{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,4]],"date-time":"2026-05-04T10:16:10Z","timestamp":1777889770830,"version":"3.51.4"},"reference-count":26,"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"}],"funder":[{"DOI":"10.13039\/100020595","name":"National Science and Technology Council (NSTC)","doi-asserted-by":"publisher","award":["NSTC-112-2628-E-002-033-MY4"],"award-info":[{"award-number":["NSTC-112-2628-E-002-033-MY4"]}],"id":[{"id":"10.13039\/100020595","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,10,19]]},"DOI":"10.1109\/iccv51701.2025.01733","type":"proceedings-article","created":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T19:45:49Z","timestamp":1777491949000},"page":"1-10","source":"Crossref","is-referenced-by-count":0,"title":["From Prompt to Progression: Taming Video Diffusion Models for Seamless Attribute Transition"],"prefix":"10.1109","author":[{"given":"Ling","family":"Lo","sequence":"first","affiliation":[{"name":"National Yang Ming Chiao Tung University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Kelvin C.K.","family":"Chan","sequence":"additional","affiliation":[{"name":"Google DeepMind"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Wen-Huang","family":"Cheng","sequence":"additional","affiliation":[{"name":"National Taiwan University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ming-Hsuan","family":"Yang","sequence":"additional","affiliation":[{"name":"UC Merced"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","article-title":"Gpt-4 technical report","author":"Achiam","year":"2023","journal-title":"arXiv preprint arXiv"},{"key":"ref2","article-title":"ediff-i: Text-to-image diffusion models with an ensemble of expert denoisers","author":"Balaji","year":"2022","journal-title":"arXiv preprint arXiv"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.52202\/075280-1102"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.02062"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00698"},{"key":"ref6","article-title":"Diffusion models beat gans on image synthesis","author":"Dhariwal","year":"2021","journal-title":"NeurIPS"},{"key":"ref7","article-title":"Tc-bench: Benchmarking temporal compositionality in text-to-video and image-tovideo generation","author":"Feng","year":"2024","journal-title":"arXiv preprint arXiv"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19790-1_7"},{"key":"ref9","article-title":"Animatediff: Animate your personalized text-toimage diffusion models without specific tuning","author":"Guo","year":"2024","journal-title":"ICLR"},{"key":"ref10","article-title":"Latent video diffusion models for high-fidelity long video generation","author":"He","year":"2022","journal-title":"arXiv preprint arXiv"},{"key":"ref11","article-title":"Prompt-to-prompt image editing with cross attention control","author":"Hertz","year":"2023","journal-title":"ICLR"},{"key":"ref12","article-title":"Classifier-free diffusion guidance","author":"Ho","year":"2021","journal-title":"NeurIPS"},{"key":"ref13","article-title":"Cogvideo: Large-scale pretraining for text-to-video generation via transformers","author":"Hong","year":"2023","journal-title":"ICLR"},{"key":"ref14","article-title":"Free-bloom: Zero-shot text-to-video generator with 11 m director and 1 dm animator","author":"Huang","year":"2023","journal-title":"NeurIPS"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00834"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19790-1_26"},{"key":"ref17","article-title":"Latte: Latent diffusion transformer for video generation","author":"Ma","year":"2024","journal-title":"arXiv preprint arXiv"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72775-7_23"},{"key":"ref19","article-title":"Freenoise: Tuning-free longer video diffusion via noise rescheduling","author":"Qiu","year":"2024","journal-title":"ICLR"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00926"},{"key":"ref21","article-title":"Maximum likelihood training of score-based diffusion models","author":"Song","year":"2021","journal-title":"NeurIPS"},{"key":"ref22","article-title":"Videotetris: Towards compositional text-to-video generation","author":"Tian","year":"2024","journal-title":"NeurIPS"},{"key":"ref23","article-title":"Phenaki: Variable length video generation from open domain textual descriptions","author":"Villegas","year":"2022","journal-title":"ICLR"},{"key":"ref24","article-title":"Gen-l-video: Multi-text to long video generation via temporal co-denoising","author":"Wang","year":"2023","journal-title":"arXiv preprint arXiv"},{"key":"ref25","article-title":"Modelscope text-to-video technical report","author":"Wang","year":"2023","journal-title":"arXiv preprint arXiv"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00701"}],"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\/11444722.pdf?arnumber=11444722","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T05:19:23Z","timestamp":1777612763000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11444722\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":26,"URL":"https:\/\/doi.org\/10.1109\/iccv51701.2025.01733","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}