{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,4]],"date-time":"2026-05-04T09:59:32Z","timestamp":1777888772104,"version":"3.51.4"},"reference-count":79,"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\/iccv51701.2025.01485","type":"proceedings-article","created":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T19:45:49Z","timestamp":1777491949000},"page":"16004-16014","source":"Crossref","is-referenced-by-count":0,"title":["DIVE: Taming DINO for Subject-Driven Video Editing"],"prefix":"10.1109","author":[{"given":"Yi","family":"Huang","sequence":"first","affiliation":[{"name":"Shenzhen Institutes of Advanced Technology, Chinese Academy of Sciences"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Wei","family":"Xiong","sequence":"additional","affiliation":[{"name":"NVIDIA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"He","family":"Zhang","sequence":"additional","affiliation":[{"name":"Adobe Research"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Chaoqi","family":"Chen","sequence":"additional","affiliation":[{"name":"Shenzhen University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jianzhuang","family":"Liu","sequence":"additional","affiliation":[{"name":"Shenzhen Institutes of Advanced Technology, Chinese Academy of Sciences"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Mingfu","family":"Yan","sequence":"additional","affiliation":[{"name":"Shenzhen Institutes of Advanced Technology, Chinese Academy of Sciences"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Shifeng","family":"Chen","sequence":"additional","affiliation":[{"name":"Shenzhen Institutes of Advanced Technology, Chinese Academy of Sciences"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"issue":"3","key":"ref1","volume":"2","author":"Amir","year":"2021","journal-title":"Deep vit features as dense visual descriptors"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02161"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01764"},{"key":"ref4","author":"Chen","year":"2023","journal-title":"Disenbooth: Identitypreserving disentangled tuning for subject-driven text-toimage generation"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.52202\/075280-1318"},{"key":"ref6","first-page":"9109","author":"Cohen","year":"2024","journal-title":"Slicedit: Zeroshot video editing with text-to-image diffusion models using spatio-temporal slices"},{"key":"ref7","author":"Cong","year":"2023","journal-title":"Flatten: optical flowguided attention for consistent text-to-video editing"},{"key":"ref8","first-page":"8780","article-title":"Diffusion models beat gans on image synthesis","author":"Dhariwal","year":"2021","journal-title":"NeurIPS"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00675"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00641"},{"key":"ref11","article-title":"An image is worth one word: Personalizing text-to-image generation using textual inversion","author":"Gal","year":"2023","journal-title":"ICLR"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.02096"},{"key":"ref13","author":"Geyer","year":"2023","journal-title":"Tokenflow: Consistent diffusion features for consistent video editing"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.52202\/075280-1529"},{"key":"ref15","article-title":"Mix-of-show: Decentralized lowrank adaptation for multi-concept customization of diffusion models","author":"Gu","year":"2024","journal-title":"NeurIPS"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00728"},{"key":"ref17","author":"Guo","year":"2023","journal-title":"Animatediff: Animate your personalized text-to-image diffusion models without specific tuning"},{"key":"ref18","author":"Hertz","year":"2022","journal-title":"Prompt-to-prompt image editing with cross attention control"},{"key":"ref19","first-page":"6840","article-title":"Denoising diffusion probabilistic models","author":"Ho","year":"2020","journal-title":"NeurIPS"},{"key":"ref20","author":"Ho","year":"2022","journal-title":"Imagen video: High definition video generation with diffusion models"},{"issue":"1","key":"ref21","first-page":"2249","article-title":"Cascaded diffusion models for high fidelity image generation","volume":"23","author":"Ho","year":"2022","journal-title":"JMLR"},{"key":"ref22","article-title":"Video diffusion models","author":"Ho","year":"2022","journal-title":"NeurIPS"},{"key":"ref23","author":"Hu","year":"2023","journal-title":"Videocontrolnet: A motion-guided video-to-video translation framework by using diffusion model with controlnet"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52733.2024.00799"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/tpami.2025.3541625"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02060"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00622"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01462"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72751-1_15"},{"key":"ref30","article-title":"Anyv2v: A tuning-free framework for any video-tovideo editing tasks","author":"Ku","year":"2024","journal-title":"TMLR"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00192"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73390-1_13"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00719"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00715"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00784"},{"key":"ref36","author":"Liew","year":"2023","journal-title":"Magicedit: High-fidelity and temporally coherent video editing"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00821"},{"key":"ref38","article-title":"Cones: Concept neurons in diffusion models for customized generation","author":"Liu","year":"2023","journal-title":"ICML"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01371"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW63382.2024.00150"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00818"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i5.28226"},{"key":"ref43","author":"Oquab","year":"2023","journal-title":"Dinov2: Learning robust visual features without supervision"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1145\/3680528.3687656"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.85"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01460"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02155"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00624"},{"key":"ref50","article-title":"Photorealistic text-to-image diffusion models with deep language understanding","author":"Saharia","year":"2022","journal-title":"NeurIPS"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52733.2024.00847"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52733.2024.00816"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW60793.2023.00100"},{"key":"ref54","article-title":"Make-a-video: Text-to-video generation without text-video data","author":"Singer","year":"2023","journal-title":"ICLR"},{"key":"ref55","article-title":"Deep unsupervised learning using nonequilibrium thermodynamics","author":"Sohl-Dickstein","year":"2015","journal-title":"ICML"},{"key":"ref56","article-title":"Denoising diffusion implicit models","author":"Song","year":"2021","journal-title":"ICLR"},{"key":"ref57","article-title":"Generative modeling by estimating gradients of the data distribution","author":"Song","year":"2019","journal-title":"NeurIPS"},{"key":"ref58","article-title":"Score-based generative modeling through stochastic differential equations","author":"Song","year":"2021","journal-title":"ICLR"},{"key":"ref59","author":"Sun","year":"2024","journal-title":"Diffusion model-based video editing: A survey"},{"key":"ref60","first-page":"1363","article-title":"Emergent correspondence from image diffusion","author":"Tang","year":"2023","journal-title":"NeurIPS"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1145\/3588432.3591506"},{"key":"ref62","article-title":"Is this loss informative? faster text-to-image customization by tracking objective dynamics","author":"Voronov","year":"2023","journal-title":"NeurIPS"},{"key":"ref63","author":"Wang","year":"2024","journal-title":"Cove: Unleashing the diffusion feature correspondence for consistent video editing"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-024-02295-1"},{"key":"ref65","author":"Wang","year":"2023","journal-title":"Internvid: A large-scale video-text dataset for multimodal understanding and generation"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01461"},{"key":"ref67","first-page":"65376549","article-title":"Dreamvideo: Composing your dream videos with customized subject and motion","author":"Wei","year":"2024","journal-title":"CVPR"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1109\/iccv51070.2023.00701"},{"key":"ref69","author":"Zhangjie Wu","year":"2023","journal-title":"Cvpr 2023 text guided video editing competition"},{"key":"ref70","author":"Xiao","year":"2023","journal-title":"Comcat: towards efficient compression and customization of attention-based vision models"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1145\/3696415"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00498"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1145\/3610548.3618160"},{"key":"ref74","author":"Ye","year":"2023","journal-title":"Ipadapter: Text compatible image prompt adapter for text-toimage diffusion models"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.1145\/3664647.3681396"},{"key":"ref76","article-title":"A tale of two features: Stable diffusion complements dino for zero-shot semantic correspondence","author":"Zhang","year":"2023","journal-title":"NeurIPS"},{"key":"ref77","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00355"},{"key":"ref78","article-title":"Towards consistent video editing with text-to-image diffusion models","author":"Zhang","year":"2024","journal-title":"NeurIPS"},{"issue":"3","key":"ref79","volume":"2","author":"Zhao","year":"2023","journal-title":"Controlvideo: Adding conditional control for one shot text-to-video editing"}],"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\/11445743.pdf?arnumber=11445743","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T04:57:18Z","timestamp":1777611438000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11445743\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":79,"URL":"https:\/\/doi.org\/10.1109\/iccv51701.2025.01485","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}