{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,8]],"date-time":"2026-05-08T16:33:50Z","timestamp":1778258030127,"version":"3.51.4"},"publisher-location":"Cham","reference-count":33,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783031732256","type":"print"},{"value":"9783031732263","type":"electronic"}],"license":[{"start":{"date-parts":[[2024,11,1]],"date-time":"2024-11-01T00:00:00Z","timestamp":1730419200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,11,1]],"date-time":"2024-11-01T00:00:00Z","timestamp":1730419200000},"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\/978-3-031-73226-3_21","type":"book-chapter","created":{"date-parts":[[2024,10,31]],"date-time":"2024-10-31T15:02:57Z","timestamp":1730386977000},"page":"361-377","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":24,"title":["Glyph-ByT5: A Customized Text Encoder for\u00a0Accurate Visual Text Rendering"],"prefix":"10.1007","author":[{"given":"Zeyu","family":"Liu","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Weicong","family":"Liang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhanhao","family":"Liang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Chong","family":"Luo","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ji","family":"Li","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Gao","family":"Huang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yuhui","family":"Yuan","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2024,11,1]]},"reference":[{"key":"21_CR1","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"319","DOI":"10.1007\/978-3-030-86549-8_21","volume-title":"Document Analysis and Recognition \u2013 ICDAR 2021","author":"R Atienza","year":"2021","unstructured":"Atienza, R.: Vision transformer for fast and efficient scene text recognition. In: Llad\u00f3s, J., Lopresti, D., Uchida, S. (eds.) ICDAR 2021. LNCS, vol. 12821, pp. 319\u2013334. Springer, Cham (2021). https:\/\/doi.org\/10.1007\/978-3-030-86549-8_21"},{"key":"21_CR2","unstructured":"Betker, J., et al.: Improving image generation with better captions (2023). https:\/\/cdn.openai.com\/papers\/dall-e-3.pdf"},{"key":"21_CR3","unstructured":"Bica, I., et al.: Improving fine-grained understanding in image-text pre-training. arXiv preprint arXiv:2401.09865 (2024)"},{"key":"21_CR4","unstructured":"Chen, H., et al.: Diffute: universal text editing diffusion model (2024)"},{"key":"21_CR5","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":"21_CR6","unstructured":"Chen, J., Huang, Y., Lv, T., Cui, L., Chen, Q., Wei, F.: Textdiffuser: diffusion models as text painters. arXiv preprint arXiv:2305.10855 (2023)"},{"key":"21_CR7","doi-asserted-by":"crossref","unstructured":"Chen, X., Huang, L., Liu, Y., Shen, Y., Zhao, D., Zhao, H.: Anydoor: zero-shot object-level image customization. arXiv preprint arXiv:2307.09481 (2023)","DOI":"10.1109\/CVPR52733.2024.00630"},{"key":"21_CR8","unstructured":"Darcet, T., Oquab, M., Mairal, J., Bojanowski, P.: Vision transformers need registers (2023)"},{"key":"21_CR9","unstructured":"Esser, P., et al.: Scaling rectified flow transformers for high-resolution image synthesis (2024)"},{"key":"21_CR10","unstructured":"Hu, E.J., et al.: Lora: low-rank adaptation of large language models. arXiv preprint arXiv:2106.09685 (2021)"},{"key":"21_CR11","unstructured":"Ji, J., et al.: Improving diffusion models for scene text editing with dual encoders. arXiv preprint arXiv:2304.05568 (2023)"},{"key":"21_CR12","unstructured":"Jia, P., et al.: Cole: a hierarchical generation framework for graphic design. arXiv preprint arXiv:2311.16974 (2023)"},{"key":"21_CR13","unstructured":"Lab, D.: Deepfloyd if (2023). https:\/\/github.com\/deep-floyd\/IF"},{"key":"21_CR14","unstructured":"Liu, H., Li, C., Wu, Q., Lee, Y.J.: Visual instruction tuning. In: Advances in Neural Information Processing Systems, vol. 36 (2024)"},{"key":"21_CR15","doi-asserted-by":"crossref","unstructured":"Liu, R., et al.: Character-aware models improve visual text rendering. In: Annual Meeting of the Association for Computational Linguistics (2022). https:\/\/api.semanticscholar.org\/CorpusID:254877579","DOI":"10.18653\/v1\/2023.acl-long.900"},{"key":"21_CR16","unstructured":"Liu, Z., Liang, W., Zhao, Y., Chen, B., Li, J., Yuan, Y.: Glyph-byt5-v2: a strong aesthetic baseline for accurate multilingual visual text rendering. arXiv preprint arXiv:2406.10208 (2024)"},{"key":"21_CR17","unstructured":"Ma, J., et al.: Glyphdraw: learning to draw Chinese characters in image synthesis models coherently. arXiv preprint arXiv:2303.17870 (2023)"},{"key":"21_CR18","unstructured":"OpenAI: DALL$$\\cdot $$E 3 system card (2023). https:\/\/cdn.openai.com\/papers\/DALL_E_3_System_Card.pdf"},{"key":"21_CR19","unstructured":"Oquab, M., et al.: Dinov2: learning robust visual features without supervision. arXiv preprint arXiv:2304.07193 (2023)"},{"key":"21_CR20","doi-asserted-by":"crossref","unstructured":"Paiss, R., et al.: Teaching clip to count to ten. arXiv preprint arXiv:2302.12066 (2023)","DOI":"10.1109\/ICCV51070.2023.00294"},{"key":"21_CR21","unstructured":"Podell, D., et al.: SDXL: improving latent diffusion models for high-resolution image synthesis. arXiv preprint arXiv:2307.01952 (2023)"},{"key":"21_CR22","unstructured":"Radford, A., et al.: Learning transferable visual models from natural language supervision. In: International Conference on Machine Learning, pp. 8748\u20138763. PMLR (2021)"},{"key":"21_CR23","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, pp. 10684\u201310695 (2022)","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"21_CR24","unstructured":"Touvron, H., et al.: Llama 2: open foundation and fine-tuned chat models. arXiv preprint arXiv:2307.09288 (2023)"},{"key":"21_CR25","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, pp. 12045\u201312055 (2021)","DOI":"10.1109\/CVPR46437.2021.01187"},{"key":"21_CR26","doi-asserted-by":"publisher","first-page":"291","DOI":"10.1162\/tacl_a_00461","volume":"10","author":"L Xue","year":"2022","unstructured":"Xue, L., et al.: ByT5: towards a token-free future with pre-trained byte-to-byte models. Trans. Assoc. Comput. Linguist. 10, 291\u2013306 (2022)","journal-title":"Trans. Assoc. Comput. Linguist."},{"key":"21_CR27","doi-asserted-by":"crossref","unstructured":"Xue, L., et al.: MT5: a massively multilingual pre-trained text-to-text transformer. arXiv preprint arXiv:2010.11934 (2020)","DOI":"10.18653\/v1\/2021.naacl-main.41"},{"key":"21_CR28","unstructured":"Yang, Y., et al.: Glyphcontrol: glyph conditional control for visual text generation. In: Advances in Neural Information Processing Systems, vol. 36 (2024)"},{"key":"21_CR29","doi-asserted-by":"crossref","unstructured":"Zhai, X., et al.: LIT: zero-shot transfer with locked-image text tuning. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 18123\u201318133 (2022)","DOI":"10.1109\/CVPR52688.2022.01759"},{"key":"21_CR30","unstructured":"Zhao, S., Wang, X., Zhu, L., Yang, Y.: CLIP4STR: a simple baseline for scene text recognition with pre-trained vision-language model. arXiv preprint arXiv:2305.14014 (2023)"},{"key":"21_CR31","doi-asserted-by":"crossref","unstructured":"Zhao, Y., Lian, Z.: Udifftext: a unified framework for high-quality text synthesis in arbitrary images via character-aware diffusion models. arXiv preprint arXiv:2312.04884 (2023)","DOI":"10.1007\/978-3-031-72751-1_13"},{"key":"21_CR32","doi-asserted-by":"crossref","unstructured":"Zhong, Y., et al.: Regionclip: region-based language-image pretraining. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 16793\u201316803 (2022)","DOI":"10.1109\/CVPR52688.2022.01629"},{"key":"21_CR33","doi-asserted-by":"crossref","unstructured":"Zhou, Y., Zhang, R., Gu, J., Sun, T.: Customization assistant for text-to-image generation. arXiv preprint arXiv:2312.03045 (2023)","DOI":"10.1109\/CVPR52733.2024.00877"}],"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\/978-3-031-73226-3_21","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,10,31]],"date-time":"2024-10-31T15:17:29Z","timestamp":1730387849000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-73226-3_21"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,11,1]]},"ISBN":["9783031732256","9783031732263"],"references-count":33,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-73226-3_21","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,11,1]]},"assertion":[{"value":"1 November 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"}}]}}