{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,10]],"date-time":"2025-12-10T04:19:17Z","timestamp":1765340357466,"version":"3.46.0"},"publisher-location":"New York, NY, USA","reference-count":47,"publisher":"ACM","content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2025,10,27]]},"DOI":"10.1145\/3746027.3755840","type":"proceedings-article","created":{"date-parts":[[2025,10,25]],"date-time":"2025-10-25T07:38:54Z","timestamp":1761377934000},"page":"10681-10689","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["CADQ: Attribute-Consistent Face Cartoonization with Cross-modal Aligned and Deformable Quantization"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0003-8554-3177","authenticated-orcid":false,"given":"Yongjie","family":"Hu","sequence":"first","affiliation":[{"name":"Xidian University, Xi'an, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0008-6267-7187","authenticated-orcid":false,"given":"Yifan","family":"Jiang","sequence":"additional","affiliation":[{"name":"Xidian University, Xi'an, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4286-9030","authenticated-orcid":false,"given":"Ziyun","family":"Li","sequence":"additional","affiliation":[{"name":"KTH Royal Institute of Technology, Stockholm, Sweden"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8714-0975","authenticated-orcid":false,"given":"Fei","family":"Gao","sequence":"additional","affiliation":[{"name":"Xidian University, Xi'an, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8382-0300","authenticated-orcid":false,"given":"Henrik","family":"Bostr\u00f6m","sequence":"additional","affiliation":[{"name":"KTH Royal Institute of Technology, Stockholm, Sweden"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1435-489X","authenticated-orcid":false,"given":"Nannan","family":"Wang","sequence":"additional","affiliation":[{"name":"Xidian University, Xi'an, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2025,10,27]]},"reference":[{"key":"e_1_3_2_1_1_1","volume-title":"Demystifying MMD GANs. In International Conference on Learning Representations.","author":"Bi\u0144kowski Miko\u0142aj","year":"2018","unstructured":"Miko\u0142aj Bi\u0144kowski, Danica J Sutherland, Michael Arbel, and Arthur Gretton. 2018. Demystifying MMD GANs. In International Conference on Learning Representations."},{"key":"e_1_3_2_1_2_1","volume-title":"Fast patch-based style transfer of arbitrary style. arXiv preprint arXiv:1612.04337","author":"Chen Tian Qi","year":"2016","unstructured":"Tian Qi Chen and Mark Schmidt. 2016. Fast patch-based style transfer of arbitrary style. arXiv preprint arXiv:1612.04337 (2016)."},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00986"},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00840"},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01104"},{"key":"e_1_3_2_1_6_1","volume-title":"BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding. arXiv preprint arXiv:1810.04805","author":"Devlin Jacob","year":"2018","unstructured":"Jacob Devlin, Ming-Wei Chang, Kenton Lee, and Kristina Toutanova. 2018. BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding. arXiv preprint arXiv:1810.04805 (2018)."},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20053-3_5"},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01268"},{"key":"e_1_3_2_1_9_1","volume-title":"Controlling Perceptual Factors in Neural Style Transfer. In 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR). IEEE, 3730--3738","author":"Gatys Leon A","year":"2017","unstructured":"Leon A Gatys, Alexander S Ecker, Matthias Bethge, Aaron Hertzmann, and Eli Shechtman. 2017. Controlling Perceptual Factors in Neural Style Transfer. In 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR). IEEE, 3730--3738."},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00975"},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"e_1_3_2_1_12_1","volume-title":"Gans trained by a two time-scale update rule converge to a local nash equilibrium. Advances in neural information processing systems 30","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 30 (2017)."},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.02080"},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00576"},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.167"},{"key":"e_1_3_2_1_16_1","unstructured":"Aaron Hurst Adam Lerer Adam P Goucher Adam Perelman Aditya Ramesh Aidan Clark AJ Ostrow Akila Welihinda Alan Hayes Alec Radford et al. 2024. Gpt-4o system card. arXiv preprint arXiv:2410.21276 (2024)."},{"key":"e_1_3_2_1_17_1","unstructured":"Max Jaderberg Karen Simonyan Andrew Zisserman et al. 2015. Spatial transformer networks. Advances in neural information processing systems 28 (2015)."},{"key":"e_1_3_2_1_18_1","volume-title":"Proceedings, Part II 14","author":"Johnson Justin","year":"2016","unstructured":"Justin Johnson, Alexandre Alahi, and Li Fei-Fei. 2016. Perceptual losses for realtime style transfer and super-resolution. In Computer Vision--ECCV 2016: 14th European Conference, Amsterdam, The Netherlands, October 11--14, 2016, Proceedings, Part II 14. Springer, 694--711."},{"key":"e_1_3_2_1_19_1","volume-title":"U-GAT-IT: Unsupervised Generative Attentional Networks with Adaptive Layer-Instance Normalization for Image-to-Image Translation. In International Conference on Learning Representations.","author":"Kim Junho","year":"2020","unstructured":"Junho Kim, Minjae Kim, Hyeonwoo Kang, and Kwang Hee Lee. 2020. U-GAT-IT: Unsupervised Generative Attentional Networks with Adaptive Layer-Instance Normalization for Image-to-Image Translation. In International Conference on Learning Representations."},{"key":"e_1_3_2_1_20_1","volume-title":"Adam: A method for stochastic optimization. arXiv preprint arXiv:1412.6980","author":"Kingma Diederik P","year":"2014","unstructured":"Diederik P Kingma. 2014. Adam: A method for stochastic optimization. arXiv preprint arXiv:1412.6980 (2014)."},{"key":"e_1_3_2_1_21_1","volume-title":"The Eleventh International Conference on Learning Representations.","author":"Kwon Gihyun","year":"2023","unstructured":"Gihyun Kwon and Jong Chul Ye. 2023. Diffusion-based Image Translation using disentangled style and content representation. In The Eleventh International Conference on Learning Representations."},{"key":"e_1_3_2_1_22_1","volume-title":"MaskGAN: Towards Diverse and Interactive Facial Image Manipulation. In IEEE Conference on Computer Vision and Pattern Recognition (CVPR).","author":"Lee Cheng-Han","year":"2020","unstructured":"Cheng-Han Lee, Ziwei Liu, Lingyun Wu, and Ping Luo. 2020. MaskGAN: Towards Diverse and Interactive Facial Image Manipulation. In IEEE Conference on Computer Vision and Pattern Recognition (CVPR)."},{"key":"e_1_3_2_1_23_1","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2021.3113786"},{"key":"e_1_3_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00393"},{"key":"e_1_3_2_1_25_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00658"},{"key":"e_1_3_2_1_26_1","volume-title":"Proceedings, Part IX 16","author":"Park Taesung","year":"2020","unstructured":"Taesung Park, Alexei A Efros, Richard Zhang, and Jun-Yan Zhu. 2020. Contrastive learning for unpaired image-to-image translation. In Computer Vision--ECCV 2020: 16th European Conference, Glasgow, UK, August 23--28, 2020, Proceedings, Part IX 16. Springer, 319--345."},{"key":"e_1_3_2_1_27_1","volume-title":"Onestep image translation with text-to-image models. arXiv preprint arXiv:2403.12036","author":"Parmar Gaurav","year":"2024","unstructured":"Gaurav Parmar, Taesung Park, Srinivasa Narasimhan, and Jun-Yan Zhu. 2024. Onestep image translation with text-to-image models. arXiv preprint arXiv:2403.12036 (2024)."},{"key":"e_1_3_2_1_28_1","volume-title":"Pytorch: An imperative style, high-performance deep learning library. Advances in neural information processing systems 32","author":"Paszke Adam","year":"2019","unstructured":"Adam Paszke, Sam Gross, Francisco Massa, Adam Lerer, James Bradbury, Gregory Chanan, Trevor Killeen, Zeming Lin, Natalia Gimelshein, Luca Antiga, et al. 2019. Pytorch: An imperative style, high-performance deep learning library. Advances in neural information processing systems 32 (2019)."},{"key":"e_1_3_2_1_29_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_30_1","unstructured":"Google Research. [n.d.]. Cartoon Set: An Image Dataset of Random Cartoons. https:\/\/google.github.io\/cartoonset\/."},{"key":"e_1_3_2_1_31_1","volume-title":"Xgan: Unsupervised image-to-image translation for many-to-many mappings. Domain Adaptation for Visual Understanding","author":"Royer Am\u00e9lie","year":"2020","unstructured":"Am\u00e9lie Royer, Konstantinos Bousmalis, Stephan Gouws, Fred Bertsch, Inbar Mosseri, Forrester Cole, and Kevin Murphy. 2020. Xgan: Unsupervised image-to-image translation for many-to-many mappings. Domain Adaptation for Visual Understanding (2020), 33--49."},{"key":"e_1_3_2_1_32_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00860"},{"key":"e_1_3_2_1_33_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01388"},{"key":"e_1_3_2_1_34_1","volume-title":"Dual Diffusion Implicit Bridges for Image-to-Image Translation. In International Conference on Learning Representations.","author":"Su Xuan","year":"2023","unstructured":"Xuan Su, Jiaming Song, Chenlin Meng, and Stefano Ermon. 2023. Dual Diffusion Implicit Bridges for Image-to-Image Translation. In International Conference on Learning Representations."},{"key":"e_1_3_2_1_35_1","unstructured":"Aaron Van Den Oord Oriol Vinyals et al. 2017. Neural discrete representation learning. Advances in neural information processing systems 30 (2017)."},{"key":"e_1_3_2_1_36_1","volume-title":"Instant Style: 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. 2024. Instant Style: Free Lunch towards Style-Preserving in Text-to-Image Generation. arXiv preprint arXiv:2404.02733 (2024)."},{"key":"e_1_3_2_1_37_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i06.6609"},{"key":"e_1_3_2_1_38_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00811"},{"key":"e_1_3_2_1_39_1","volume-title":"DAGM German Conference on Pattern Recognition. Springer, 560--576","author":"Bj\u00f6rn Ommer MatthiasWright","year":"2022","unstructured":"MatthiasWright and Bj\u00f6rn Ommer. 2022. Artfid: Quantitative evaluation of neural style transfer. In DAGM German Conference on Pattern Recognition. Springer, 560--576."},{"key":"e_1_3_2_1_40_1","unstructured":"Chen Henry Wu and Fernando De la Torre. 2023. A Latent Space of Stochastic Diffusion Models for Zero-Shot Image Editing and Guidance. In ICCV."},{"key":"e_1_3_2_1_41_1","volume-title":"TediGAN: Text-Guided Diverse Face Image Generation and Manipulation. In IEEE Conference on Computer Vision and Pattern Recognition (CVPR).","author":"Xia Weihao","year":"2021","unstructured":"Weihao Xia, Yujiu Yang, Jing-Hao Xue, and Baoyuan Wu. 2021. TediGAN: Text-Guided Diverse Face Image Generation and Manipulation. In IEEE Conference on Computer Vision and Pattern Recognition (CVPR)."},{"key":"e_1_3_2_1_42_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01779"},{"key":"e_1_3_2_1_43_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01100"},{"key":"e_1_3_2_1_44_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00978"},{"key":"e_1_3_2_1_45_1","doi-asserted-by":"crossref","unstructured":"Yuxin Zhang Fan Tang Weiming Dong Haibin Huang Chongyang Ma Tong-Yee Lee and Changsheng Xu. 2022. Domain Enhanced Arbitrary Image Style Transfer via Contrastive Learning. In ACM SIGGRAPH.","DOI":"10.1145\/3528233.3530736"},{"key":"e_1_3_2_1_46_1","volume-title":"Attention distillation: A unified approach to visual characteristics transfer. arXiv preprint arXiv:2502.20235","author":"Zhou Yang","year":"2025","unstructured":"Yang Zhou, Xu Gao, Zichong Chen, and Hui Huang. 2025. Attention distillation: A unified approach to visual characteristics transfer. arXiv preprint arXiv:2502.20235 (2025)."},{"key":"e_1_3_2_1_47_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.244"}],"event":{"name":"MM '25: The 33rd ACM International Conference on Multimedia","sponsor":["SIGMM ACM Special Interest Group on Multimedia"],"location":"Dublin Ireland","acronym":"MM '25"},"container-title":["Proceedings of the 33rd ACM International Conference on Multimedia"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3746027.3755840","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,12,10]],"date-time":"2025-12-10T04:14:32Z","timestamp":1765340072000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3746027.3755840"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,27]]},"references-count":47,"alternative-id":["10.1145\/3746027.3755840","10.1145\/3746027"],"URL":"https:\/\/doi.org\/10.1145\/3746027.3755840","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"}}]}}