{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,15]],"date-time":"2025-11-15T08:09:56Z","timestamp":1763194196822,"version":"3.45.0"},"reference-count":36,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,6,30]],"date-time":"2025-06-30T00:00:00Z","timestamp":1751241600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,6,30]],"date-time":"2025-06-30T00:00:00Z","timestamp":1751241600000},"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":[[2025,6,30]]},"DOI":"10.1109\/ijcnn64981.2025.11228439","type":"proceedings-article","created":{"date-parts":[[2025,11,14]],"date-time":"2025-11-14T18:46:15Z","timestamp":1763145975000},"page":"1-8","source":"Crossref","is-referenced-by-count":0,"title":["AnyStyler: Adding Style Control in Diffusion Models to Any Modality Stylization"],"prefix":"10.1109","author":[{"given":"Wuqin","family":"Liu","sequence":"first","affiliation":[{"name":"Kuaishou Technology,Safety Compliance Line - User Experience Department,Beijing,China"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00978"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i2.27824"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02155"},{"key":"ref4","first-page":"19822","article-title":"Cogview: Mastering text-to-image generation via transformers","volume":"34","author":"Ding","year":"2021","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19784-0_6"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i5.28226"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1167\/16.12.326"},{"article-title":"Instance normalization: The missing ingredient for fast stylization","year":"2016","author":"Ulyanov","key":"ref8"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.244"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00093"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1145\/3450525"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01104"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-45886-1_3"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-018-1089-z"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.438"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.745"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.126"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/WACV45572.2020.9093420"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00393"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i2.16208"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00658"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19787-1_11"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.02152"},{"article-title":"Tokenflow: Consistent diffusion features for consistent video editing","year":"2023","author":"Geyer","key":"ref24"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01462"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01460"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00701"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1145\/3610548.3618160"},{"article-title":"Soundini: Sound-guided diffusion for natural video editing","year":"2023","author":"Lee","key":"ref29"},{"article-title":"Videocrafter1: Open diffusion models for high-quality video generation","year":"2023","author":"Chen","key":"ref30"},{"key":"ref31","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"International Conference on Machine Learning","author":"Radford"},{"article-title":"p+: Ex-tended textual conditioning in text-to-image generation","year":"2023","author":"Voynov","key":"ref32"},{"article-title":"An image is worth one word: Personalizing text-to-image generation using textual inversion","year":"2022","author":"Gal","key":"ref33"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00192"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.02080"},{"key":"ref36","first-page":"26561","article-title":"Artistic style transfer with internal-external learning and contrastive learning","volume":"34","author":"Chen","year":"2021","journal-title":"Advances in Neural Information Processing Systems"}],"event":{"name":"2025 International Joint Conference on Neural Networks (IJCNN)","start":{"date-parts":[[2025,6,30]]},"location":"Rome, Italy","end":{"date-parts":[[2025,7,5]]}},"container-title":["2025 International Joint Conference on Neural Networks (IJCNN)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11227166\/11227148\/11228439.pdf?arnumber=11228439","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,11,15]],"date-time":"2025-11-15T08:06:26Z","timestamp":1763193986000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11228439\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,6,30]]},"references-count":36,"URL":"https:\/\/doi.org\/10.1109\/ijcnn64981.2025.11228439","relation":{},"subject":[],"published":{"date-parts":[[2025,6,30]]}}}