{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T17:26:46Z","timestamp":1777656406445,"version":"3.51.4"},"publisher-location":"Cham","reference-count":77,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783031727535","type":"print"},{"value":"9783031727542","type":"electronic"}],"license":[{"start":{"date-parts":[[2024,10,31]],"date-time":"2024-10-31T00:00:00Z","timestamp":1730332800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,10,31]],"date-time":"2024-10-31T00:00:00Z","timestamp":1730332800000},"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\/978-3-031-72754-2_10","type":"book-chapter","created":{"date-parts":[[2024,10,30]],"date-time":"2024-10-30T14:57:07Z","timestamp":1730300227000},"page":"166-185","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":2,"title":["Kinetic Typography Diffusion Model"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0009-0007-8890-554X","authenticated-orcid":false,"given":"Seonmi","family":"Park","sequence":"first","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1884-2268","authenticated-orcid":false,"given":"Inhwan","family":"Bae","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0009-0006-3012-9675","authenticated-orcid":false,"given":"Seunghyun","family":"Shin","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1105-1666","authenticated-orcid":false,"given":"Hae-Gon","family":"Jeon","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2024,10,31]]},"reference":[{"key":"10_CR1","unstructured":"Anderson, D., Shamir, A., Fried, O.: Neural font rendering. arXiv preprint arXiv:2211.14802 (2022)"},{"key":"10_CR2","doi-asserted-by":"crossref","unstructured":"Azadi, S., Fisher, M., Kim, V.G., Wang, Z., Shechtman, E., Darrell, T.: Multi-content gan for few-shot font style transfer. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR) (2018)","DOI":"10.1109\/CVPR.2018.00789"},{"key":"10_CR3","doi-asserted-by":"crossref","unstructured":"Bain, M., Nagrani, A., Varol, G., Zisserman, A.: Frozen in time: a joint video and image encoder for end-to-end retrieval. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision (ICCV) (2021)","DOI":"10.1109\/ICCV48922.2021.00175"},{"key":"10_CR4","unstructured":"Barratt, S., Sharma, R.: A note on the inception score. arXiv preprint arXiv:1801.01973 (2018)"},{"key":"10_CR5","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3505246","volume":"41","author":"D Berio","year":"2022","unstructured":"Berio, D., Leymarie, F.F., Asente, P., Echevarria, J.: Strokestyles: stroke-based segmentation and stylization of fonts. ACM Trans. Graph. (TOG) 41, 1\u201321 (2022)","journal-title":"ACM Trans. Graph. (TOG)"},{"key":"10_CR6","unstructured":"Blattmann, A., et\u00a0al.: Stable video diffusion: scaling latent video diffusion models to large datasets. arXiv preprint arXiv:2311.15127 (2023)"},{"key":"10_CR7","doi-asserted-by":"crossref","unstructured":"Blattmann, A., et al.: Align your latents: high-resolution video synthesis with latent diffusion models. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR) (2023)","DOI":"10.1109\/CVPR52729.2023.02161"},{"key":"10_CR8","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/2601097.2601212","volume":"33","author":"ND Campbell","year":"2014","unstructured":"Campbell, N.D., Kautz, J.: Learning a manifold of fonts. ACM Trans. Graph. (TOG) 33, 1\u201311 (2014)","journal-title":"ACM Trans. Graph. (TOG)"},{"key":"10_CR9","doi-asserted-by":"crossref","unstructured":"Chen, C.H., Liu, Y.T., Zhang, Z., Guo, Y.C., Zhang, S.H.: Joint implicit neural representation for high-fidelity and compact vector fonts. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision (ICCV) (2023)","DOI":"10.1109\/ICCV51070.2023.00510"},{"key":"10_CR10","doi-asserted-by":"crossref","unstructured":"Chen, J., Huang, Y., Lv, T., Cui, L., Chen, Q., Wei, F.: Textdiffuser-2: unleashing the power of language models for text rendering. arXiv preprint arXiv:2311.16465 (2023)","DOI":"10.1007\/978-3-031-72652-1_23"},{"key":"10_CR11","unstructured":"Chen, J., Huang, Y., Lv, T., Cui, L., Chen, Q., Wei, F.: Textdiffuser: diffusion models as text painters. In: Proceedings of the Neural Information Processing Systems (NeurIPS) (2023)"},{"key":"10_CR12","doi-asserted-by":"crossref","unstructured":"Esser, P., Chiu, J., Atighehchian, P., Granskog, J., Germanidis, A.: Structure and content-guided video synthesis with diffusion models. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision (ICCV) (2023)","DOI":"10.1109\/ICCV51070.2023.00675"},{"key":"10_CR13","doi-asserted-by":"crossref","unstructured":"Ford, S., Forlizzi, J., Ishizaki, S.: Kinetic typography: issues in time-based presentation of text. In: CHI\u201997 Extended Abstracts on Human Factors in Computing Systems, pp. 269\u2013270. ACM Digital Library (1997)","DOI":"10.1145\/1120212.1120387"},{"key":"10_CR14","unstructured":"Fridsma, L., Gyncild, B.: Adobe After Effects CC Classroom in a Book. Adobe Press (2019)"},{"key":"10_CR15","doi-asserted-by":"crossref","unstructured":"Fu, B., He, J., Wang, J., Qiao, Y.: Neural transformation fields for arbitrary-styled font generation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR) (2023)","DOI":"10.1109\/CVPR52729.2023.02149"},{"key":"10_CR16","doi-asserted-by":"crossref","unstructured":"Ge, S., et al.: Preserve your own correlation: a noise prior for video diffusion models. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision (ICCV) (2023)","DOI":"10.1109\/ICCV51070.2023.02096"},{"key":"10_CR17","doi-asserted-by":"crossref","unstructured":"Guo, Y., Yang, C., Rao, A., Agrawala, M., Lin, D., Dai, B.: Sparsectrl: adding sparse controls to text-to-video diffusion models. arXiv preprint arXiv:2311.16933 (2023)","DOI":"10.1007\/978-3-031-72946-1_19"},{"key":"10_CR18","unstructured":"Guo, Y., et al.: AnimateDiff: animate your personalized text-to-image diffusion models without specific tuning. arXiv preprint arXiv:2307.04725 (2023)"},{"key":"10_CR19","doi-asserted-by":"crossref","unstructured":"Hessel, J., Holtzman, A., Forbes, M., Le\u00a0Bras, R., Choi, Y.: Clipscore: A reference-free evaluation metric for image captioning. In: Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing (2021)","DOI":"10.18653\/v1\/2021.emnlp-main.595"},{"key":"10_CR20","unstructured":"Ho, J., et\u00a0al.: Imagen video: high definition video generation with diffusion models. arXiv preprint arXiv:2210.02303 (2022)"},{"key":"10_CR21","doi-asserted-by":"crossref","unstructured":"Hu, Y., Luo, C., Chen, Z.: Make it move: controllable image-to-video generation with text descriptions. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR) (2022)","DOI":"10.1109\/CVPR52688.2022.01768"},{"key":"10_CR22","doi-asserted-by":"crossref","unstructured":"Huang, Y., Xue, H., Liu, B., Lu, Y.: Unifying multimodal transformer for bi-directional image and text generation. In: Proceedings of the 29th ACM International Conference on Multimedia, pp. 1138\u20131147 (2021)","DOI":"10.1145\/3474085.3481540"},{"key":"10_CR23","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3592123","volume":"42","author":"S Iluz","year":"2023","unstructured":"Iluz, S., Vinker, Y., Hertz, A., Berio, D., Cohen-Or, D., Shamir, A.: Word-as-image for semantic typography. ACM Trans. Graph. (TOG) 42, 1\u201311 (2023)","journal-title":"ACM Trans. Graph. (TOG)"},{"key":"10_CR24","doi-asserted-by":"crossref","unstructured":"Jahanian, A., et al.: Recommendation system for automatic design of magazine covers. In: Proceedings of the 2013 International Conference on Intelligent User Interfaces (IUI) (2013)","DOI":"10.1145\/2449396.2449411"},{"key":"10_CR25","unstructured":"Jia, P., et\u00a0al.: Cole: a hierarchical generation framework for graphic design. arXiv preprint arXiv:2311.16974 (2023)"},{"key":"10_CR26","doi-asserted-by":"crossref","unstructured":"Kato, J., Nakano, T., Goto, M.: Textalive: integrated design environment for kinetic typography. In: Proceedings of the 33rd Annual ACM Conference on Human Factors in Computing Systems (CHI) (2015)","DOI":"10.1145\/2702123.2702140"},{"key":"10_CR27","doi-asserted-by":"crossref","unstructured":"Krishnan, P., Kovvuri, R., Pang, G., Vassilev, B., Hassner, T.: Textstylebrush: transfer of text aesthetics from a single example. IEEE Trans. Pattern Anal. Mach. Intell. (TPAMI) (2023)","DOI":"10.1109\/TPAMI.2023.3239736"},{"key":"10_CR28","doi-asserted-by":"crossref","unstructured":"Lee, J.C., Forlizzi, J., Hudson, S.E.: The kinetic typography engine: an extensible system for animating expressive text. In: Proceedings of the 15th Annual ACM Symposium on User Interface Software and Technology (UIST) (2002)","DOI":"10.1145\/571985.571997"},{"key":"10_CR29","doi-asserted-by":"crossref","unstructured":"Lee, J., Jun, S., Forlizzi, J., Hudson, S.E.: Using kinetic typography to convey emotion in text-based interpersonal communication. In: Proceedings of the 6th Conference on Designing Interactive systems (DIS) (2006)","DOI":"10.1145\/1142405.1142414"},{"key":"10_CR30","doi-asserted-by":"crossref","unstructured":"Li, C., Taniguchi, Y., Lu, M., Konomi, S.: Few-shot font style transfer between different languages. In: Proceedings of the IEEE\/CVF Winter Conference on Applications of Computer Vision (WACV) (2021)","DOI":"10.1109\/WACV48630.2021.00048"},{"key":"10_CR31","doi-asserted-by":"crossref","unstructured":"Li, X., Wu, L., Wang, C., Meng, L., Meng, X.: Compositional zero-shot artistic font synthesis. In: Proceedings of the International Joint Conferences on Artificial Intelligence (IJCAI) (2023)","DOI":"10.24963\/ijcai.2023\/122"},{"key":"10_CR32","doi-asserted-by":"publisher","first-page":"1787","DOI":"10.1109\/TMM.2021.3072449","volume":"24","author":"X Liu","year":"2021","unstructured":"Liu, X., Meng, G., Chang, J., Hu, R., Xiang, S., Pan, C.: Decoupled representation learning for character glyph synthesis. IEEE Trans. Multimedia (TMM) 24, 1787\u20131799 (2021)","journal-title":"IEEE Trans. Multimedia (TMM)"},{"key":"10_CR33","doi-asserted-by":"publisher","first-page":"4172","DOI":"10.1109\/TVCG.2022.3183400","volume":"29","author":"YT Liu","year":"2022","unstructured":"Liu, Y.T., Guo, Y.C., Li, Y.X., Wang, C., Zhang, S.H.: Learning implicit glyph shape representation. IEEE Trans. Visualizat. Comput. Graph. (TVCG) 29, 4172\u20134182 (2022)","journal-title":"IEEE Trans. Visualizat. Comput. Graph. (TVCG)"},{"key":"10_CR34","doi-asserted-by":"crossref","unstructured":"Liu, Y.T., Zhang, Z., Guo, Y.C., Fisher, M., Wang, Z., Zhang, S.H.: Dualvector: unsupervised vector font synthesis with dual-part representation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR) (2023)","DOI":"10.1109\/CVPR52729.2023.01364"},{"key":"10_CR35","unstructured":"Loshchilov, I., Hutter, F.: Decoupled weight decay regularization. In: Proceedings of the International Conference on Learning Representations (ICLR) (2018)"},{"key":"10_CR36","doi-asserted-by":"crossref","unstructured":"Luo, Z., et al.: Videofusion: decomposed diffusion models for high-quality video generation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR) (2023)","DOI":"10.1109\/CVPR52729.2023.10308948"},{"key":"10_CR37","doi-asserted-by":"crossref","unstructured":"Men, Y., Lian, Z., Tang, Y., Xiao, J.: Dyntypo: example-based dynamic text effects transfer. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR) (2019)","DOI":"10.1109\/CVPR.2019.00602"},{"key":"10_CR38","doi-asserted-by":"crossref","unstructured":"Minakuchi, M., Tanaka, K.: Automatic kinetic typography composer. In: Proceedings of the ACM SIGCHI International Conference on Advances in Computer Entertainment Technology (ACE) (2005)","DOI":"10.1145\/1178477.1178512"},{"key":"10_CR39","doi-asserted-by":"crossref","unstructured":"Mu, X., et al.: Fontstudio: shape-adaptive diffusion model for coherent and consistent font effect generation. arXiv preprint arXiv:2406.08392 (2024)","DOI":"10.1007\/978-3-031-73636-0_18"},{"key":"10_CR40","doi-asserted-by":"crossref","unstructured":"Nagata, Y., Iwana, B.K., Uchida, S.: Contour completion by transformers and its application to vector font data. arXiv preprint arXiv:2304.13988 (2023)","DOI":"10.1007\/978-3-031-41734-4_30"},{"key":"10_CR41","unstructured":"OpenAI: GPT-4V(ision) system card (2023). https:\/\/cdn.openai.com\/papers\/GPTV_System_Card.pdf"},{"key":"10_CR42","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 (ICCV) (2023)","DOI":"10.1109\/ICCV51070.2023.01787"},{"key":"10_CR43","doi-asserted-by":"crossref","unstructured":"Qu, Y., Tan, Q., Xie, H., Xu, J., Wang, Y., Zhang, Y.: Exploring stroke-level modifications for scene text editing. In: Proceedings of the AAAI Conference on Artificial Intelligence (AAAI) (2023)","DOI":"10.1609\/aaai.v37i2.25305"},{"key":"10_CR44","unstructured":"Radford, A., et\u00a0al.: Learning transferable visual models from natural language supervision. In: Proceedings of the International Conference on Machine Learning (ICML) (2021)"},{"key":"10_CR45","unstructured":"Reddy, P., Zhang, Z., Wang, Z., Fisher, M., Jin, H., Mitra, N.: A multi-implicit neural representation for fonts. In: Proceedings of the Neural Information Processing Systems (NeurIPS) (2021)"},{"key":"10_CR46","doi-asserted-by":"crossref","unstructured":"Rombach, R., Blattmann, A., Lorenz, D., Esser, P., Ommer, B.: High-resolution image synthesis with latent diffusion models. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR) (2022)","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"10_CR47","doi-asserted-by":"crossref","unstructured":"Shimoda, W., Haraguchi, D., Uchida, S., Yamaguchi, K.: De-rendering stylized texts. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision (ICCV) (2021)","DOI":"10.1109\/ICCV48922.2021.00111"},{"key":"10_CR48","doi-asserted-by":"crossref","unstructured":"Shimoda, W., Haraguchi, D., Uchida, S., Yamaguchi, K.: Towards diverse and consistent typography generation. In: Proceedings of the IEEE\/CVF Winter Conference on Applications of Computer Vision (WACV) (2024)","DOI":"10.1109\/WACV57701.2024.00713"},{"key":"10_CR49","unstructured":"Singer, U., et\u00a0al.: Make-a-video: text-to-video generation without text-video data. In: Proceedings of the International Conference on Learning Representations (ICLR) (2023)"},{"key":"10_CR50","volume-title":"Adobe After Effects CS6 Digital Classroom","author":"Smith, J., Team, A.C.","year":"2012","unstructured":"Smith, J., Team, A.C.: Adobe After Effects CS6 Digital Classroom. John Wiley & Sons, Hoboken (2012)"},{"key":"10_CR51","unstructured":"Subramanian, J., Chordia, V., Bart, E., Fang, S., Guan, K., Bala, R., et\u00a0al.: Strive: scene text replacement in videos. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision (ICCV) (2021)"},{"key":"10_CR52","doi-asserted-by":"crossref","unstructured":"Tanveer, M., Wang, Y., Mahdavi-Amiri, A., Zhang, H.: Ds-fusion: artistic typography via discriminated and stylized diffusion. arXiv preprint arXiv:2303.09604 (2023)","DOI":"10.1109\/ICCV51070.2023.00041"},{"key":"10_CR53","doi-asserted-by":"crossref","unstructured":"Thamizharasan, V., et al.: Vecfusion: vector font generation with diffusion. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR) (2024)","DOI":"10.1109\/CVPR52733.2024.00759"},{"key":"10_CR54","unstructured":"Tuo, Y., Xiang, W., He, J.Y., Geng, Y., Xie, X.: Anytext: multilingual visual text generation and editing. In: Proceedings of the International Conference on Learning Representations (ICLR) (2024)"},{"key":"10_CR55","unstructured":"Unterthiner, T., Van\u00a0Steenkiste, S., Kurach, K., Marinier, R., Michalski, M., Gelly, S.: Towards accurate generative models of video: a new metric & challenges. arXiv preprint arXiv:1812.01717 (2018)"},{"key":"10_CR56","doi-asserted-by":"crossref","unstructured":"Wang, C., Wu, L., Liu, X., Li, X., Meng, L., Meng, X.: Anything to glyph: artistic font synthesis via text-to-image diffusion model. In: SIGGRAPH Asia 2023 Conference Papers (2023)","DOI":"10.1145\/3610548.3618208"},{"key":"10_CR57","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 (CVPR) (2023)","DOI":"10.1109\/CVPR52729.2023.00185"},{"key":"10_CR58","unstructured":"Wang, Y., et\u00a0al.: Lavie: high-quality video generation with cascaded latent diffusion models. arXiv preprint arXiv:2309.15103 (2023)"},{"key":"10_CR59","doi-asserted-by":"crossref","unstructured":"Wang, Y., Ye, Y., Mao, Y., Yu, Y., Song, Y.: Self-supervised scene text segmentation with object-centric layered representations augmented by text regions. In: Proceedings of the 30th ACM International Conference on Multimedia (2022)","DOI":"10.1145\/3503161.3548315"},{"key":"10_CR60","doi-asserted-by":"crossref","unstructured":"Wang, Y., Lian, Z.: Deepvecfont: synthesizing high-quality vector fonts via dual-modality learning. ACM Trans. Graph. (TOG) (2021)","DOI":"10.1145\/3478513.3480488"},{"key":"10_CR61","doi-asserted-by":"crossref","unstructured":"Wang, Y., et al.: Aesthetic text logo synthesis via content-aware layout inferring. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR) (2022)","DOI":"10.1109\/CVPR52688.2022.00247"},{"key":"10_CR62","doi-asserted-by":"crossref","unstructured":"Wang, Y., Wang, Y., Yu, L., Zhu, Y., Lian, Z.: Deepvecfont-v2: exploiting transformers to synthesize vector fonts with higher quality. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR) (2023)","DOI":"10.1109\/CVPR52729.2023.01757"},{"key":"10_CR63","doi-asserted-by":"crossref","unstructured":"Wong, Y.Y.: Temporal typography: a proposal to enrich written expression. In: Proceedings of the Conference Companion on Human Factors in Computing Systems (CHI) (1996)","DOI":"10.1145\/257089.257401"},{"key":"10_CR64","doi-asserted-by":"crossref","unstructured":"Xia, Z., Xiong, B., Lian, Z.: Vecfontsdf: learning to reconstruct and synthesize high-quality vector fonts via signed distance functions. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR) (2023)","DOI":"10.1109\/CVPR52729.2023.00184"},{"key":"10_CR65","doi-asserted-by":"crossref","unstructured":"Xie, L., Shu, X., Su, J.C., Wang, Y., Chen, S., Qu, H.: Creating emordle: animating word cloud for emotion expression. IEEE Trans. Visualizat. Comput. Graph. (TVCG) (2023)","DOI":"10.1109\/TVCG.2023.3286392"},{"key":"10_CR66","doi-asserted-by":"crossref","unstructured":"Xie, L., Zhou, Z., Yu, K., Wang, Y., Qu, H., Chen, S.: Wakey-wakey: animate text by mimicking characters in a gif. In: Proceedings of the 36th Annual ACM Symposium on User Interface Software and Technology (2023)","DOI":"10.1145\/3586183.3606813"},{"key":"10_CR67","doi-asserted-by":"crossref","unstructured":"Xu, C., Zhou, M., Ge, T., Jiang, Y., Xu, W.: Unsupervised domain adaption with pixel-level discriminator for image-aware layout generation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR) (2023)","DOI":"10.1109\/CVPR52729.2023.00975"},{"key":"10_CR68","doi-asserted-by":"crossref","unstructured":"Xu, X., Zhang, Z., Wang, Z., Price, B., Wang, Z., Shi, H.: Rethinking text segmentation: a novel dataset and a text-specific refinement approach. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR) (2021)","DOI":"10.1109\/CVPR46437.2021.01187"},{"key":"10_CR69","doi-asserted-by":"crossref","unstructured":"Yang, Q., Huang, J., Lin, W.: Swaptext: image based texts transfer in scenes. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR) (2020)","DOI":"10.1109\/CVPR42600.2020.01471"},{"key":"10_CR70","doi-asserted-by":"crossref","unstructured":"Yang, S., Liu, J., Lian, Z., Guo, Z.: Awesome typography: statistics-based text effects transfer. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR) (2017)","DOI":"10.1109\/CVPR.2017.308"},{"key":"10_CR71","doi-asserted-by":"crossref","unstructured":"Yang, S., Wang, W., Liu, J.: Te141k: artistic text benchmark for text effect transfer. IEEE Trans. Pattern Anal. Mach. Intell. (TPAMI) (2020)","DOI":"10.1109\/TPAMI.2020.2983697"},{"key":"10_CR72","doi-asserted-by":"crossref","unstructured":"Yang, S., Wang, Z., Liu, J.: Shape-matching gan++: scale controllable dynamic artistic text style transfer. IIEEE Trans. Pattern Anal. Mach. Intell. (TPAMI) (2021)","DOI":"10.1109\/TPAMI.2021.3055211"},{"key":"10_CR73","doi-asserted-by":"crossref","unstructured":"Yang, S., Wang, Z., Wang, Z., Xu, N., Liu, J., Guo, Z.: Controllable artistic text style transfer via shape-matching gan. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision (ICCV) (2019)","DOI":"10.1109\/ICCV.2019.00454"},{"key":"10_CR74","unstructured":"Yang, Y., et al.: Glyphcontrol: glyph conditional control for visual text generation. In: Proceedings of the Neural Information Processing Systems (NeurIPS) (2023)"},{"key":"10_CR75","doi-asserted-by":"crossref","unstructured":"Yang, Z., Peng, D., Kong, Y., Zhang, Y., Yao, C., Jin, L.: Fontdiffuser: one-shot font generation via denoising diffusion with multi-scale content aggregation and style contrastive learning. arXiv preprint arXiv:2312.12142 (2023)","DOI":"10.1609\/aaai.v38i7.28482"},{"key":"10_CR76","doi-asserted-by":"crossref","unstructured":"Zhang, L., Rao, A., Agrawala, M.: Adding conditional control to text-to-image diffusion models. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision (ICCV) (2023)","DOI":"10.1109\/ICCV51070.2023.00355"},{"key":"10_CR77","doi-asserted-by":"crossref","unstructured":"Zhang, S., Ma, J., Wu, J., Ritchie, D., Agrawala, M.: Editing motion graphics video via motion vectorization and transformation. ACM Trans. Graph. (TOG) (2023)","DOI":"10.1145\/3618316"}],"container-title":["Lecture Notes in Computer Science","Computer Vision \u2013 ECCV 2024"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-72754-2_10","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,11,30]],"date-time":"2024-11-30T14:09:25Z","timestamp":1732975765000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-72754-2_10"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,10,31]]},"ISBN":["9783031727535","9783031727542"],"references-count":77,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-72754-2_10","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,10,31]]},"assertion":[{"value":"31 October 2024","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ECCV","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"European Conference on Computer Vision","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Milan","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Italy","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":"29 September 2024","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"4 October 2024","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"18","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"eccv2024","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/eccv2024.ecva.net\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}