{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,13]],"date-time":"2026-10-13T17:33:11Z","timestamp":1791912791240,"version":"4.3.4"},"publisher-location":"New York, NY, USA","reference-count":71,"publisher":"ACM","funder":[{"name":"Hong Kong Research Grants Council","award":["GRF-15229423"],"award-info":[{"award-number":["GRF-15229423"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2025,10,27]]},"DOI":"10.1145\/3746027.3755010","type":"proceedings-article","created":{"date-parts":[[2025,10,25]],"date-time":"2025-10-25T05:47:42Z","timestamp":1761371262000},"page":"9598-9607","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":5,"title":["DiffArtist: Towards Structure and Appearance Controllable Image Stylization"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-8666-6767","authenticated-orcid":false,"given":"Ruixiang","family":"Jiang","sequence":"first","affiliation":[{"name":"Computing, The Hong Kong Polytechnic University, Hong Kong, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6720-234X","authenticated-orcid":false,"given":"Chang Wen","family":"Chen","sequence":"additional","affiliation":[{"name":"Computing, The Hong Kong Polytechnic University, Hong Kong, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2025,10,27]]},"reference":[{"key":"e_1_3_2_1_1_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00092"},{"key":"e_1_3_2_1_2_1","volume-title":"Training diffusion models with reinforcement learning. arXiv preprint arXiv:2305.13301","author":"Black Kevin","year":"2023","unstructured":"Kevin Black, Michael Janner, Yilun Du, Ilya Kostrikov, and Sergey Levine. 2023. Training diffusion models with reinforcement learning. arXiv preprint arXiv:2305.13301 (2023)."},{"key":"e_1_3_2_1_3_1","volume-title":"Computational aesthetics and applications. Visual computing for industry, biomedicine, and art","author":"Bo Yihang","year":"2018","unstructured":"Yihang Bo, Jinhui Yu, and Kang Zhang. 2018. Computational aesthetics and applications. Visual computing for industry, biomedicine, and art, Vol. 1 (2018), 1-19."},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01764"},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01701"},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2024.3410672"},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3612524"},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00840"},{"key":"e_1_3_2_1_9_1","volume-title":"Directly fine-tuning diffusion models on differentiable rewards. arXiv preprint arXiv:2309.17400","author":"Clark Kevin","year":"2023","unstructured":"Kevin Clark, Paul Vicol, Kevin Swersky, and David J Fleet. 2023. Directly fine-tuning diffusion models on differentiable rewards. arXiv preprint arXiv:2309.17400 (2023)."},{"key":"e_1_3_2_1_10_1","volume-title":"Huaibo Huang, and Zhaofeng He.","author":"Cui Xing","year":"2023","unstructured":"Xing Cui, Zekun Li, Pei Pei Li, Huaibo Huang, and Zhaofeng He. 2023. InstaStyle: Inversion Noise of a Stylized Image is Secretly a Style Adviser. arXiv preprint arXiv:2311.15040 (2023)."},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01104"},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.1145\/3664647.3681310"},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.1145\/3528223.3530164"},{"key":"e_1_3_2_1_14_1","volume-title":"Styleshot: A snapshot on any style. arXiv preprint arXiv:2407.01414","author":"Gao Junyao","year":"2024","unstructured":"Junyao Gao, Yanchen Liu, Yanan Sun, Yinhao Tang, Yanhong Zeng, Kai Chen, and Cairong Zhao. 2024. Styleshot: A snapshot on any style. arXiv preprint arXiv:2407.01414 (2024)."},{"key":"e_1_3_2_1_15_1","volume-title":"A neural algorithm of artistic style. arXiv preprint arXiv:1508.06576","author":"Gatys Leon A","year":"2015","unstructured":"Leon A Gatys, Alexander S Ecker, and Matthias Bethge. 2015. A neural algorithm of artistic style. arXiv preprint arXiv:1508.06576 (2015)."},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.265"},{"key":"e_1_3_2_1_17_1","volume-title":"The story of art","author":"Gombrich Ernst Hans","unstructured":"Ernst Hans Gombrich and EH Gombrich. 1995. The story of art. Vol. 12. Phaidon London."},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"crossref","unstructured":"Nelson Goodman. 1976. Languages of art: An approach to a theory of symbols. Hackett.","DOI":"10.5040\/9781350928541"},{"key":"e_1_3_2_1_19_1","volume-title":"Freestyle: Free lunch for text-guided style transfer using diffusion models. arXiv preprint arXiv:2401.15636","author":"He Feihong","year":"2024","unstructured":"Feihong He, Gang Li, Mengyuan Zhang, Leilei Yan, Lingyu Si, Fanzhang Li, and Li Shen. 2024. Freestyle: Free lunch for text-guided style transfer using diffusion models. arXiv preprint arXiv:2401.15636 (2024)."},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00221"},{"key":"e_1_3_2_1_21_1","volume-title":"Prompt-to-prompt image editing with cross attention control. arXiv preprint arXiv:2208.01626","author":"Hertz Amir","year":"2022","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:2208.01626 (2022)."},{"key":"e_1_3_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00457"},{"key":"e_1_3_2_1_23_1","volume-title":"Gans trained by a two time-scale update rule converge to a local nash equilibrium. Advances in neural information processing systems","author":"Heusel Martin","year":"2017","unstructured":"Martin Heusel, Hubert Ramsauer, Thomas Unterthiner, Bernhard Nessler, and Sepp Hochreiter. 2017. Gans trained by a two time-scale update rule converge to a local nash equilibrium. Advances in neural information processing systems, Vol. 30 (2017)."},{"key":"e_1_3_2_1_24_1","volume-title":"Diffstyler: Controllable dual diffusion for text-driven image stylization","author":"Huang Nisha","year":"2024","unstructured":"Nisha Huang, Yuxin Zhang, Fan Tang, Chongyang Ma, Haibin Huang, Weiming Dong, and Changsheng Xu. 2024. Diffstyler: Controllable dual diffusion for text-driven image stylization. IEEE Transactions on Neural Networks and Learning Systems (2024)."},{"key":"e_1_3_2_1_25_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.167"},{"key":"e_1_3_2_1_26_1","volume-title":"Ideogram: Explore. https:\/\/ideogram.ai\/t\/explore Accessed: 2024-03-20.","year":"2024","unstructured":"Ideogram. 2024. Ideogram: Explore. https:\/\/ideogram.ai\/t\/explore Accessed: 2024-03-20."},{"key":"e_1_3_2_1_27_1","volume-title":"Computer Graphics Forum","author":"Ioannou Eleftherios","unstructured":"Eleftherios Ioannou and Steve Maddock. 2024. Evaluation in Neural Style Transfer: A Review. In Computer Graphics Forum. Wiley Online Library, e15165."},{"key":"e_1_3_2_1_28_1","volume-title":"Multimodal LLMs Can Reason about Aesthetics in Zero-Shot. arXiv preprint arXiv:2501.09012","author":"Jiang Ruixiang","year":"2025","unstructured":"Ruixiang Jiang and Changwen Chen. 2025. Multimodal LLMs Can Reason about Aesthetics in Zero-Shot. arXiv preprint arXiv:2501.09012 (2025)."},{"key":"e_1_3_2_1_29_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01322"},{"key":"e_1_3_2_1_30_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00818"},{"key":"e_1_3_2_1_31_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00582"},{"key":"e_1_3_2_1_32_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00246"},{"key":"e_1_3_2_1_33_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58574-7_15"},{"key":"e_1_3_2_1_34_1","first-page":"36652","article-title":"Pick-a-pic: An open dataset of user preferences for text-to-image generation","volume":"36","author":"Kirstain Yuval","year":"2023","unstructured":"Yuval Kirstain, Adam Polyak, Uriel Singer, Shahbuland Matiana, Joe Penna, and Omer Levy. 2023. Pick-a-pic: An open dataset of user preferences for text-to-image generation. Advances in Neural Information Processing Systems, Vol. 36 (2023), 36652-36663.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_1_35_1","volume-title":"Machel Reid, Yutaka Matsuo, and Yusuke Iwasawa.","author":"Kojima Takeshi","year":"2022","unstructured":"Takeshi Kojima, Shixiang Shane Gu, Machel Reid, Yutaka Matsuo, and Yusuke Iwasawa. 2022. Large language models are zero-shot reasoners. Advances in neural information processing systems, Vol. 35 (2022), 22199-22213."},{"key":"e_1_3_2_1_36_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00452"},{"key":"e_1_3_2_1_37_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01753"},{"key":"e_1_3_2_1_38_1","volume-title":"M2iv: Towards efficient and fine-grained multimodal in-context learning in large vision-language models. arXiv preprint arXiv:2504.04633","author":"Li Yanshu","year":"2025","unstructured":"Yanshu Li, Hongyang He, Yi Cao, Qisen Cheng, Xiang Fu, and Ruixiang Tang. 2025a. M2iv: Towards efficient and fine-grained multimodal in-context learning in large vision-language models. arXiv preprint arXiv:2504.04633 (2025)."},{"key":"e_1_3_2_1_39_1","volume-title":"Demystifying neural style transfer. arXiv preprint arXiv:1701.01036","author":"Li Yanghao","year":"2017","unstructured":"Yanghao Li, Naiyan Wang, Jiaying Liu, and Xiaodi Hou. 2017. Demystifying neural style transfer. arXiv preprint arXiv:1701.01036 (2017)."},{"key":"e_1_3_2_1_40_1","volume-title":"TACO: Enhancing Multimodal In-context Learning via Task Mapping-Guided Sequence Configuration. arXiv preprint arXiv:2505.17098","author":"Li Yanshu","year":"2025","unstructured":"Yanshu Li, Tian Yun, Jianjiang Yang, Pinyuan Feng, Jinfa Huang, and Ruixiang Tang. 2025b. TACO: Enhancing Multimodal In-context Learning via Task Mapping-Guided Sequence Configuration. arXiv preprint arXiv:2505.17098 (2025)."},{"key":"e_1_3_2_1_41_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01835"},{"key":"e_1_3_2_1_42_1","first-page":"128911","article-title":"Ctrl-x: Controlling structure and appearance for text-to-image generation without guidance","volume":"37","author":"Lin Kuan Heng","year":"2024","unstructured":"Kuan Heng 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, Vol. 37 (2024), 128911-128939.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_1_43_1","first-page":"740","volume-title":"Switzerland","author":"Lin Tsung-Yi","year":"2014","unstructured":"Tsung-Yi Lin, Michael Maire, Serge Belongie, James Hays, Pietro Perona, Deva Ramanan, Piotr Doll\u00e1r, and C Lawrence Zitnick. 2014. Microsoft coco: Common objects in context. In Computer vision-ECCV 2014: 13th European conference, zurich, Switzerland, September 6-12, 2014, proceedings, part v 13. Springer, 740-755."},{"key":"e_1_3_2_1_44_1","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2023.3300906"},{"key":"e_1_3_2_1_45_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01313"},{"key":"e_1_3_2_1_46_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00585"},{"key":"e_1_3_2_1_47_1","volume-title":"Dreamfusion: Text-to-3d using 2d diffusion. arXiv preprint arXiv:2209.14988","author":"Poole Ben","year":"2022","unstructured":"Ben Poole, Ajay Jain, Jonathan T Barron, and Ben Mildenhall. 2022. Dreamfusion: Text-to-3d using 2d diffusion. arXiv preprint arXiv:2209.14988 (2022)."},{"key":"e_1_3_2_1_48_1","volume-title":"International conference on machine learning. PMLR, 8748-8763","author":"Radford Alec","year":"2021","unstructured":"Alec Radford, Jong Wook Kim, Chris Hallacy, Aditya Ramesh, Gabriel Goh, Sandhini Agarwal, Girish Sastry, Amanda Askell, Pamela Mishkin, Jack Clark, et al., 2021. Learning transferable visual models from natural language supervision. In International conference on machine learning. PMLR, 8748-8763."},{"key":"e_1_3_2_1_49_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01237-3_43"},{"key":"e_1_3_2_1_50_1","doi-asserted-by":"publisher","DOI":"10.1080\/10447318.2022.2049081"},{"key":"e_1_3_2_1_51_1","volume-title":"Denoising diffusion implicit models. arXiv preprint arXiv:2010.02502","author":"Song Jiaming","year":"2020","unstructured":"Jiaming Song, Chenlin Meng, and Stefano Ermon. 2020. Denoising diffusion implicit models. arXiv preprint arXiv:2010.02502 (2020)."},{"key":"e_1_3_2_1_52_1","volume-title":"The handbook of visual analysis","author":"Leeuwen Theo Van","unstructured":"Theo Van Leeuwen and Carey Jewitt. 2000. The handbook of visual analysis. Sage."},{"key":"e_1_3_2_1_53_1","volume-title":"Nerf-art: Text-driven neural radiance fields stylization","author":"Wang Can","year":"2023","unstructured":"Can Wang, Ruixiang Jiang, Menglei Chai, Mingming He, Dongdong Chen, and Jing Liao. 2023a. Nerf-art: Text-driven neural radiance fields stylization. IEEE Transactions on Visualization and Computer Graphics (2023)."},{"key":"e_1_3_2_1_54_1","volume-title":"Instantstyle: Free lunch towards style-preserving in text-to-image generation. arXiv preprint arXiv:2404.02733","author":"Wang Haofan","year":"2024","unstructured":"Haofan Wang, Qixun Wang, Xu Bai, Zekui Qin, and Anthony Chen. 2024a. Instantstyle: Free lunch towards style-preserving in text-to-image generation. arXiv preprint arXiv:2404.02733 (2024)."},{"key":"e_1_3_2_1_55_1","volume-title":"Instantstyle-plus: Style transfer with content-preserving in text-to-image generation. arXiv preprint arXiv:2407.00788","author":"Wang Haofan","year":"2024","unstructured":"Haofan Wang, Peng Xing, Renyuan Huang, Hao Ai, Qixun Wang, and Xu Bai. 2024b. Instantstyle-plus: Style transfer with content-preserving in text-to-image generation. arXiv preprint arXiv:2407.00788 (2024)."},{"key":"e_1_3_2_1_56_1","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2022.3215899"},{"key":"e_1_3_2_1_57_1","volume-title":"Image quality assessment: from error visibility to structural similarity","author":"Wang Zhou","year":"2004","unstructured":"Zhou Wang, Alan C Bovik, Hamid R Sheikh, and Eero P Simoncelli. 2004. Image quality assessment: from error visibility to structural similarity. IEEE transactions on image processing, Vol. 13, 4 (2004), 600-612."},{"key":"e_1_3_2_1_58_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00706"},{"key":"e_1_3_2_1_59_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01755"},{"key":"e_1_3_2_1_60_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-16788-1_34"},{"key":"e_1_3_2_1_61_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00768"},{"key":"e_1_3_2_1_62_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.02091"},{"key":"e_1_3_2_1_63_1","volume-title":"Ip-adapter: Text compatible image prompt adapter for text-to-image diffusion models. arXiv preprint arXiv:2308.06721","author":"Ye Hu","year":"2023","unstructured":"Hu Ye, Jun Zhang, Sibo Liu, Xiao Han, and Wei Yang. 2023. Ip-adapter: Text compatible image prompt adapter for text-to-image diffusion models. arXiv preprint arXiv:2308.06721 (2023)."},{"key":"e_1_3_2_1_64_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02144"},{"key":"e_1_3_2_1_65_1","volume-title":"Mm-llms: Recent advances in multimodal large language models. arXiv preprint arXiv:2401.13601","author":"Zhang Duzhen","year":"2024","unstructured":"Duzhen Zhang, Yahan Yu, Jiahua Dong, Chenxing Li, Dan Su, Chenhui Chu, and Dong Yu. 2024. Mm-llms: Recent advances in multimodal large language models. arXiv preprint arXiv:2401.13601 (2024)."},{"key":"e_1_3_2_1_66_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00355"},{"key":"e_1_3_2_1_67_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00068"},{"key":"e_1_3_2_1_68_1","doi-asserted-by":"publisher","DOI":"10.1145\/3618342"},{"key":"e_1_3_2_1_69_1","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2020.2969081"},{"key":"e_1_3_2_1_70_1","volume-title":"Multimodal chain-of-thought reasoning in language models. arXiv preprint arXiv:2302.00923","author":"Zhang Zhuosheng","year":"2023","unstructured":"Zhuosheng Zhang, Aston Zhang, Mu Li, Hai Zhao, George Karypis, and Alex Smola. 2023c. Multimodal chain-of-thought reasoning in language models. arXiv preprint arXiv:2302.00923 (2023)."},{"key":"e_1_3_2_1_71_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00744"}],"event":{"name":"MM '25: The 33rd ACM International Conference on Multimedia","location":"Dublin Ireland","acronym":"MM '25","sponsor":["SIGMM ACM Special Interest Group on Multimedia"]},"container-title":["Proceedings of the 33rd ACM International Conference on Multimedia"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3746027.3755010","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,12,9]],"date-time":"2025-12-09T19:19:21Z","timestamp":1765307961000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3746027.3755010"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,27]]},"references-count":71,"alternative-id":["10.1145\/3746027.3755010","10.1145\/3746027"],"URL":"https:\/\/doi.org\/10.1145\/3746027.3755010","relation":{},"subject":[],"published":{"date-parts":[[2025,10,27]]},"assertion":[{"value":"2025-10-27","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}