{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,15]],"date-time":"2026-06-15T14:56:02Z","timestamp":1781535362067,"version":"3.54.5"},"publisher-location":"New York, NY, USA","reference-count":52,"publisher":"ACM","license":[{"start":{"date-parts":[[2026,6,15]],"date-time":"2026-06-15T00:00:00Z","timestamp":1781481600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/legalcode"}],"funder":[{"name":"Sichuan Provincial Science and Technology Program","award":["2026NSFSC0430"],"award-info":[{"award-number":["2026NSFSC0430"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2026,6,16]]},"DOI":"10.1145\/3805622.3810798","type":"proceedings-article","created":{"date-parts":[[2026,6,15]],"date-time":"2026-06-15T14:42:57Z","timestamp":1781534577000},"page":"1812-1821","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["FreSCo: Joint Frequency-Aware and Spatial Control for Image Zero-Shot Style Transfer"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0005-7705-7587","authenticated-orcid":false,"given":"Tingrun","family":"Chen","sequence":"first","affiliation":[{"name":"University of Electronic Science and Technology of China, Chengdu, Sichuan, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0009-1128-8322","authenticated-orcid":false,"given":"Xudong","family":"Ling","sequence":"additional","affiliation":[{"name":"University of Electronic Science and Technology of China, Chengdu, Sichuan, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5744-2035","authenticated-orcid":false,"given":"Shicai","family":"Wei","sequence":"additional","affiliation":[{"name":"University of Electronic Science and Technology of China, Chengdu, Sichuan, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6857-7744","authenticated-orcid":false,"given":"Guiduo","family":"Duan","sequence":"additional","affiliation":[{"name":"University of Electronic Science and Technology of China, Chengdu, Sichuan, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7486-5264","authenticated-orcid":false,"given":"Yue","family":"Zhang","sequence":"additional","affiliation":[{"name":"University of Electronic Science and Technology of China, Chengdu, Sichuan, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2026,6,15]]},"reference":[{"key":"e_1_3_3_1_2_2","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i2.27824"},{"key":"e_1_3_3_1_3_2","doi-asserted-by":"publisher","DOI":"10.1145\/3641519.3657423"},{"key":"e_1_3_3_1_4_2","doi-asserted-by":"crossref","unstructured":"Omri Avrahami Ohad Fried and Dani Lischinski. 2023. Blended latent diffusion. ACM transactions on graphics (TOG) 42 4 (2023) 1\u201311.","DOI":"10.1145\/3592450"},{"key":"e_1_3_3_1_5_2","unstructured":"Eyal Benaroche Clement Chadebec Onur Tasar and Benjamin Aubin. 2024. Style-Rank: Benchmarking stylization for diffusion models."},{"key":"e_1_3_3_1_6_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.02062"},{"key":"e_1_3_3_1_7_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00823"},{"key":"e_1_3_3_1_8_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00793"},{"key":"e_1_3_3_1_9_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00840"},{"key":"e_1_3_3_1_10_2","unstructured":"Guillaume Couairon Jakob Verbeek Holger Schwenk and Matthieu Cord. 2022. Diffedit: Diffusion-based semantic image editing with mask guidance. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2210.11427 (2022)."},{"key":"e_1_3_3_1_11_2","unstructured":"Junyao Gao Yanan Sun Yanchen Liu Yinhao Tang Yanhong Zeng Ding Qi Kai Chen and Cairong Zhao. 2025. Styleshot: A snapshot on any style. IEEE Transactions on Pattern Analysis and Machine Intelligence (2025)."},{"key":"e_1_3_3_1_12_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.265"},{"key":"e_1_3_3_1_13_2","unstructured":"Feihong He Gang Li Fuhui Sun Mengyuan Zhang Lingyu Si Xiaoyan Wang and Li Shen. 2024. Freestyle: Free lunch for text-guided style transfer using diffusion models. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2401.15636 (2024)."},{"key":"e_1_3_3_1_14_2","unstructured":"Amir Hertz Ron Mokady Jay Tenenbaum Kfir Aberman Yael Pritch and Daniel Cohen-Or. 2022. Prompt-to-prompt image editing with cross attention control. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2208.01626 (2022)."},{"key":"e_1_3_3_1_15_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00457"},{"key":"e_1_3_3_1_16_2","unstructured":"Jonathan Ho Ajay Jain and Pieter Abbeel. 2020. Denoising diffusion probabilistic models. Advances in neural information processing systems 33 (2020) 6840\u20136851."},{"key":"e_1_3_3_1_17_2","unstructured":"Jonathan Ho and Tim Salimans. 2022. Classifier-free diffusion guidance. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2207.12598 (2022)."},{"key":"e_1_3_3_1_18_2","doi-asserted-by":"publisher","DOI":"10.1145\/3731715.3733366"},{"key":"e_1_3_3_1_19_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00576"},{"key":"e_1_3_3_1_20_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.167"},{"key":"e_1_3_3_1_21_2","doi-asserted-by":"crossref","unstructured":"Quan Huynh-Thu and Mohammed Ghanbari. 2008. Scope of validity of PSNR in image\/video quality assessment. Electronics letters 44 13 (2008) 800\u2013801.","DOI":"10.1049\/el:20080522"},{"key":"e_1_3_3_1_22_2","unstructured":"Jaeseok Jeong Junho Kim Yunjey Choi Gayoung Lee and Youngjung Uh. 2024. Visual style prompting with swapping self-attention. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2402.12974 (2024)."},{"key":"e_1_3_3_1_23_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46475-6_43"},{"key":"e_1_3_3_1_24_2","unstructured":"Xuan Ju Ailing Zeng Yuxuan Bian Shaoteng Liu and Qiang Xu. 2024. PnP Inversion: Boosting Diffusion-based Editing with 3 Lines of Code. International Conference on Learning Representations (ICLR) (2024)."},{"key":"e_1_3_3_1_25_2","doi-asserted-by":"crossref","unstructured":"Kuan\u00a0Heng Lin Sicheng Mo Ben Klingher Fangzhou Mu and Bolei Zhou. 2024. Ctrl-x: Controlling structure and appearance for text-to-image generation without guidance. Advances in Neural Information Processing Systems 37 (2024) 128911\u2013128939.","DOI":"10.52202\/079017-4095"},{"key":"e_1_3_3_1_26_2","doi-asserted-by":"publisher","DOI":"10.1145\/3652583.3658071"},{"key":"e_1_3_3_1_27_2","doi-asserted-by":"publisher","DOI":"10.1109\/WACV61041.2025.00207"},{"key":"e_1_3_3_1_28_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00713"},{"key":"e_1_3_3_1_29_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00585"},{"key":"e_1_3_3_1_30_2","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i5.28226"},{"key":"e_1_3_3_1_31_2","unstructured":"Maxime Oquab Timoth\u00e9e Darcet Th\u00e9o Moutakanni Huy Vo Marc Szafraniec Vasil Khalidov Pierre Fernandez Daniel Haziza Francisco Massa Alaaeldin El-Nouby et\u00a0al. 2023. Dinov2: Learning robust visual features without supervision. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2304.07193 (2023)."},{"key":"e_1_3_3_1_32_2","unstructured":"Dustin Podell Zion English Kyle Lacey Andreas Blattmann Tim Dockhorn Jonas M\u00fcller Joe Penna and Robin Rombach. 2023. Sdxl: Improving latent diffusion models for high-resolution image synthesis. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2307.01952 (2023)."},{"key":"e_1_3_3_1_33_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00830"},{"key":"e_1_3_3_1_34_2","first-page":"8748","volume-title":"International conference on machine learning","author":"Radford Alec","year":"2021","unstructured":"Alec Radford, Jong\u00a0Wook Kim, Chris Hallacy, Aditya Ramesh, Gabriel Goh, Sandhini Agarwal, Girish Sastry, Amanda Askell, Pamela Mishkin, Jack Clark, et\u00a0al. 2021. Learning transferable visual models from natural language supervision. In International conference on machine learning. PmLR, 8748\u20138763."},{"key":"e_1_3_3_1_35_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"e_1_3_3_1_36_2","doi-asserted-by":"crossref","unstructured":"Leonid\u00a0I Rudin Stanley Osher and Emad Fatemi. 1992. Nonlinear total variation based noise removal algorithms. Physica D: nonlinear phenomena 60 1-4 (1992) 259\u2013268.","DOI":"10.1016\/0167-2789(92)90242-F"},{"key":"e_1_3_3_1_37_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00453"},{"key":"e_1_3_3_1_38_2","unstructured":"Kihyuk Sohn Nataniel Ruiz Kimin Lee Daniel\u00a0Castro Chin Irina Blok Huiwen Chang Jarred Barber Lu Jiang Glenn Entis Yuanzhen Li et\u00a0al. 2023. Styledrop: Text-to-image generation in any style. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2306.00983 (2023)."},{"key":"e_1_3_3_1_39_2","unstructured":"Jiaming Song Chenlin Meng and Stefano Ermon. 2020. Denoising diffusion implicit models. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2010.02502 (2020)."},{"key":"e_1_3_3_1_40_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00507"},{"key":"e_1_3_3_1_41_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00191"},{"key":"e_1_3_3_1_42_2","unstructured":"Haofan Wang Matteo Spinelli Qixun Wang Xu Bai Zekui Qin and Anthony Chen. 2024. Instantstyle: Free lunch towards style-preserving in text-to-image generation. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2404.02733 (2024)."},{"key":"e_1_3_3_1_43_2","unstructured":"Qixun Wang Xu Bai Haofan Wang Zekui Qin Anthony Chen Huaxia Li Xu Tang and Yao Hu. 2024. Instantid: Zero-shot identity-preserving generation in seconds. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2401.07519 (2024)."},{"key":"e_1_3_3_1_44_2","first-page":"15802","volume-title":"Proceedings of the IEEE\/CVF International Conference on Computer Vision","author":"Wang Xinbo","year":"2025","unstructured":"Xinbo Wang, Wenju Xu, Qing Zhang, and Wei-Shi Zheng. 2025. Domain generalizable portrait style transfer. In Proceedings of the IEEE\/CVF International Conference on Computer Vision. 15802\u201315811."},{"key":"e_1_3_3_1_45_2","doi-asserted-by":"crossref","unstructured":"Zhou Wang Alan\u00a0C Bovik Hamid\u00a0R Sheikh and Eero\u00a0P Simoncelli. 2004. Image quality assessment: from error visibility to structural similarity. IEEE transactions on image processing 13 4 (2004) 600\u2013612.","DOI":"10.1109\/TIP.2003.819861"},{"key":"e_1_3_3_1_46_2","doi-asserted-by":"publisher","DOI":"10.1145\/3591106.3592262"},{"key":"e_1_3_3_1_47_2","unstructured":"Peng Xing Haofan Wang Yanpeng Sun Qixun Wang Xu Bai Hao Ai Renyuan Huang and Zechao Li. 2024. Csgo: Content-style composition in text-to-image generation. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2408.16766 (2024)."},{"key":"e_1_3_3_1_48_2","unstructured":"Ruojun Xu Weijie Xi Xiaodi Wang Yongbo Mao and Zach Cheng. 2025. StyleSSP: Sampling StartPoint Enhancement for Training-free Diffusion-based Method for Style Transfer. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2501.11319 (2025)."},{"key":"e_1_3_3_1_49_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00355"},{"key":"e_1_3_3_1_50_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00068"},{"key":"e_1_3_3_1_51_2","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2025\/266"},{"key":"e_1_3_3_1_52_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00978"},{"key":"e_1_3_3_1_53_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.244"}],"event":{"name":"ICMR '26: International Conference on Multimedia Retrieval","location":"Amsterdam The Netherlands","acronym":"ICMR '26","sponsor":["SIGMM ACM Special Interest Group on Multimedia"]},"container-title":["Proceedings of the 2026 International Conference on Multimedia Retrieval"],"original-title":[],"deposited":{"date-parts":[[2026,6,15]],"date-time":"2026-06-15T14:46:14Z","timestamp":1781534774000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3805622.3810798"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,6,15]]},"references-count":52,"alternative-id":["10.1145\/3805622.3810798","10.1145\/3805622"],"URL":"https:\/\/doi.org\/10.1145\/3805622.3810798","relation":{},"subject":[],"published":{"date-parts":[[2026,6,15]]},"assertion":[{"value":"2026-06-15","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}