{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,6]],"date-time":"2026-05-06T07:19:13Z","timestamp":1778051953013,"version":"3.51.4"},"reference-count":43,"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\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100001809","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\/wacv61042.2026.00452","type":"proceedings-article","created":{"date-parts":[[2026,5,5]],"date-time":"2026-05-05T19:59:32Z","timestamp":1778011172000},"page":"4651-4660","source":"Crossref","is-referenced-by-count":0,"title":["Towards Photorealistic Style Transfer with Multimodal Guidance and Robustness to Content Images in Arbitrary Styles"],"prefix":"10.1109","author":[{"given":"Ruikai","family":"Zhou","sequence":"first","affiliation":[{"name":"Shanghai Jiao Tong University,Shanghai,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yating","family":"Liu","sequence":"additional","affiliation":[{"name":"Shanghai Jiao Tong University,Shanghai,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yi","family":"Xu","sequence":"additional","affiliation":[{"name":"Shanghai Jiao Tong University,Shanghai,China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1111\/cgf.15127"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i07.6614"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01767"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01764"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2011.5995413"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2025.3530822"},{"key":"ref7","article-title":"Nlut: Neural-based 3d lookup tables for video photorealistic style transfer","author":"Chen","year":"2023"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/WACV51458.2022.00303"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00840"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00662"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20059-5_41"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1145\/3528223.3530164"},{"key":"ref13","article-title":"Open-vocabulary object detection via vision and language knowledge distillation","volume-title":"International Conference on Learning Representations (ICLR)","author":"Gu"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1007\/s00371-025-03799-8"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01362"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00246"},{"key":"ref17","article-title":"Adam: A method for stochastic optimization","author":"Kingma","year":"2014"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01753"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00284"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/WACV61041.2025.00892"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1145\/3732801.3732802"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01219-9_28"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i2.25248"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.740"},{"key":"ref26","article-title":"Superedit: Rectifying and facilitating supervision for instruction-based image editing","volume-title":"Proceedings of the IEEE\/CVF International Conference on Computer Vision (ICCV)","author":"Chen"},{"key":"ref27","article-title":"Clip-cap: Clip prefix for image captioning","author":"Mokady","year":"2021"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00603"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00209"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2005.166"},{"key":"ref31","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"International Conference on Machine Learning (ICML)","author":"Radford"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/38.946629"},{"key":"ref33","first-page":"6105","article-title":"Efficientnet: Rethinking model scaling for convolutional neural networks","volume-title":"International Conference on Machine Learning (ICML)","author":"Tan"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/WACV57701.2024.00490"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i2.25353"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52729.2023.01755"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58598-3_20"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1111\/j.1467-8659.2009.01566.x"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/WACV57701.2024.00504"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.02091"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00913"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i7.28529"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00978"}],"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\/11492633.pdf?arnumber=11492633","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,6]],"date-time":"2026-05-06T06:33:35Z","timestamp":1778049215000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11492633\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,3,6]]},"references-count":43,"URL":"https:\/\/doi.org\/10.1109\/wacv61042.2026.00452","relation":{},"subject":[],"published":{"date-parts":[[2026,3,6]]}}}