{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,7]],"date-time":"2026-05-07T20:56:54Z","timestamp":1778187414057,"version":"3.51.4"},"publisher-location":"New York, NY, USA","reference-count":82,"publisher":"ACM","license":[{"start":{"date-parts":[[2024,10,28]],"date-time":"2024-10-28T00:00:00Z","timestamp":1730073600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"DOI":"10.13039\/https:\/\/doi.org\/10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["U21B2045, U20A20223, 32341009, 62206277"],"award-info":[{"award-number":["U21B2045, U20A20223, 32341009, 62206277"]}],"id":[{"id":"10.13039\/https:\/\/doi.org\/10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Youth Innovation Promotion Association CAS","award":["2022132"],"award-info":[{"award-number":["2022132"]}]},{"DOI":"10.13039\/https:\/\/doi.org\/10.13039\/501100005090","name":"Beijing Nova Program","doi-asserted-by":"publisher","award":["20230484276"],"award-info":[{"award-number":["20230484276"]}],"id":[{"id":"10.13039\/https:\/\/doi.org\/10.13039\/501100005090","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2024,10,28]]},"DOI":"10.1145\/3664647.3680676","type":"proceedings-article","created":{"date-parts":[[2024,10,26]],"date-time":"2024-10-26T06:59:27Z","timestamp":1729925967000},"page":"3509-3518","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":6,"title":["ZePo: Zero-Shot Portrait Stylization with Faster Sampling"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0007-7320-5479","authenticated-orcid":false,"given":"Jin","family":"Liu","sequence":"first","affiliation":[{"name":"SIST, ShanghaiTech University & NLPR & MAIS, Institute of Automation, CAS, Shanghai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5866-2283","authenticated-orcid":false,"given":"Huaibo","family":"Huang","sequence":"additional","affiliation":[{"name":"NLPR & MAIS, Institute of Automation, CAS, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6368-4495","authenticated-orcid":false,"given":"Jie","family":"Cao","sequence":"additional","affiliation":[{"name":"NLPR & MAIS, Institute of Automation, CAS, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3807-991X","authenticated-orcid":false,"given":"Ran","family":"He","sequence":"additional","affiliation":[{"name":"NLPR & MAIS, Institute of Automation, CAS, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2024,10,28]]},"reference":[{"key":"e_1_3_2_1_1_1","doi-asserted-by":"crossref","unstructured":"Aibek Alanov Vadim Titov Maksim Nakhodnov and Dmitry Vetrov. 2023. Style-Domain: Efficient and Lightweight Parameterizations of StyleGAN for One-Shot and Few-Shot Domain Adaptation. In ICCV. 2184--2194.","DOI":"10.1109\/ICCV51070.2023.00208"},{"key":"e_1_3_2_1_2_1","unstructured":"Fan Bao Chongxuan Li Jun Zhu and Bo Zhang. 2021. Analytic-DPM: An Analytic Estimate of the Optimal Reverse Variance in Diffusion Probabilistic Models. In ICLR."},{"key":"e_1_3_2_1_3_1","volume-title":"Token Merging: Your ViT But Faster. arXiv:2210.09461","author":"Bolya Daniel","year":"2023","unstructured":"Daniel Bolya, Cheng-Yang Fu, Xiaoliang Dai, Peizhao Zhang, Christoph Feichtenhofer, and Judy Hoffman. 2023. Token Merging: Your ViT But Faster. arXiv:2210.09461"},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"crossref","unstructured":"Daniel Bolya and Judy Hoffman. 2023. Token Merging for Fast Stable Diffusion. In CVPR. 4598--4602.","DOI":"10.1109\/CVPRW59228.2023.00484"},{"key":"e_1_3_2_1_5_1","unstructured":"Mingdeng Cao XintaoWang Zhongang Qi Ying Shan Xiaohu Qie and Yinqiang Zheng. 2023. MasaCtrl: Tuning-Free Mutual Self-Attention Control for Consistent Image Synthesis and Editing. In ICCV. 22560--22570."},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"crossref","unstructured":"Mathilde Caron Hugo Touvron Ishan Misra Herv\u00e9 J\u00e9gou Julien Mairal Piotr Bojanowski and Armand Joulin. 2021. Emerging Properties in Self-Supervised Vision Transformers. In ICCV. 9650--9660.","DOI":"10.1109\/ICCV48922.2021.00951"},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"crossref","unstructured":"Hila Chefer Sagie Benaim Roni Paiss and Lior Wolf. 2022. Image-Based Clip-Guided Essence Transfer. In ECCV. 695--711.","DOI":"10.1007\/978-3-031-19778-9_40"},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"crossref","unstructured":"Bin Cheng Zuhao Liu Yunbo Peng and Yue Lin. 2023. General Image-to-Image Translation with One-Shot Image Guidance. In ICCV. 22736--22746.","DOI":"10.1109\/ICCV51070.2023.02078"},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"crossref","unstructured":"Hansam Cho Jonghyun Lee Seunggyu Chang and Yonghyun Jeong. 2024. One-Shot Structure-Aware Stylized Image Synthesis. In CVPR.","DOI":"10.1109\/CVPR52733.2024.00793"},{"key":"e_1_3_2_1_10_1","volume-title":"Jojogan: One Shot Face Stylization. In ECCV. 128--152.","author":"Chong Min Jin","year":"2022","unstructured":"Min Jin Chong and David Forsyth. 2022. Jojogan: One Shot Face Stylization. In ECCV. 128--152."},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"crossref","unstructured":"Jiwoo Chung Sangeek Hyun and Jae-Pil Heo. 2024. Style Injection in Diffusion: A Training-Free Approach for Adapting Large-Scale Diffusion Models for Style Transfer. In CVPR.","DOI":"10.1109\/CVPR52733.2024.00840"},{"key":"e_1_3_2_1_12_1","volume-title":"Huaibo Huang, and Zhaofeng He.","author":"Cui Xing","year":"2024","unstructured":"Xing Cui, Zekun Li, Pei Pei Li, Huaibo Huang, and Zhaofeng He. 2024. InstaStyle: Inversion Noise of a Stylized Image is Secretly a Style Adviser. In ECCV."},{"key":"e_1_3_2_1_13_1","volume-title":"Zero-Shot Style Transfer via Attention Rearrangement. arXiv preprint arXiv:2311.16491","author":"Deng Yingying","year":"2023","unstructured":"Yingying Deng, Xiangyu He, Fan Tang, and Weiming Dong. 2023. Z?: Zero-Shot Style Transfer via Attention Rearrangement. arXiv preprint arXiv:2311.16491 (2023). arXiv:2311.16491"},{"key":"e_1_3_2_1_14_1","first-page":"8780","article-title":"Diffusion Models Beat Gans on Image Synthesis","volume":"34","author":"Dhariwal Prafulla","year":"2021","unstructured":"Prafulla Dhariwal and Alexander Nichol. 2021. Diffusion Models Beat Gans on Image Synthesis. In NeurIPS, Vol. 34. 8780--8794.","journal-title":"NeurIPS"},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"crossref","unstructured":"Patrick Esser Robin Rombach and Bjorn Ommer. 2021. Taming Transformers for High-Resolution Image Synthesis. In CVPR. 12873--12883.","DOI":"10.1109\/CVPR46437.2021.01268"},{"key":"e_1_3_2_1_16_1","volume-title":"Gal Chechik, and Daniel Cohen-or.","author":"Gal Rinon","year":"2022","unstructured":"Rinon Gal, Yuval Alaluf, Yuval Atzmon, Or Patashnik, Amit Haim Bermano, Gal Chechik, and Daniel Cohen-or. 2022. An Image IsWorth OneWord: Personalizing Text-to-Image Generation Using Textual Inversion. In ICLR."},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.1145\/3528223.3530164"},{"key":"e_1_3_2_1_18_1","volume-title":"CVPR.","author":"Gatys Leon A.","unstructured":"Leon A. Gatys, Alexander S. Ecker, and Matthias Bethge. 2016. Image Style Transfer Using Convolutional Neural Networks. In CVPR. Las Vegas, NV, USA, 2414--2423."},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.1145\/3422622"},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"crossref","unstructured":"Ran He Baogang Hu Xiaotong Yuan Liang Wang et al. 2014. Robust recognition via information theoretic learning. Springer.","DOI":"10.1007\/978-3-319-07416-0"},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2015.2466106"},{"key":"e_1_3_2_1_22_1","first-page":"6840","article-title":"Denoising Diffusion Probabilistic Models","volume":"33","author":"Ho Jonathan","year":"2020","unstructured":"Jonathan Ho, Ajay Jain, and Pieter Abbeel. 2020. Denoising Diffusion Probabilistic Models. In NeurIPS, Vol. 33. 6840--6851.","journal-title":"NeurIPS"},{"key":"e_1_3_2_1_23_1","unstructured":"Edward J Hu Phillip Wallis Zeyuan Allen-Zhu Yuanzhi Li Shean Wang Lu Wang Weizhu Chen et al. 2021. LoRA: Low-Rank Adaptation of Large Language Models. In ICLR."},{"key":"e_1_3_2_1_24_1","doi-asserted-by":"crossref","unstructured":"Phillip Isola Jun-Yan Zhu Tinghui Zhou and Alexei A Efros. 2017. Image-to-Image Translation with Conditional Adversarial Networks. In CVPR.","DOI":"10.1109\/CVPR.2017.632"},{"key":"e_1_3_2_1_25_1","unstructured":"Tero Karras Timo Aila Samuli Laine and Jaakko Lehtinen. 2018. Progressive Growing of GANs for Improved Quality Stability and Variation. In ICLR."},{"key":"e_1_3_2_1_26_1","first-page":"12104","article-title":"Training Generative Adversarial Networks with Limited Data","volume":"33","author":"Karras Tero","year":"2020","unstructured":"Tero Karras, Miika Aittala, Janne Hellsten, Samuli Laine, Jaakko Lehtinen, and Timo Aila. 2020. Training Generative Adversarial Networks with Limited Data. In NeurIPS, Vol. 33. 12104--12114.","journal-title":"NeurIPS"},{"key":"e_1_3_2_1_27_1","doi-asserted-by":"crossref","unstructured":"Tero Karras Samuli Laine and Timo Aila. 2019. A Style-Based Generator Architecture for Generative Adversarial Networks. In CVPR. 4401--4410.","DOI":"10.1109\/CVPR.2019.00453"},{"key":"e_1_3_2_1_28_1","doi-asserted-by":"crossref","unstructured":"Tero Karras Samuli Laine Miika Aittala Janne Hellsten Jaakko Lehtinen and Timo Aila. 2020. Analyzing and Improving the Image Quality of Stylegan. In CVPR. 8110--8119.","DOI":"10.1109\/CVPR42600.2020.00813"},{"key":"e_1_3_2_1_29_1","unstructured":"Gwanghyun Kim Taesung Kwon and Jong Chul Ye. 2022. DiffusionCLIP: Text-Guided Diffusion Models for Robust Image Manipulation. In CVPR. 2426--2435."},{"key":"e_1_3_2_1_30_1","unstructured":"Junho Kim Minjae Kim Hyeonwoo Kang and Kwang Hee Lee. 2019. U-GAT-IT: Unsupervised Generative Attentional Networks with Adaptive Layer-Instance Normalization for Image-to-Image Translation. In ICLR."},{"key":"e_1_3_2_1_31_1","doi-asserted-by":"crossref","unstructured":"Seongtae Kim Kyoungkook Kang Geonung Kim Seung-Hwan Baek and Sunghyun Cho. 2022. DynaGAN: Dynamic Few-Shot Adaptation of GANs to Multiple Domains. In SIGGRAPH Asia. 1--8.","DOI":"10.1145\/3550469.3555416"},{"key":"e_1_3_2_1_32_1","volume-title":"Clipstyler: Image Style Transfer with a Single Text Condition. In CVPR. 18062--18071.","author":"Kwon Gihyun","year":"2022","unstructured":"Gihyun Kwon and Jong Chul Ye. 2022. Clipstyler: Image Style Transfer with a Single Text Condition. In CVPR. 18062--18071."},{"key":"e_1_3_2_1_33_1","unstructured":"Gihyun Kwon and Jong Chul Ye. 2022. Diffusion-Based Image Translation Using Disentangled Style and Content Representation. In ICLR."},{"key":"e_1_3_2_1_34_1","volume-title":"StyO: Stylize Your Face in Only One-Shot. arXiv preprint arXiv:2303.03231","author":"Li Bonan","year":"2023","unstructured":"Bonan Li, Zicheng Zhang, Xuecheng Nie, Congying Han, Yinhan Hu, and Tiande Guo. 2023. StyO: Stylize Your Face in Only One-Shot. arXiv preprint arXiv:2303.03231 (2023). arXiv:2303.03231"},{"key":"e_1_3_2_1_35_1","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-019-01267-0"},{"key":"e_1_3_2_1_36_1","first-page":"15885","article-title":"Few-Shot Image Generation with Elastic Weight Consolidation","volume":"33","author":"Li Yijun","year":"2020","unstructured":"Yijun Li, Richard Zhang, Jingwan Cynthia Lu, and Eli Shechtman. 2020. Few-Shot Image Generation with Elastic Weight Consolidation. In NeurIPS, Vol. 33. 15885--15896.","journal-title":"NeurIPS"},{"key":"e_1_3_2_1_37_1","volume-title":"Portrait Diffusion: Training-Free Face Stylization with Chain-of-Painting. arXiv preprint arXiv:2312.02212","author":"Liu Jin","year":"2023","unstructured":"Jin Liu, Huaibo Huang, Chao Jin, and Ran He. 2023. Portrait Diffusion: Training-Free Face Stylization with Chain-of-Painting. arXiv preprint arXiv:2312.02212 (2023). arXiv:2312.02212"},{"key":"e_1_3_2_1_38_1","first-page":"29710","article-title":"Blendgan: Implicitly Gan Blending for Arbitrary Stylized Face Generation","volume":"34","author":"Liu Mingcong","year":"2021","unstructured":"Mingcong Liu, Qiang Li, Zekui Qin, Guoxin Zhang, Pengfei Wan, and Wen Zheng. 2021. Blendgan: Implicitly Gan Blending for Arbitrary Stylized Face Generation. NeurIPS 34 (2021), 29710--29722.","journal-title":"NeurIPS"},{"key":"e_1_3_2_1_39_1","volume-title":"NIPS","volume":"30","author":"Liu Ming-Yu","year":"2017","unstructured":"Ming-Yu Liu, Thomas Breuel, and Jan Kautz. 2017. Unsupervised Image-to-Image Translation Networks. In NIPS, Vol. 30."},{"key":"e_1_3_2_1_40_1","volume-title":"DPM-Solver: Fast Solver for Guided Sampling of Diffusion Probabilistic Models. arXiv preprint arXiv:2211.01095","author":"Lu Cheng","year":"2022","unstructured":"Cheng Lu, Yuhao Zhou, Fan Bao, Jianfei Chen, Chongxuan Li, and Jun Zhu. 2022. DPM-Solver: Fast Solver for Guided Sampling of Diffusion Probabilistic Models. arXiv preprint arXiv:2211.01095 (2022). arXiv:2211.01095"},{"key":"e_1_3_2_1_41_1","volume-title":"Latent Consistency Models: Synthesizing High-Resolution Images with Few-Step Inference. arXiv preprint arXiv:2310.04378","author":"Luo Simian","year":"2023","unstructured":"Simian Luo, Yiqin Tan, Longbo Huang, Jian Li, and Hang Zhao. 2023. Latent Consistency Models: Synthesizing High-Resolution Images with Few-Step Inference. arXiv preprint arXiv:2310.04378 (2023). arXiv:2310.04378"},{"key":"e_1_3_2_1_42_1","doi-asserted-by":"crossref","unstructured":"Ron Mokady Amir Hertz Kfir Aberman Yael Pritch and Daniel Cohen-Or. 2023. NULL-Text Inversion for Editing Real Images Using Guided Diffusion Models. In CVPR. 6038--6047.","DOI":"10.1109\/CVPR52729.2023.00585"},{"key":"e_1_3_2_1_43_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i5.28226"},{"key":"e_1_3_2_1_44_1","volume-title":"Steered Diffusion: A Generalized Framework for Plug-and-Play Conditional Image Synthesis. In ICCV. 20850--20860.","author":"Nair Nithin Gopalakrishnan","year":"2023","unstructured":"Nithin Gopalakrishnan Nair, Anoop Cherian, Suhas Lohit, Ye Wang, Toshiaki Koike-Akino, Vishal M Patel, and Tim K Marks. 2023. Steered Diffusion: A Generalized Framework for Plug-and-Play Conditional Image Synthesis. In ICCV. 20850--20860."},{"key":"e_1_3_2_1_45_1","doi-asserted-by":"crossref","unstructured":"Atsuhiro Noguchi and Tatsuya Harada. 2019. Image Generation from Small Datasets via Batch Statistics Adaptation. In ICCV. 2750--2758.","DOI":"10.1109\/ICCV.2019.00284"},{"key":"e_1_3_2_1_46_1","volume-title":"Eli Shechtman, and Richard Zhang.","author":"Ojha Utkarsh","year":"2021","unstructured":"Utkarsh Ojha, Yijun Li, Jingwan Lu, Alexei A Efros, Yong Jae Lee, Eli Shechtman, and Richard Zhang. 2021. Few-Shot Image Generation via Cross-Domain Correspondence. In CVPR. 10743--10752."},{"key":"e_1_3_2_1_47_1","unstructured":"OpenAI. 2023. DALL\u00b7E 3."},{"key":"e_1_3_2_1_48_1","volume-title":"Styleclip: Text-Driven Manipulation of Stylegan Imagery. In ICCV. 2085--2094.","author":"Patashnik Or","year":"2021","unstructured":"Or Patashnik, Zongze Wu, Eli Shechtman, Daniel Cohen-Or, and Dani Lischinski. 2021. Styleclip: Text-Driven Manipulation of Stylegan Imagery. In ICCV. 2085--2094."},{"key":"e_1_3_2_1_49_1","volume-title":"Resolution Dependent Gan Interpolation for Controllable Image Synthesis between Domains. arXiv:2010.05334","author":"Pinkney Justin NM","year":"2020","unstructured":"Justin NM Pinkney and Doron Adler. 2020. Resolution Dependent Gan Interpolation for Controllable Image Synthesis between Domains. arXiv:2010.05334 (2020). arXiv:2010.05334"},{"key":"e_1_3_2_1_50_1","volume-title":"Diffusion Autoencoders: Toward a Meaningful and Decodable Representation. In CVPR.","author":"Preechakul Konpat","year":"2022","unstructured":"Konpat Preechakul, Nattanat Chatthee, Suttisak Wizadwongsa, and Supasorn Suwajanakorn. 2022. Diffusion Autoencoders: Toward a Meaningful and Decodable Representation. In CVPR."},{"key":"e_1_3_2_1_51_1","volume-title":"Chris Hallacy, Aditya Ramesh, Gabriel Goh, Sandhini Agarwal, Girish Sastry, Amanda Askell, Pamela Mishkin, Jack Clark, et al.","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 ICML. 8748--8763."},{"key":"e_1_3_2_1_52_1","volume-title":"Few-Shot Adaptation of Generative Adversarial Networks. arXiv preprint arXiv:2010.11943","author":"Robb Esther","year":"2020","unstructured":"Esther Robb, Wen-Sheng Chu, Abhishek Kumar, and Jia-Bin Huang. 2020. Few-Shot Adaptation of Generative Adversarial Networks. arXiv preprint arXiv:2010.11943 (2020). arXiv:2010.11943"},{"key":"e_1_3_2_1_53_1","doi-asserted-by":"crossref","unstructured":"Robin Rombach Andreas Blattmann Dominik Lorenz Patrick Esser and Bj\u00f6rn Ommer. 2022. High-Resolution Image Synthesis with Latent Diffusion Models. In CVPR. 10684--10695.","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"e_1_3_2_1_54_1","doi-asserted-by":"crossref","unstructured":"Olaf Ronneberger Philipp Fischer and Thomas Brox. 2015. U-Net: Convolutional Networks for Biomedical Image Segmentation. In MICCAI. 234--241.","DOI":"10.1007\/978-3-319-24574-4_28"},{"key":"e_1_3_2_1_55_1","volume-title":"Dreambooth: Fine Tuning Text-to-Image Diffusion Models for Subject-Driven Generation. In CVPR. 22500--22510.","author":"Ruiz Nataniel","year":"2023","unstructured":"Nataniel Ruiz, Yuanzhen Li, Varun Jampani, Yael Pritch, Michael Rubinstein, and Kfir Aberman. 2023. Dreambooth: Fine Tuning Text-to-Image Diffusion Models for Subject-Driven Generation. In CVPR. 22500--22510."},{"key":"e_1_3_2_1_56_1","first-page":"36479","article-title":"Photorealistic Text-to-Image Diffusion Models with Deep Language Understanding","volume":"35","author":"Saharia Chitwan","year":"2022","unstructured":"Chitwan Saharia, William Chan, Saurabh Saxena, Lala Li, Jay Whang, Emily L Denton, Kamyar Ghasemipour, Raphael Gontijo Lopes, Burcu Karagol Ayan, Tim Salimans, et al. 2022. Photorealistic Text-to-Image Diffusion Models with Deep Language Understanding. NeurIPS 35 (2022), 36479--36494.","journal-title":"NeurIPS"},{"key":"e_1_3_2_1_57_1","volume-title":"Adversarial diffusion distillation. arXiv preprint arXiv:2311.17042","author":"Sauer Axel","year":"2023","unstructured":"Axel Sauer, Dominik Lorenz, Andreas Blattmann, and Robin Rombach. 2023. Adversarial diffusion distillation. arXiv preprint arXiv:2311.17042 (2023). arXiv:2311.17042"},{"key":"e_1_3_2_1_58_1","unstructured":"Jascha Sohl-Dickstein Eric Weiss Niru Maheswaranathan and Surya Ganguli. 2015. Deep Unsupervised Learning Using Nonequilibrium Thermodynamics. In ICML."},{"key":"e_1_3_2_1_59_1","doi-asserted-by":"publisher","DOI":"10.1145\/3450626.3459771"},{"key":"e_1_3_2_1_60_1","unstructured":"Jiaming Song Chenlin Meng and Stefano Ermon. 2020. Denoising Diffusion Implicit Models. In ICLR."},{"key":"e_1_3_2_1_61_1","unstructured":"Yang Song Prafulla Dhariwal Mark Chen and Ilya Sutskever. 2023. Consistency Models. arXiv:2303.01469"},{"key":"e_1_3_2_1_62_1","unstructured":"Yang Song Jascha Sohl-Dickstein Diederik P Kingma Abhishek Kumar Stefano Ermon and Ben Poole. 2020. Score-Based Generative Modeling through Stochastic Differential Equations. In ICLR."},{"key":"e_1_3_2_1_63_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00191"},{"key":"e_1_3_2_1_64_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i2.25353"},{"key":"e_1_3_2_1_65_1","doi-asserted-by":"crossref","unstructured":"Rui Wang Huaibo Huang Aihua Zheng and Ran He. 2021. Attentional wavelet network for traditional chinese painting transfer. In ICPR. 3077--3083.","DOI":"10.1109\/ICPR48806.2021.9413063"},{"key":"e_1_3_2_1_66_1","doi-asserted-by":"crossref","unstructured":"Ting-Chun Wang Ming-Yu Liu Jun-Yan Zhu Andrew Tao Jan Kautz and Bryan Catanzaro. 2018. High-Resolution Image Synthesis and Semantic Manipulation with Conditional Gans. In CVPR. 8798--8807.","DOI":"10.1109\/CVPR.2018.00917"},{"key":"e_1_3_2_1_67_1","volume-title":"Fahad Shahbaz Khan, and Joost van de Weijer","author":"Wang Yaxing","year":"2020","unstructured":"Yaxing Wang, Abel Gonzalez-Garcia, David Berga, Luis Herranz, Fahad Shahbaz Khan, and Joost van de Weijer. 2020. Minegan: Effective Knowledge Transfer from Gans to Target Domains with Few Images. In CVPR. 9332--9341."},{"key":"e_1_3_2_1_68_1","volume-title":"Abel Gonzalez-Garcia, and Bogdan Raducanu.","author":"Wang Yaxing","year":"2018","unstructured":"Yaxing Wang, Chenshen Wu, Luis Herranz, Joost Van de Weijer, Abel Gonzalez-Garcia, and Bogdan Raducanu. 2018. Transferring Gans: Generating Images from Limited Data. In ECCV. 218--234."},{"key":"e_1_3_2_1_69_1","doi-asserted-by":"crossref","unstructured":"Xin Xie Yi Li Huaibo Huang Haiyan Fu WanwanWang and Yanqing Guo. 2022. Artistic style discovery with independent components. In CVPR. 19870--19879.","DOI":"10.1109\/CVPR52688.2022.01925"},{"key":"e_1_3_2_1_70_1","doi-asserted-by":"crossref","unstructured":"Ceyuan Yang Yujun Shen Zhiyi Zhang Yinghao Xu Jiapeng Zhu Zhirong Wu and Bolei Zhou. 2023. One-Shot Generative Domain Adaptation. In ICCV. 7733--7742.","DOI":"10.1109\/ICCV51070.2023.00711"},{"key":"e_1_3_2_1_71_1","doi-asserted-by":"crossref","unstructured":"Serin Yang Hyunmin Hwang and Jong Chul Ye. 2023. Zero-Shot Contrastive Loss for Text-Guided Diffusion Image Style Transfer. In ICCV. 22873--22882.","DOI":"10.1109\/ICCV51070.2023.02091"},{"key":"e_1_3_2_1_72_1","volume-title":"Pastiche Master: Exemplar-Based High-Resolution Portrait Style Transfer. In CVPR. 7693--7702.","author":"Yang Shuai","year":"2022","unstructured":"Shuai Yang, Liming Jiang, Ziwei Liu, and Chen Change Loy. 2022. Pastiche Master: Exemplar-Based High-Resolution Portrait Style Transfer. In CVPR. 7693--7702."},{"key":"e_1_3_2_1_73_1","volume-title":"Freedom: Training-Free Energy-Guided Conditional Diffusion Model. In ICCV. 23174--23184.","author":"Yu Jiwen","year":"2023","unstructured":"Jiwen Yu, Yinhuai Wang, Chen Zhao, Bernard Ghanem, and Jian Zhang. 2023. Freedom: Training-Free Energy-Guided Conditional Diffusion Model. In ICCV. 23174--23184."},{"key":"e_1_3_2_1_74_1","doi-asserted-by":"crossref","unstructured":"Lvmin Zhang Anyi Rao and Maneesh Agrawala. 2023. Adding Conditional Control to Text-to-Image Diffusion Models. In ICCV. 3836--3847.","DOI":"10.1109\/ICCV51070.2023.00355"},{"key":"e_1_3_2_1_75_1","doi-asserted-by":"crossref","unstructured":"Richard Zhang Phillip Isola Alexei A Efros Eli Shechtman and Oliver Wang. 2018. The Unreasonable Effectiveness of Deep Features as a Perceptual Metric. In CVPR. 586--595.","DOI":"10.1109\/CVPR.2018.00068"},{"key":"e_1_3_2_1_76_1","doi-asserted-by":"crossref","unstructured":"Yuxin Zhang Nisha Huang Fan Tang Haibin Huang Chongyang Ma Weiming Dong and Changsheng Xu. 2023. Inversion-Based Style Transfer with Diffusion Models. In CVPR. 10146--10156.","DOI":"10.1109\/CVPR52729.2023.00978"},{"key":"e_1_3_2_1_77_1","first-page":"13718","article-title":"Generalized One-Shot Domain Adaptation of Generative Adversarial Networks","volume":"35","author":"Zhang Zicheng","year":"2022","unstructured":"Zicheng Zhang, Yinglu Liu, Congying Han, Tiande Guo, Ting Yao, and Tao Mei. 2022. Generalized One-Shot Domain Adaptation of Generative Adversarial Networks. In NeurIPS, Vol. 35. 13718--13730.","journal-title":"NeurIPS"},{"key":"e_1_3_2_1_78_1","unstructured":"Miaoyun Zhao Yulai Cong and Lawrence Carin. 2020. On Leveraging Pretrained GANs for Generation with Limited Data. In ICML. 11340--11351."},{"key":"e_1_3_2_1_79_1","volume-title":"NeurIPS","volume":"36","author":"Zhao Wenliang","year":"2024","unstructured":"Wenliang Zhao, Lujia Bai, Yongming Rao, Jie Zhou, and Jiwen Lu. 2024. Unipc: A Unified Predictor-Corrector Framework for Fast Sampling of Diffusion Models. In NeurIPS, Vol. 36."},{"key":"e_1_3_2_1_80_1","doi-asserted-by":"crossref","unstructured":"Yang Zhou Zichong Chen and Hui Huang. 2024. Deformable One-Shot Face Stylization via DINO Semantic Guidance. In CVPR.","DOI":"10.1109\/CVPR52733.2024.00744"},{"key":"e_1_3_2_1_81_1","unstructured":"Jun-Yan Zhu Taesung Park Phillip Isola and Alexei A Efros. 2017. Unpaired Image-to-Image Translation Using Cycle-Consistent Adversarial Networks. In ICCV. 2223--2232."},{"key":"e_1_3_2_1_82_1","unstructured":"Jun-Yan Zhu Richard Zhang Deepak Pathak Trevor Darrell Alexei A Efros Oliver Wang and Eli Shechtman. 2017. Toward Multimodal Image-to-Image Translation. In NIPS I. Guyon U. V. Luxburg S. Bengio H. Wallach R. Fergus S. Vishwanathan and R. Garnett (Eds.). 465--476."}],"event":{"name":"MM '24: The 32nd ACM International Conference on Multimedia","location":"Melbourne VIC Australia","acronym":"MM '24","sponsor":["SIGMM ACM Special Interest Group on Multimedia"]},"container-title":["Proceedings of the 32nd ACM International Conference on Multimedia"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3664647.3680676","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3664647.3680676","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,19]],"date-time":"2025-06-19T01:17:57Z","timestamp":1750295877000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3664647.3680676"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,10,28]]},"references-count":82,"alternative-id":["10.1145\/3664647.3680676","10.1145\/3664647"],"URL":"https:\/\/doi.org\/10.1145\/3664647.3680676","relation":{},"subject":[],"published":{"date-parts":[[2024,10,28]]},"assertion":[{"value":"2024-10-28","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}