{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,13]],"date-time":"2026-03-13T15:14:34Z","timestamp":1773414874278,"version":"3.50.1"},"publisher-location":"Singapore","reference-count":45,"publisher":"Springer Nature Singapore","isbn-type":[{"value":"9789819609161","type":"print"},{"value":"9789819609178","type":"electronic"}],"license":[{"start":{"date-parts":[[2024,12,8]],"date-time":"2024-12-08T00:00:00Z","timestamp":1733616000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,12,8]],"date-time":"2024-12-08T00:00:00Z","timestamp":1733616000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025]]},"DOI":"10.1007\/978-981-96-0917-8_15","type":"book-chapter","created":{"date-parts":[[2024,12,7]],"date-time":"2024-12-07T07:57:39Z","timestamp":1733558259000},"page":"256-272","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["Masking Cascaded Self-attentions for\u00a0Few-Shot Font-Generation Transformer"],"prefix":"10.1007","author":[{"given":"Jing","family":"Ma","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0000-1530-8938","authenticated-orcid":false,"given":"Xiang","family":"Xiang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yan","family":"He","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2024,12,8]]},"reference":[{"key":"15_CR1","doi-asserted-by":"crossref","unstructured":"An, J., Huang, S., Song, Y., Dou, D., Liu, W., Luo, J.: Artflow: Unbiased image style transfer via reversible neural flows. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition. pp. 862\u2013871 (2021)","DOI":"10.1109\/CVPR46437.2021.00092"},{"key":"15_CR2","doi-asserted-by":"crossref","unstructured":"Baek, K., Choi, Y., Uh, Y., Yoo, J., Shim, H.: Rethinking the truly unsupervised image-to-image translation. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision. pp. 14154\u201314163 (2021)","DOI":"10.1109\/ICCV48922.2021.01389"},{"key":"15_CR3","unstructured":"Below, V.C.A.L.: Cjkv information processing chinese japanese korean and vietnamese computing"},{"key":"15_CR4","unstructured":"Chang, J., Gu, Y., Zhang, Y., Wang, Y.F., Innovation, C.: Chinese handwriting imitation with hierarchical generative adversarial network. In: BMVC. p.\u00a0290 (2018)"},{"key":"15_CR5","doi-asserted-by":"crossref","unstructured":"Chen, D., Yuan, L., Liao, J., Yu, N., Hua, G.: Stylebank: An explicit representation for neural image style transfer. In: Proceedings of the IEEE conference on computer vision and pattern recognition. pp. 1897\u20131906 (2017)","DOI":"10.1109\/CVPR.2017.296"},{"key":"15_CR6","doi-asserted-by":"crossref","unstructured":"Deng, Y., Tang, F., Dong, W., Ma, C., Pan, X., Wang, L., Xu, C.: Stytr2: Image style transfer with transformers. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition. pp. 11326\u201311336 (2022)","DOI":"10.1109\/CVPR52688.2022.01104"},{"key":"15_CR7","doi-asserted-by":"crossref","unstructured":"Deng, Y., Tang, F., Dong, W., Sun, W., Huang, F., Xu, C.: Arbitrary style transfer via multi-adaptation network. In: Proceedings of the 28th ACM international conference on multimedia. pp. 2719\u20132727 (2020)","DOI":"10.1145\/3394171.3414015"},{"key":"15_CR8","unstructured":"Dosovitskiy, A., Beyer, L., Kolesnikov, A., Weissenborn, D., Zhai, X., Unterthiner, T., Dehghani, M., Minderer, M., Heigold, G., Gelly, S., et\u00a0al.: An image is worth 16x16 words: Transformers for image recognition at scale. arXiv preprint arXiv:2010.11929 (2020)"},{"key":"15_CR9","unstructured":"Dumoulin, V., Shlens, J., Kudlur, M.: A learned representation for artistic style. arXiv preprint arXiv:1610.07629 (2016)"},{"key":"15_CR10","doi-asserted-by":"crossref","unstructured":"Gao, Y., Wu, J.: Gan-based unpaired chinese character image translation via skeleton transformation and stroke rendering. In: proceedings of the AAAI conference on artificial intelligence. vol.\u00a034, pp. 646\u2013653 (2020)","DOI":"10.1609\/aaai.v34i01.5405"},{"key":"15_CR11","doi-asserted-by":"crossref","unstructured":"Gatys, L.A., Ecker, A.S., Bethge, M.: Image style transfer using convolutional neural networks. In: Proceedings of the IEEE conference on computer vision and pattern recognition. pp. 2414\u20132423 (2016)","DOI":"10.1109\/CVPR.2016.265"},{"key":"15_CR12","doi-asserted-by":"crossref","unstructured":"He, K., Chen, X., Xie, S., Li, Y., Doll\u00e1r, P., Girshick, R.: Masked autoencoders are scalable vision learners. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition. pp. 16000\u201316009 (2022)","DOI":"10.1109\/CVPR52688.2022.01553"},{"key":"15_CR13","unstructured":"Heusel, M., Ramsauer, H., Unterthiner, T., Nessler, B., Hochreiter, S.: Gans trained by a two time-scale update rule converge to a local nash equilibrium. Advances in neural information processing systems 30 (2017)"},{"key":"15_CR14","doi-asserted-by":"crossref","unstructured":"Huang, X., Belongie, S.: Arbitrary style transfer in real-time with adaptive instance normalization. In: Proceedings of the IEEE international conference on computer vision. pp. 1501\u20131510 (2017)","DOI":"10.1109\/ICCV.2017.167"},{"key":"15_CR15","doi-asserted-by":"crossref","unstructured":"Huang, X., Liu, M.Y., Belongie, S., Kautz, J.: Multimodal unsupervised image-to-image translation. In: Proceedings of the European conference on computer vision (ECCV). pp. 172\u2013189 (2018)","DOI":"10.1007\/978-3-030-01219-9_11"},{"key":"15_CR16","doi-asserted-by":"crossref","unstructured":"Isola, P., Zhu, J.Y., Zhou, T., Efros, A.A.: Image-to-image translation with conditional adversarial networks. In: Proceedings of the IEEE conference on computer vision and pattern recognition. pp. 1125\u20131134 (2017)","DOI":"10.1109\/CVPR.2017.632"},{"key":"15_CR17","doi-asserted-by":"crossref","unstructured":"Jiang, Y., Lian, Z., Tang, Y., Xiao, J.: Dcfont: an end-to-end deep chinese font generation system. In: SIGGRAPH Asia 2017 Technical Briefs, pp.\u00a01\u20134 (2017)","DOI":"10.1145\/3145749.3149440"},{"key":"15_CR18","doi-asserted-by":"crossref","unstructured":"Jiang, Y., Lian, Z., Tang, Y., Xiao, J.: Scfont: Structure-guided chinese font generation via deep stacked networks. In: Proceedings of the AAAI conference on artificial intelligence. vol.\u00a033, pp. 4015\u20134022 (2019)","DOI":"10.1609\/aaai.v33i01.33014015"},{"key":"15_CR19","doi-asserted-by":"crossref","unstructured":"Johnson, J., Alahi, A., Fei-Fei, L.: Perceptual losses for real-time style transfer and super-resolution. In: Computer Vision\u2013ECCV 2016: 14th European Conference, Amsterdam, The Netherlands, October 11-14, 2016, Proceedings, Part II 14. pp. 694\u2013711. Springer (2016)","DOI":"10.1007\/978-3-319-46475-6_43"},{"key":"15_CR20","doi-asserted-by":"crossref","unstructured":"Karras, T., Laine, S., Aila, T.: A style-based generator architecture for generative adversarial networks. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition. pp. 4401\u20134410 (2019)","DOI":"10.1109\/CVPR.2019.00453"},{"key":"15_CR21","unstructured":"Kim, T., Cha, M., Kim, H., Lee, J.K., Kim, J.: Learning to discover cross-domain relations with generative adversarial networks. In: International conference on machine learning. pp. 1857\u20131865. PMLR (2017)"},{"key":"15_CR22","doi-asserted-by":"crossref","unstructured":"Kong, Y., Luo, C., Ma, W., Zhu, Q., Zhu, S., Yuan, N., Jin, L.: Look closer to supervise better: one-shot font generation via component-based discriminator. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition. pp. 13482\u201313491 (2022)","DOI":"10.1109\/CVPR52688.2022.01312"},{"key":"15_CR23","doi-asserted-by":"crossref","unstructured":"Li, C., Wand, M.: Precomputed real-time texture synthesis with markovian generative adversarial networks. In: Computer Vision\u2013ECCV 2016: 14th European Conference, Amsterdam, The Netherlands, October 11-14, 2016, Proceedings, Part III 14. pp. 702\u2013716. Springer (2016)","DOI":"10.1007\/978-3-319-46487-9_43"},{"key":"15_CR24","doi-asserted-by":"crossref","unstructured":"Liu, M.Y., Huang, X., Mallya, A., Karras, T., Aila, T., Lehtinen, J., Kautz, J.: Few-shot unsupervised image-to-image translation. In: Proceedings of the IEEE\/CVF international conference on computer vision. pp. 10551\u201310560 (2019)","DOI":"10.1109\/ICCV.2019.01065"},{"key":"15_CR25","doi-asserted-by":"crossref","unstructured":"Liu, S., Lin, T., He, D., Li, F., Wang, M., Li, X., Sun, Z., Li, Q., Ding, E.: Adaattn: Revisit attention mechanism in arbitrary neural style transfer. In: Proceedings of the IEEE\/CVF international conference on computer vision. pp. 6649\u20136658 (2021)","DOI":"10.1109\/ICCV48922.2021.00658"},{"key":"15_CR26","doi-asserted-by":"crossref","unstructured":"Liu, W., Liu, F., Ding, F., He, Q., Yi, Z.: Xmp-font: self-supervised cross-modality pre-training for few-shot font generation. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition. pp. 7905\u20137914 (2022)","DOI":"10.1109\/CVPR52688.2022.00775"},{"key":"15_CR27","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2023.109593","volume":"141","author":"Y Liu","year":"2023","unstructured":"Liu, Y., Lian, Z.: Fonttransformer: Few-shot high-resolution chinese glyph image synthesis via stacked transformers. Pattern Recogn. 141, 109593 (2023)","journal-title":"Pattern Recogn."},{"key":"15_CR28","doi-asserted-by":"crossref","unstructured":"Liu, Z., Lin, Y., Cao, Y., Hu, H., Wei, Y., Zhang, Z., Lin, S., Guo, B.: Swin transformer: Hierarchical vision transformer using shifted windows. In: Proceedings of the IEEE\/CVF international conference on computer vision. pp. 10012\u201310022 (2021)","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"15_CR29","doi-asserted-by":"crossref","unstructured":"Lyu, P., Bai, X., Yao, C., Zhu, Z., Huang, T., Liu, W.: Auto-encoder guided gan for chinese calligraphy synthesis. In: 2017 14th IAPR International Conference on Document Analysis and Recognition (ICDAR). vol.\u00a01, pp. 1095\u20131100. IEEE (2017)","DOI":"10.1109\/ICDAR.2017.181"},{"key":"15_CR30","doi-asserted-by":"crossref","unstructured":"Pan, W., Zhu, A., Zhou, X., Iwana, B.K., Li, S.: Few shot font generation via transferring similarity guided global style and quantization local style. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision. pp. 19506\u201319516 (2023)","DOI":"10.1109\/ICCV51070.2023.01787"},{"key":"15_CR31","doi-asserted-by":"crossref","unstructured":"Park, D.Y., Lee, K.H.: Arbitrary style transfer with style-attentional networks. In: proceedings of the IEEE\/CVF conference on computer vision and pattern recognition. pp. 5880\u20135888 (2019)","DOI":"10.1109\/CVPR.2019.00603"},{"key":"15_CR32","doi-asserted-by":"crossref","unstructured":"Park, S., Chun, S., Cha, J., Lee, B., Shim, H.: Few-shot font generation with localized style representations and factorization. In: Proceedings of the AAAI conference on artificial intelligence. vol.\u00a035, pp. 2393\u20132402 (2021)","DOI":"10.1609\/aaai.v35i3.16340"},{"key":"15_CR33","doi-asserted-by":"crossref","unstructured":"Park, S., Chun, S., Cha, J., Lee, B., Shim, H.: Multiple heads are better than one: Few-shot font generation with multiple localized experts. In: Proceedings of the IEEE\/CVF international conference on computer vision. pp. 13900\u201313909 (2021)","DOI":"10.1109\/ICCV48922.2021.01364"},{"key":"15_CR34","doi-asserted-by":"crossref","unstructured":"Paul, S., Chen, P.Y.: Vision transformers are robust learners. In: Proceedings of the AAAI conference on Artificial Intelligence. vol.\u00a036, pp. 2071\u20132081 (2022)","DOI":"10.1609\/aaai.v36i2.20103"},{"key":"15_CR35","first-page":"12116","volume":"34","author":"M Raghu","year":"2021","unstructured":"Raghu, M., Unterthiner, T., Kornblith, S., Zhang, C., Dosovitskiy, A.: Do vision transformers see like convolutional neural networks? Adv. Neural. Inf. Process. Syst. 34, 12116\u201312128 (2021)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"15_CR36","doi-asserted-by":"crossref","unstructured":"Sun, D., Ren, T., Li, C., Su, H., Zhu, J.: Learning to write stylized chinese characters by reading a handful of examples. arXiv preprint arXiv:1712.06424 (2017)","DOI":"10.24963\/ijcai.2018\/128"},{"key":"15_CR37","doi-asserted-by":"crossref","unstructured":"Sun, D., Zhang, Q., Yang, J.: Pyramid embedded generative adversarial network for automated font generation. In: 2018 24th International Conference on Pattern Recognition (ICPR). pp. 976\u2013981. IEEE (2018)","DOI":"10.1109\/ICPR.2018.8545701"},{"key":"15_CR38","doi-asserted-by":"crossref","unstructured":"Tang, L., Cai, Y., Liu, J., Hong, Z., Gong, M., Fan, M., Han, J., Liu, J., Ding, E., Wang, J.: Few-shot font generation by learning fine-grained local styles. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition. pp. 7895\u20137904 (2022)","DOI":"10.1109\/CVPR52688.2022.00774"},{"key":"15_CR39","unstructured":"Tian, Y.: zi2zi: Master chinese calligraphy with conditional adversarial networks. Internet] https:\/\/github. com\/kaonashi-tyc\/zi2zi 3, 2 (2017)"},{"key":"15_CR40","unstructured":"Vaswani, A., Shazeer, N., Parmar, N., Uszkoreit, J., Jones, L., Gomez, A.N., Kaiser, \u0141., Polosukhin, I.: Attention is all you need. Advances in neural information processing systems 30 (2017)"},{"key":"15_CR41","doi-asserted-by":"crossref","unstructured":"Wang, C., Zhou, M., Ge, T., Jiang, Y., Bao, H., Xu, W.: Cf-font: Content fusion for few-shot font generation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition. pp. 1858\u20131867 (2023)","DOI":"10.1109\/CVPR52729.2023.00185"},{"key":"15_CR42","unstructured":"Wu, S.J., Yang, C.Y., Hsu, J.Y.j.: Calligan: Style and structure-aware chinese calligraphy character generator. arXiv preprint arXiv:2005.12500 (2020)"},{"key":"15_CR43","doi-asserted-by":"crossref","unstructured":"Xie, Y., Chen, X., Sun, L., Lu, Y.: Dg-font: Deformable generative networks for unsupervised font generation. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition. pp. 5130\u20135140 (2021)","DOI":"10.1109\/CVPR46437.2021.00509"},{"key":"15_CR44","doi-asserted-by":"crossref","unstructured":"Zhang, R., Isola, P., Efros, A.A., Shechtman, E., Wang, O.: The unreasonable effectiveness of deep features as a perceptual metric. In: Proceedings of the IEEE conference on computer vision and pattern recognition. pp. 586\u2013595 (2018)","DOI":"10.1109\/CVPR.2018.00068"},{"key":"15_CR45","doi-asserted-by":"crossref","unstructured":"Zhang, Y., Zhang, Y., Cai, W.: Separating style and content for generalized style transfer. In: Proceedings of the IEEE conference on computer vision and pattern recognition. pp. 8447\u20138455 (2018)","DOI":"10.1109\/CVPR.2018.00881"}],"container-title":["Lecture Notes in Computer Science","Computer Vision \u2013 ACCV 2024"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-981-96-0917-8_15","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,12,7]],"date-time":"2024-12-07T08:26:39Z","timestamp":1733559999000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-981-96-0917-8_15"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,12,8]]},"ISBN":["9789819609161","9789819609178"],"references-count":45,"URL":"https:\/\/doi.org\/10.1007\/978-981-96-0917-8_15","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,12,8]]},"assertion":[{"value":"8 December 2024","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ACCV","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Asian Conference on Computer Vision","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Hanoi","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Vietnam","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2024","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"8 December 2024","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"12 December 2024","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"17","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"accv2024","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}