{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,4]],"date-time":"2026-05-04T03:29:07Z","timestamp":1777865347430,"version":"3.51.4"},"reference-count":42,"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\/iccv51701.2025.01550","type":"proceedings-article","created":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T19:45:49Z","timestamp":1777491949000},"page":"16692-16701","source":"Crossref","is-referenced-by-count":1,"title":["InsViE-1M: Effective Instruction-Based Video Editing with Elaborate Dataset Construction"],"prefix":"10.1109","author":[{"given":"Yuhui","family":"Wu","sequence":"first","affiliation":[{"name":"The Hong Kong Polytechnic University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Liyi","family":"Chen","sequence":"additional","affiliation":[{"name":"The Hong Kong Polytechnic University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ruibin","family":"Li","sequence":"additional","affiliation":[{"name":"The Hong Kong Polytechnic University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Shihao","family":"Wang","sequence":"additional","affiliation":[{"name":"The Hong Kong Polytechnic University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Chenxi","family":"Xie","sequence":"additional","affiliation":[{"name":"The Hong Kong Polytechnic University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Lei","family":"Zhang","sequence":"additional","affiliation":[{"name":"The Hong Kong Polytechnic University"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref3","article-title":"Cosxl: A text-to-image model","year":"2024","journal-title":"Hugging Face Model Hub"},{"key":"ref4","author":"Blattmann","year":"2023","journal-title":"Stable video diffusion: Scaling latent video diffusion models to large datasets"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01764"},{"key":"ref6","author":"Cheng","year":"2023","journal-title":"Consistent video-to-video transfer using synthetic dataset"},{"key":"ref7","author":"Cohen","year":"2024","journal-title":"Slicedit: Zeroshot video editing with text-to-image diffusion models using spatio-temporal slices"},{"key":"ref8","author":"Cong","year":"2023","journal-title":"Flatten: optical flowguided attention for consistent text-to-video editing"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73254-6_14"},{"key":"ref10","author":"Geyer","year":"2023","journal-title":"Tokenflow: Consistent diffusion features for consistent video editing"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00728"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00667"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01354"},{"key":"ref14","author":"Edward","year":"2021","journal-title":"Lora: Low-rank adaptation of large language models"},{"key":"ref15","author":"Hu","year":"2024","journal-title":"Vivid-10m: A dataset and baseline for versatile and interactive video local editing"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00799"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00622"},{"key":"ref18","author":"Ku","year":"2024","journal-title":"Anyv2v: A plug-and-play framework for any video-to-video editing tasks"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73390-1_13"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52733.2024.00715"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52734.2025.01650"},{"key":"ref22","author":"Nan","year":"2024","journal-title":"Openvid-1m: A large-scale high-quality dataset for text-tovideo generation"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00773"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1145\/3680528.3687656"},{"key":"ref25","author":"Pont-Tuset","year":"2017","journal-title":"The 2017 davis challenge on video object segmentation"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01460"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ICME57554.2024.10687529"},{"key":"ref28","article-title":"Learning transferable visual models from natural language supervision","volume-title":"International conference on machine learning","author":"Radford","year":"2021"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73116-7_26"},{"key":"ref31","author":"Song","year":"2020","journal-title":"Denoising diffusion implicit models"},{"key":"ref32","author":"Sun","year":"2024","journal-title":"Diffusion model-based video editing: A survey"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1145\/3721238.3730647"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01843"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00701"},{"key":"ref36","author":"Zhangjie Wu","year":"2023","journal-title":"Cvpr 2023 text guided video editing competition"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00795"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01228-1_36"},{"key":"ref39","author":"Yang","year":"2024","journal-title":"CogVideoX: Text-to-video diffusion models with an expert transformer"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.52202\/075280-1365"},{"key":"ref41","author":"Zhang","year":"2023","journal-title":"I2vgen-xl: High-quality image-to-video synthesis via cascaded diffusion models"},{"key":"ref42","author":"Zhang","year":"2024","journal-title":"Effived: Efficient video editing via text-instruction diffusion models"},{"key":"ref43","author":"Zheng","year":"2024","journal-title":"Open-sora: Democratizing efficient video production for all"},{"key":"ref44","author":"Zi","year":"2025","journal-title":"Se\\~norita-2m: A high-quality instruction-based dataset for general video editing by video specialists"}],"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\/11446233.pdf?arnumber=11446233","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,30]],"date-time":"2026-04-30T06:18:48Z","timestamp":1777529928000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11446233\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":42,"URL":"https:\/\/doi.org\/10.1109\/iccv51701.2025.01550","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}