{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,17]],"date-time":"2026-07-17T06:09:19Z","timestamp":1784268559936,"version":"3.55.0"},"reference-count":57,"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\/iccv51701.2025.01389","type":"proceedings-article","created":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T19:45:49Z","timestamp":1777491949000},"page":"14973-14982","source":"Crossref","is-referenced-by-count":1,"title":["MatchDiffusion: Training-Free Generation of Match-Cuts"],"prefix":"10.1109","author":[{"given":"Alejandro","family":"Pardo","sequence":"first","affiliation":[{"name":"KAUST"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Fabio","family":"Pizzati","sequence":"additional","affiliation":[{"name":"MBZUAI"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Tong","family":"Zhang","sequence":"additional","affiliation":[{"name":"KAUST"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Alexander","family":"Pondaven","sequence":"additional","affiliation":[{"name":"University of Oxford"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Philip","family":"Torr","sequence":"additional","affiliation":[{"name":"University of Oxford"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Juan Camilo","family":"Perez","sequence":"additional","affiliation":[{"name":"KAUST"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Bernard","family":"Ghanem","sequence":"additional","affiliation":[{"name":"KAUST"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","year":"2024","journal-title":"What is a match cut?"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.71"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1145\/3746027.3755462"},{"key":"ref4","article-title":"Talc: Time-aligned captions for multi-scene text-to-video generation","author":"Bansal","year":"2024","journal-title":"arXiv preprint"},{"key":"ref5","article-title":"Multidiffusion: Fusing diffusion paths for controlled image generation","author":"Bar-Tal","year":"2023","journal-title":"ICML"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1145\/3641519.3657500"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.00011"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v39i2.32192"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/WACV56688.2023.00215"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10447306"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73229-4_22"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72998-0_21"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02280"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52734.2025.00245"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.emnlp-main.595"},{"key":"ref16","article-title":"Denoising diffusion probabilistic models","author":"Ho","year":"2020","journal-title":"NeurIPS"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73033-7_2"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.52202\/079017-3016"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1145\/3072959.3073653"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.52202\/075280-2203"},{"key":"ref21","article-title":"A technique for the measurement of attitudes","author":"Likert","year":"1932","journal-title":"Archives of psychology"},{"key":"ref22","article-title":"Videodirectorgpt: Consistent multi-scene video generation via 11 m -guided planning","author":"Lin","year":"2023","journal-title":"arXiv preprint"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/WACV57701.2024.00532"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"ref25","article-title":"Videodrafter: Content-consistent multi-scene video generation with 11m","author":"Long","year":"2024","journal-title":"arXiv preprint"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73027-6_27"},{"key":"ref27","article-title":"Sdedit: Guided image synthesis and editing with stochastic differential equations","author":"Meng","year":"2022","journal-title":"ICLR"},{"key":"ref28","article-title":"In the Blink of an Eye","author":"Murch","year":"2001","journal-title":"Silman-James Press Los Angeles"},{"key":"ref29","year":"2024","journal-title":"How to use match cuts to tell stories"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00678"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20071-7_39"},{"key":"ref32","article-title":"Automatch: A large-scale audio beat matching benchmark for boosting deep learning assistant video editing","author":"Pei","year":"2023","journal-title":"arXiv preprint"},{"key":"ref33","author":"Perez","year":"2024","journal-title":"My favourite match cut"},{"key":"ref34","article-title":"Film analysis guide","author":"Prunes","year":"2002","journal-title":"New Haven, CT"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00851"},{"key":"ref36","article-title":"Freenoise: Tuning-free longer video diffusion via noise rescheduling","author":"Qiu","year":"2024","journal-title":"ICLR"},{"key":"ref37","article-title":"Contrastive sequential-diffusion learning: An approach to multi-scene instructional video synthesis","author":"Ramos","year":"2024","journal-title":"arXiv preprint"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19839-7_17"},{"key":"ref41","article-title":"Denoising diffusion implicit models","author":"Song","year":"2021","journal-title":"ICLR"},{"key":"ref42","year":"2024","journal-title":"Match cuts: Creative transitions examples"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2018.2831899"},{"key":"ref44","year":"2024","journal-title":"Types of match cuts, examples, and how to use them"},{"key":"ref45","article-title":"Gen-l-video: Multi-text to long video generation via temporal co-denoising","author":"Wang","year":"2024","journal-title":"ICLR"},{"key":"ref46","article-title":"Zola: Zero-shot creative long animation generation with short video model","author":"Wang","year":"2024","journal-title":"ECCV"},{"key":"ref47","article-title":"Lavie: High-quality video generation with cascaded latent diffusion models","author":"Wang","year":"2024","journal-title":"IJCV"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2003.819861"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.02234"},{"key":"ref50","article-title":"Video diffusion models are training-free motion interpreter and controller","author":"Xiao","year":"2024","journal-title":"arXiv preprint"},{"key":"ref51","article-title":"Dreamfactory: Pioneering multi-scene long video generation with a multi-agent framework","author":"Xie","year":"2024","journal-title":"arXiv preprint"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1145\/3610548.3618160"},{"key":"ref53","article-title":"Cogvideox: Text-to-video diffusion models with an expert transformer","author":"Yang","year":"2025","journal-title":"ICLR"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00809"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00068"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00828"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.02065"}],"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\/11444896.pdf?arnumber=11444896","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T04:54:17Z","timestamp":1777611257000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11444896\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":57,"URL":"https:\/\/doi.org\/10.1109\/iccv51701.2025.01389","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}