{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,6]],"date-time":"2026-05-06T07:13:46Z","timestamp":1778051626024,"version":"3.51.4"},"reference-count":57,"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"}],"funder":[{"DOI":"10.13039\/501100001321","name":"National Research Foundation","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100001321","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001321","name":"National Research Foundation","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100001321","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100010002","name":"Ministry of Education","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100010002","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100010002","name":"Ministry of Education","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100010002","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2026,3,6]]},"DOI":"10.1109\/wacv61042.2026.00708","type":"proceedings-article","created":{"date-parts":[[2026,5,5]],"date-time":"2026-05-05T19:59:32Z","timestamp":1778011172000},"page":"7333-7343","source":"Crossref","is-referenced-by-count":0,"title":["VideoSketcher: A Training-Free Approach for Coherent Video Sketch Transfer"],"prefix":"10.1109","author":[{"given":"Huining","family":"Li","sequence":"first","affiliation":[{"name":"Singapore Management University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Bangzhen","family":"Liu","sequence":"additional","affiliation":[{"name":"Singapore Management University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Rui","family":"Yang","sequence":"additional","affiliation":[{"name":"Huaqiao University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yang","family":"Zhou","sequence":"additional","affiliation":[{"name":"Singapore Management University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Chenshu","family":"Xu","sequence":"additional","affiliation":[{"name":"Singapore Management University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xufang","family":"Pang","sequence":"additional","affiliation":[{"name":"Shenzhen Institute of Artificial Intelligence and Robotics for Society"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Shengfeng","family":"He","sequence":"additional","affiliation":[{"name":"Singapore Management University"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1145\/3641519.3657423"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1145\/3550454.3555504"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19784-0_41"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1145\/2816795.2818107"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.02062"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.02121"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00840"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v39i3.32277"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00675"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00414"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00414"},{"key":"ref12","author":"Hertz","year":"2022","journal-title":"Prompt-to-prompt image editing with cross attention control"},{"key":"ref13","first-page":"30","article-title":"Gans trained by a two time-scale update rule converge to a local nash equilibrium","author":"Heusel","year":"2017","journal-title":"Adv. Neural Inform. Process. Syst."},{"key":"ref14","first-page":"6840","article-title":"Denoising diffusion probabilistic models","volume":"33","author":"Ho","year":"2020","journal-title":"Adv. Neural Inform. Process. Syst."},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.52202\/068431-0628"},{"key":"ref16","author":"Hu","year":"2021","journal-title":"Lora: Low-rank adaptation of large language models"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2024.3398538"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01185"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01462"},{"key":"ref20","author":"Ku","year":"2024","journal-title":"Anyv2v: A plug-and-play framework for any video-to-video editing tasks"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01267-0_11"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1112\/S0024610799008352"},{"issue":"6","key":"ref23","first-page":"1","article-title":"Differentiable vector graphics rasterization for editing and learning","volume":"39","author":"Li","year":"2020","journal-title":"ACM Trans. Graph."},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.52202\/079017-4308"},{"key":"ref25","author":"Liu","year":"2023","journal-title":"Stylecrafter: Enhancing stylized text-to-video generation with style adapter"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00644"},{"key":"ref27","first-page":"8162","article-title":"Improved denoising diffusion probabilistic models","volume-title":"Int. Conf. Mach. Learn","author":"Nichol"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00890"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.85"},{"key":"ref30","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"Int. Conf. Mach. Learn","author":"Radford"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-24574-4_28"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02155"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1145\/3592392"},{"key":"ref35","author":"Su","year":"2025","journal-title":"Safe-sora: Safe text-to-video generation via graphical watermarking"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1145\/3528223.3530068"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00383"},{"key":"ref38","author":"Wang","year":"2024","journal-title":"Instantstyle: Free lunch towards style-preserving in text-to-image generation"},{"key":"ref39","author":"Wang","year":"2024","journal-title":"InstantStyle-Plus: Style Transfer with Content-Preserving in Text-to-Image Generation"},{"key":"ref40","author":"Wang","year":"2023","journal-title":"Zero-shot video editing using off-the-shelf image diffusion models"},{"key":"ref41","author":"Wang","year":"2024","journal-title":"Zero-Shot Video Editing Using Off-The-Shelf Image Diffusion Models"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.52202\/075280-0334"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-16788-1_34"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00701"},{"key":"ref45","author":"Wu","year":"2023","journal-title":"Cvpr 2023 text guided video editing competition"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/TVCG.2024.3502395"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51701.2025.01536"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1145\/3610548.3618160"},{"key":"ref49","author":"Yang","year":"2024","journal-title":"Cogvideox: Text-to-video diffusion models with an expert transformer"},{"key":"ref50","author":"Ye","year":"2023","journal-title":"Ipadapter: Text compatible image prompt adapter for text-to-image diffusion models"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52734.2025.00251"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00679"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00355"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00068"},{"key":"ref55","author":"Zhang","year":"2023","journal-title":"Controlvideo: Training-free controllable text-to-video generation"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1111\/cgf.15044"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1111\/cgf.15044"}],"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\/11492263.pdf?arnumber=11492263","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,6]],"date-time":"2026-05-06T06:20:03Z","timestamp":1778048403000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11492263\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,3,6]]},"references-count":57,"URL":"https:\/\/doi.org\/10.1109\/wacv61042.2026.00708","relation":{},"subject":[],"published":{"date-parts":[[2026,3,6]]}}}