{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,6]],"date-time":"2026-05-06T06:18:47Z","timestamp":1778048327101,"version":"3.51.4"},"reference-count":56,"publisher":"IEEE","license":[{"start":{"date-parts":[[2026,3,6]],"date-time":"2026-03-06T00:00:00Z","timestamp":1772755200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,3,6]],"date-time":"2026-03-06T00:00:00Z","timestamp":1772755200000},"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":[[2026,3,6]]},"DOI":"10.1109\/wacv61042.2026.00258","type":"proceedings-article","created":{"date-parts":[[2026,5,5]],"date-time":"2026-05-05T19:59:32Z","timestamp":1778011172000},"page":"2626-2636","source":"Crossref","is-referenced-by-count":0,"title":["CineVerse: Consistent Keyframe Synthesis for Cinematic Scene Composition"],"prefix":"10.1109","author":[{"given":"Quynh","family":"Phung","sequence":"first","affiliation":[{"name":"University of Maryland,College Park"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Long","family":"Mai","sequence":"additional","affiliation":[{"name":"Adobe Research"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Fabian David","family":"Caba Heilbron","sequence":"additional","affiliation":[{"name":"Adobe Research"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Feng","family":"Liu","sequence":"additional","affiliation":[{"name":"Adobe Research"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jia-Bin","family":"Huang","sequence":"additional","affiliation":[{"name":"University of Maryland,College Park"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Cusuh","family":"Ham","sequence":"additional","affiliation":[{"name":"Adobe Research"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20074-8_12"},{"key":"ref2","volume-title":"Grammar of the Film Language","author":"Arijon","year":"1976"},{"key":"ref3","article-title":"Talc: Time-aligned captions for multi-scene text-to-video generation","author":"Bansal","year":"2024"},{"key":"ref4","article-title":"Stable video diffusion: Scaling latent video diffusion models to large datasets","author":"Blattmann","year":"2023"},{"key":"ref5","article-title":"Dreamsim: Learning new dimensions of human visual similarity using synthetic data","author":"Fu","year":"2023"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73027-6_27"},{"key":"ref7","article-title":"Seed-x: Multimodal models with unified multi-granularity comprehension and generation","author":"Ge","year":"2024"},{"key":"ref8","article-title":"The llama 3 herd of models","author":"Grattafiori","year":"2024"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00633"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3612417"},{"key":"ref11","article-title":"Shot2story20k: A new benchmark for comprehensive understanding of multi-shot videos","author":"Han","year":"2023"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01255"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01815"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01720"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/tpami.2025.3600149"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.emnlp-main.595"},{"key":"ref17","article-title":"Imagen video: High definition video generation with diffusion models","author":"Ho","year":"2022"},{"key":"ref18","article-title":"Denoising diffusion probabilistic models","volume-title":"NeurIPS","author":"Ho"},{"issue":"2","key":"ref19","first-page":"3","article-title":"Lora: Low-rank adaptation of large language models","volume":"1","author":"Hu","year":"2022","journal-title":"ICLR"},{"key":"ref20","article-title":"In-context lora for diffusion transformers","author":"Huang","year":"2024"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58548-8_41"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01462"},{"key":"ref23","article-title":"Hunyuanvideo: A systematic framework for large video generative models","author":"Kong","year":"2024"},{"key":"ref24","volume-title":"Flux","year":"2024"},{"key":"ref25","article-title":"Llava-onevision: Easy visual task transfer","author":"Li","year":"2024"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00649"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1038\/s41598-023-43281-w"},{"key":"ref28","article-title":"Videodirectorgpt: Consistent multi-scene video generation via llm-guided planning","author":"Lin","year":"2023"},{"key":"ref29","article-title":"One-prompt-one-story: Free-lunch consistent text-to-image generation using a single prompt","author":"Liu","year":"2025"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19836-6_5"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206557"},{"key":"ref32","year":"2023","journal-title":"Gpt-4 technical report"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00387"},{"key":"ref34","article-title":"Sdxl: Improving latent diffusion models for high-resolution image synthesis","author":"Podell","year":"2023"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/wacv61041.2025.00456"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58621-8_2"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-016-0987-1"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-24574-4_28"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.52202\/068431-2643"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1016\/j.dib.2021.107002"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00497"},{"key":"ref43","article-title":"Makeany-thing: Harnessing diffusion transformers for multi-domain procedural sequence generation","author":"Song","year":"2025"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.501"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1145\/3658157"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.26599\/CVM.2025.9450322"},{"key":"ref47","article-title":"Wan: Open and advanced large-scale video generative models","author":"Wang","year":"2025"},{"key":"ref48","article-title":"Autostory: Generating diverse storytelling images with minimal human effort","author":"Wang","year":"2024","journal-title":"Int. J. Computer Vision"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.52202\/075280-0334"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00701"},{"key":"ref51","article-title":"Learning long-form video prior via generative pre-training","author":"Xie","year":"2024"},{"key":"ref52","article-title":"Show-o: One single transformer to unify multimodal understanding and generation","author":"Xie","year":"2024"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/iccvw69036.2025.00197"},{"key":"ref54","article-title":"Cogvideox: Text-to-video diffusion models with an expert transformer","author":"Yang","year":"2024"},{"key":"ref55","article-title":"Moviedreamer: Hierarchical generation for coherent long visual sequence","author":"Zhao","year":"2024"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.52202\/079017-3501"}],"event":{"name":"2026 IEEE\/CVF Winter Conference on Applications of Computer Vision (WACV)","location":"Tucson, AZ, USA","start":{"date-parts":[[2026,3,6]]},"end":{"date-parts":[[2026,3,10]]}},"container-title":["2026 IEEE\/CVF Winter Conference on Applications of Computer Vision (WACV)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11491838\/11491925\/11491928.pdf?arnumber=11491928","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,6]],"date-time":"2026-05-06T05:53:14Z","timestamp":1778046794000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11491928\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,3,6]]},"references-count":56,"URL":"https:\/\/doi.org\/10.1109\/wacv61042.2026.00258","relation":{},"subject":[],"published":{"date-parts":[[2026,3,6]]}}}