{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,4]],"date-time":"2026-05-04T10:23:43Z","timestamp":1777890223769,"version":"3.51.4"},"reference-count":50,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,10,19]],"date-time":"2025-10-19T00:00:00Z","timestamp":1760832000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,10,19]],"date-time":"2025-10-19T00:00:00Z","timestamp":1760832000000},"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":[[2025,10,19]]},"DOI":"10.1109\/iccv51701.2025.01494","type":"proceedings-article","created":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T19:45:49Z","timestamp":1777491949000},"page":"16102-16111","source":"Crossref","is-referenced-by-count":0,"title":["Lay2Story: Extending Diffusion Transformers for Layout-Togglable Story Generation"],"prefix":"10.1109","author":[{"given":"Ao","family":"Ma","sequence":"first","affiliation":[{"name":"JD.com, Inc.,Beijing,China"}]},{"given":"Jiasong","family":"Feng","sequence":"additional","affiliation":[{"name":"JD.com, Inc.,Beijing,China"}]},{"given":"Ke","family":"Cao","sequence":"additional","affiliation":[{"name":"JD.com, Inc.,Beijing,China"}]},{"given":"Jing","family":"Wang","sequence":"additional","affiliation":[{"name":"JD.com, Inc.,Beijing,China"}]},{"given":"Yun","family":"Wang","sequence":"additional","affiliation":[{"name":"JD.com, Inc.,Beijing,China"}]},{"given":"Quanwei","family":"Zhang","sequence":"additional","affiliation":[{"name":"JD.com, Inc.,Beijing,China"}]},{"given":"Zhanjie","family":"Zhang","sequence":"additional","affiliation":[{"name":"JD.com, Inc.,Beijing,China"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.3390\/electronics9081295"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1145\/3453156"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v40i4.37247"},{"key":"ref4","author":"Che","year":"2024","journal-title":"Gamegen-x: Interactive open-world game video generation"},{"key":"ref5","volume-title":"Pixart-\u03b1: Fast training of diffusion transformer for photorealistic text-to-image synthesis","author":"Chen","year":"2023"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01265"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2024\/1120"},{"key":"ref8","author":"Fu","year":"2023","journal-title":"Dreamsim: Learning new dimensions of human visual similarity using synthetic data"},{"key":"ref9","author":"He","year":"2025","journal-title":"Anystory: Towards unified single and multiple subject personalization in text-to-image generation"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51701.2025.01686"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.emnlp-main.595"},{"key":"ref12","article-title":"Gans trained by a two time-scale update rule converge to a local nash equilibrium","volume":"30","author":"Heusel","year":"2017","journal-title":"Advances in neural information processing systems"},{"key":"ref13","author":"Hurst","year":"2024","journal-title":"Gpt-4o system card"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.52202\/075280-1850"},{"key":"ref15","first-page":"48955","article-title":"Miradata: A large-scale video dataset with long durations and structured captions","volume":"37","author":"Ju","year":"2025","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v27i1.8649"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.52202\/075280-1312"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00592"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72970-6_3"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v39i5.32590"},{"key":"ref21","author":"Liu","year":"2025","journal-title":"One-prompt-one-story: Free-lunch consistent text-to-image generation using a single prompt"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.52202\/079017-4094"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v39i6.32644"},{"key":"ref24","author":"Mao","year":"2024","journal-title":"Story-adapter: A training-free iterative framework for long story visualization"},{"key":"ref25","author":"Nan","year":"2024","journal-title":"Openvid-1m: A large-scale high-quality dataset for text-tovideo generation"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00387"},{"key":"ref27","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"International conference on machine learning","author":"Radford","year":"2021"},{"issue":"2","key":"ref28","first-page":"3","volume":"1","author":"Ramesh","year":"2022","journal-title":"Hierarchical text-conditional image generation with clip latents"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"ref30","volume-title":"Carvekit: Automated high-quality background removal framework","author":"Selin","year":"2023"},{"key":"ref31","article-title":"Storybooth: Training-free multi-subject consistency for improved visual storytelling","volume-title":"The Thirteenth International Conference on Learning Representations","author":"Singh"},{"key":"ref32","year":"2024","journal-title":"Instantx flux.1-dev ip-adapter page"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1145\/3658157"},{"key":"ref34","first-page":"10","article-title":"Converting video formats with ffmpeg","volume":"146","author":"Tomar","year":"2006","journal-title":"Linux journal"},{"key":"ref35","author":"Wang","year":"2024","journal-title":"Qihoo-t2x: An efficiency-focused diffusion transformer via proxy tokens for text-to-any-task"},{"key":"ref36","author":"Wang","year":"2025","journal-title":"Wisa: World simulator assistant for physics-aware text-to-video generation"},{"key":"ref37","author":"Wang","year":"2023","journal-title":"Videofactory: Swap attention in spatiotemporal diffusions for text-to-video generation"},{"key":"ref38","author":"Wang","year":"2023","journal-title":"Internvid: A large-scale video-text dataset for multimodal understanding and generation"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2025.3540282"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v39i8.32882"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/iccvw69036.2025.00197"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73223-2_20"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2024\/865"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i7.28570"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2025.129434"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1016\/j.neunet.2025.107556"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1016\/j.engappai.2025.111005"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.52202\/075280-0491"},{"key":"ref49","first-page":"110315","article-title":"Storydiffusion: Consistent selfattention for long-range image and video generation","volume":"37","author":"Zhou","year":"2025","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref50","author":"Zhou","year":"2024","journal-title":"Storymaker: Towards holistic consistent characters in text-to-image generation"}],"event":{"name":"2025 IEEE\/CVF International Conference on Computer Vision (ICCV)","location":"Honolulu, HI, USA","start":{"date-parts":[[2025,10,19]]},"end":{"date-parts":[[2025,10,25]]}},"container-title":["2025 IEEE\/CVF International Conference on Computer Vision (ICCV)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11443115\/11443287\/11445807.pdf?arnumber=11445807","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T05:32:44Z","timestamp":1777613564000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11445807\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":50,"URL":"https:\/\/doi.org\/10.1109\/iccv51701.2025.01494","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}