzhou City","award":["2023B01J0001"],"award-info":[{"award-number":["2023B01J0001"]}]},{"name":"Research Foundation of Science and Technology Plan Project of Guangzhou City","award":["2024B01W0004"],"award-info":[{"award-number":["2024B01W0004"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Pattern Anal. Mach. Intell."],"published-print":{"date-parts":[[2025,12]]},"DOI":"10.1109\/tpami.2025.3600149","type":"journal-article","created":{"date-parts":[[2025,8,19]],"date-time":"2025-08-19T18:15:55Z","timestamp":1755627355000},"page":"11874-11891","source":"Crossref","is-referenced-by-count":8,"title":["DreamStory: Open-Domain Story Visualization by LLM-Guided Multi-Subject Consistent Diffusion"],"prefix":"10.1109","volume":"47","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-1419-059X","authenticated-orcid":false,"given":"Huiguo","family":"He","sequence":"first","affiliation":[{"name":"School of Computer Science and Engineering, Sun Yat-sen University, Guangzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8612-0702","authenticated-orcid":false,"given":"Huan","family":"Yang","sequence":"additional","affiliation":[{"name":"01.AI, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0005-5402-0458","authenticated-orcid":false,"given":"Zixi","family":"Tuo","sequence":"additional","affiliation":[{"name":"01.AI, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yuan","family":"Zhou","sequence":"additional","affiliation":[{"name":"01.AI, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Qiuyue","family":"Wang","sequence":"additional","affiliation":[{"name":"01.AI, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yuhang","family":"Zhang","sequence":"additional","affiliation":[{"name":"01.AI, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0009-7765-0638","authenticated-orcid":false,"given":"Zeyu","family":"Liu","sequence":"additional","affiliation":[{"name":"01.AI, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Wenhao","family":"Huang","sequence":"additional","affiliation":[{"name":"01.AI, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6104-2322","authenticated-orcid":false,"given":"Hongyang","family":"Chao","sequence":"additional","affiliation":[{"name":"School of Computer Science and Engineering, Sun Yat-sen University, Guangzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1214-5384","authenticated-orcid":false,"given":"Jian","family":"Yin","sequence":"additional","affiliation":[{"name":"School of Artificial Intelligence, Sun Yat-sen University, Zhuhai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1177\/1555412012451123"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1016\/j.cedpsych.2017.05.001"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.3102\/0013189X022001005"},{"key":"ref4","first-page":"1","article-title":"Denoising diffusion implicit models","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Song"},{"key":"ref5","first-page":"1","article-title":"Score-based generative modeling through stochastic differential equations","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Song"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"ref7","article-title":"Hierarchical text-conditional image generation with CLIP latents","author":"Ramesh","year":"2022"},{"key":"ref8","first-page":"1","article-title":"SDXL: Improving latent diffusion models for high-resolution image synthesis","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Podell"},{"key":"ref9","article-title":"Playground v2.5: Three insights towards enhancing aesthetic quality in text-to-image generation","author":"Li","year":"2024"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2024.3382753"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2023.3261988"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2023.3321329"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2023.3305243"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2024.3355414"},{"key":"ref15","article-title":"LongLoRA: Efficient fine-tuning of long-context large language models","author":"Chen","year":"2023"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.acl-short.17"},{"key":"ref17","article-title":"A survey of large language models","author":"Zhao","year":"2023"},{"key":"ref18","first-page":"24824","article-title":"Chain-of-thought prompting elicits reasoning in large language models","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Wei"},{"issue":"70","key":"ref19","first-page":"1","article-title":"Scaling instruction-finetuned language models","volume":"25","author":"Chung","year":"2024","journal-title":"J. Mach. Learn. Res."},{"key":"ref20","first-page":"11809","article-title":"Tree of thoughts: Deliberate problem solving with large language models","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Yao"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1145\/3641519.3657430"},{"key":"ref22","article-title":"IP-Adapter: Text compatible image prompt adapter for text-to-image diffusion models","author":"Ye","year":"2023"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02155"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.52202\/079017-3200"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00592"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.02062"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1145\/3658157"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00649"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01237-3_37"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00355"},{"key":"ref31","first-page":"110315","article-title":"StoryDiffusion: Consistent self-attention for long-range image and video generation","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Zhou"},{"key":"ref32","article-title":"GPT-4 technical report","year":"2023"},{"key":"ref33","article-title":"Yi: Open foundation models by 01.AI","author":"Young","year":"2024"},{"key":"ref34","first-page":"1","article-title":"Auto-encoding variational Bayes","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Kingma"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58520-4_2"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3548034"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3547790"},{"key":"ref38","first-page":"1","article-title":"Unrolled generative adversarial networks","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Metz"},{"key":"ref39","first-page":"214","article-title":"Wasserstein generative adversarial networks","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Arjovsky"},{"key":"ref40","first-page":"5769","article-title":"Improved training of wasserstein GANs","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Gulrajani"},{"key":"ref41","first-page":"6840","article-title":"Denoising diffusion probabilistic models","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Ho"},{"key":"ref42","first-page":"8162","article-title":"Improved denoising diffusion probabilistic models","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Nichol"},{"key":"ref43","first-page":"8780","article-title":"Diffusion models beat GANs on image synthesis","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Dhariwal"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1145\/3528233.3530757"},{"key":"ref45","article-title":"LAION-5B: An open large-scale dataset for training next generation image-text models","author":"Schuhmann","year":"2022"},{"key":"ref46","article-title":"PixArt-$\\alpha$\u03b1: Fast training of diffusion transformer for photorealistic text-to-image synthesis","author":"Chen","year":"2023"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.emnlp-main.543"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.naacl-main.194"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.emnlp-main.565"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00246"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3612417"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19836-6_5"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/WACV57701.2024.00290"},{"key":"ref54","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Radford"},{"key":"ref55","first-page":"12888","article-title":"BLIP: Bootstrapping language-image pre-training for unified vision-language understanding and generation","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Li"},{"key":"ref56","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"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02557"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v39i10.33187"},{"key":"ref59","article-title":"Direct consistency optimization for compositional text-to-image personalization","author":"Lee","year":"2024"},{"key":"ref60","first-page":"1","article-title":"LoRA: Low-rank adaptation of large language models","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Hu"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1145\/3610548.3618173"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW63382.2024.00100"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00630"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00825"},{"key":"ref65","first-page":"30146","article-title":"BLIP-diffusion: Pre-trained subject representation for controllable text-to-image generation and editing","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Li"},{"key":"ref66","first-page":"1363","article-title":"Emergent correspondence from image diffusion","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Tang"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.11912"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D19-1117"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.12053"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P18-1160"},{"key":"ref71","first-page":"27730","article-title":"Training language models to follow instructions with human feedback","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Ouyang"},{"key":"ref72","article-title":"A picture is worth a thousand words: Principled recaptioning improves image generation","author":"Segalis","year":"2023"},{"key":"ref73","article-title":"Improving compositional text-to-image generation with large vision-language models","author":"Wen","year":"2023"},{"key":"ref74","article-title":"Stable video diffusion: Scaling latent video diffusion models to large datasets","author":"Blattmann","year":"2023"},{"key":"ref75","first-page":"66923","article-title":"Optimizing prompts for text-to-image generation","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Hao"},{"key":"ref76","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3612595"},{"key":"ref77","article-title":"AutoStudio: Crafting consistent subjects in multi-turn interactive image generation","author":"Cheng","year":"2024"},{"key":"ref78","first-page":"56704","article-title":"Mastering text-to-image diffusion: Recaptioning, planning, and generating with multimodal LLMs","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Yang"},{"key":"ref79","article-title":"TheaterGen: Character management with LLM for consistent multi-turn image generation","author":"Cheng","year":"2024"},{"key":"ref80","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00841"},{"key":"ref81","first-page":"1","article-title":"ConsistI2V: Enhancing visual consistency for image-to-video generation","author":"Ren","year":"2024","journal-title":"Trans. Mach. Learn. Res."},{"key":"ref82","first-page":"1","article-title":"SEINE: Short-to-long video diffusion model for generative transition and prediction","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Chen"},{"key":"ref83","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.acl-long.153"},{"key":"ref84","first-page":"70757","article-title":"Towards revealing the mystery behind chain of thought: A theoretical perspective","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Feng"},{"key":"ref85","article-title":"A survey of chain of thought reasoning: Advances, frontiers and future","author":"Chu","year":"2023"},{"key":"ref86","doi-asserted-by":"publisher","DOI":"10.1145\/3641519.3657423"},{"key":"ref87","doi-asserted-by":"publisher","DOI":"10.1145\/3592116"},{"key":"ref88","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00895"},{"key":"ref89","doi-asserted-by":"publisher","DOI":"10.1109\/WACV57701.2024.00526"},{"key":"ref90","article-title":"Grounded SAM: Assembling open-world models for diverse visual tasks","author":"Ren","year":"2024"},{"key":"ref91","first-page":"23","article-title":"A threshold selection method from gray-level histograms","volume":"11","author":"Otsu","year":"1975","journal-title":"Automatica"},{"key":"ref92","first-page":"50742","article-title":"DreamSim: Learning new dimensions of human visual similarity using synthetic data","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Fu"},{"key":"ref93","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72970-6_3"},{"key":"ref94","doi-asserted-by":"publisher","DOI":"10.1007\/s11633-025-1562-4"},{"key":"ref95","first-page":"1","article-title":"Classifier-free diffusion guidance","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst. Workshop","author":"Ho"},{"key":"ref96","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00371"},{"key":"ref97","article-title":"The lLAMA 3 herd of models","author":"Dubey","year":"2024"},{"key":"ref98","first-page":"29914","article-title":"Segment anything in high quality","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Ke"},{"key":"ref99","article-title":"Faster segment anything: Towards lightweight sam for mobile applications","author":"Zhang","year":"2023"}],"container-title":["IEEE Transactions on Pattern Analysis and Machine Intelligence"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/34\/11230086\/11130395.pdf?arnumber=11130395","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,11,6]],"date-time":"2025-11-06T18:53:29Z","timestamp":1762455209000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11130395\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,12]]},"references-count":99,"journal-issue":{"issue":"12"},"URL":"https:\/\/doi.org\/10.1109\/tpami.2025.3600149","relation":{},"ISSN":["0162-8828","2160-9292","1939-3539"],"issn-type":[{"value":"0162-8828","type":"print"},{"value":"2160-9292","type":"electronic"},{"value":"1939-3539","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,12]]}}}