{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,2]],"date-time":"2026-01-02T00:14:57Z","timestamp":1767312897984,"version":"3.48.0"},"publisher-location":"Cham","reference-count":26,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783032073426","type":"print"},{"value":"9783032073433","type":"electronic"}],"license":[{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"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":[[2026]]},"DOI":"10.1007\/978-3-032-07343-3_13","type":"book-chapter","created":{"date-parts":[[2026,1,2]],"date-time":"2026-01-02T00:11:12Z","timestamp":1767312672000},"page":"159-171","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["SAViL-Det: Semantic-Aware Vision-Language Model for Multi-script Text Detection"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-4796-8230","authenticated-orcid":false,"given":"Mohammed-En-Nadhir","family":"Zighem","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9092-735X","authenticated-orcid":false,"given":"Abdenour","family":"Hadid","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2026,1,2]]},"reference":[{"key":"13_CR1","doi-asserted-by":"crossref","unstructured":"Baek, Y., Lee, B., Han, D., Yun, S., Lee, H.: Character region awareness for text detection. In: Proceedings of CVPR, pp. 9365\u20139374 (2019)","DOI":"10.1109\/CVPR.2019.00959"},{"issue":"10","key":"13_CR2","first-page":"1234","volume":"16","author":"R Blanco-Medina","year":"2022","unstructured":"Blanco-Medina, R., et al.: A survey on methods, datasets and implementations for scene text spotting. IET Image Proc. 16(10), 1234\u20131245 (2022)","journal-title":"IET Image Proc."},{"key":"13_CR3","doi-asserted-by":"crossref","unstructured":"Bu, Q., Park, S., Khang, M., Cheng, Y.: Srformer: text detection transformer with incorporated segmentation and regression. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol.\u00a038, pp. 855\u2013863 (2024)","DOI":"10.1609\/aaai.v38i2.27844"},{"key":"13_CR4","doi-asserted-by":"crossref","unstructured":"Deng, D., Liu, H., Li, X., Cai, D.: Pixellink: detecting scene text via instance segmentation (2018). https:\/\/arxiv.org\/abs\/1801.01315","DOI":"10.1609\/aaai.v32i1.12269"},{"key":"13_CR5","doi-asserted-by":"crossref","unstructured":"Karatzas, D., et al.: ICDAR 2013 robust reading competition. In: 2013 12th ICDAR, pp. 1484\u20131493. IEEE (2013)","DOI":"10.1109\/ICDAR.2013.221"},{"key":"13_CR6","unstructured":"Lefaudeux, B., et al.: xformers: a modular and hackable transformer modelling library (2022). https:\/\/github.com\/facebookresearch\/xformers"},{"issue":"1","key":"13_CR7","doi-asserted-by":"publisher","first-page":"919","DOI":"10.1109\/TPAMI.2022.3155612","volume":"45","author":"M Liao","year":"2022","unstructured":"Liao, M., Zou, Z., Wan, Z., Yao, C., Bai, X.: Real-time scene text detection with differentiable binarization and adaptive scale fusion. TPAMI 45(1), 919\u2013931 (2022)","journal-title":"TPAMI"},{"key":"13_CR8","doi-asserted-by":"crossref","unstructured":"Liu, Y., Jin, L., Zhang, S., Luo, C., Zhang, S.: Curved scene text detection via transverse and longitudinal sequence connection. Pattern Recognit. 90 (2019)","DOI":"10.1016\/j.patcog.2019.02.002"},{"key":"13_CR9","doi-asserted-by":"crossref","unstructured":"Long, S., Ruan, J., Zhang, W., He, X., Wu, W., Yao, C.: Textsnake: a flexible representation for detecting text of arbitrary shapes. In: ECCV, pp. 20\u201336 (2018)","DOI":"10.1007\/978-3-030-01216-8_2"},{"key":"13_CR10","doi-asserted-by":"crossref","unstructured":"Nayef, N., et al.: ICDAR2019 robust reading challenge on multi-lingual scene text detection and recognition. In: ICDAR, pp. 1582\u20131587 (2019)","DOI":"10.1109\/ICDAR.2019.00254"},{"key":"13_CR11","unstructured":"Pan, Y., et al.: Fast: faster arbitrarily-shaped text detector with minimalist kernel representation. In: ICCV (2021)"},{"key":"13_CR12","unstructured":"Radford, A., et al.: Learning transferable visual models from natural language supervision. In: ICML 2021 (2021)"},{"key":"13_CR13","unstructured":"Raisi, Z., Naiel, M.A., Fieguth, P., Wardell, S., Zelek, J.: Text detection and recognition in the wild: a review. arXiv preprint arXiv:2006.04305 (2020)"},{"key":"13_CR14","doi-asserted-by":"crossref","unstructured":"Song, S., et al.: Vision-language pre-training for boosting scene text detectors. In: CVPR, pp. 15681\u201315691 (2022)","DOI":"10.1109\/CVPR52688.2022.01523"},{"key":"13_CR15","doi-asserted-by":"crossref","unstructured":"Wang, W., et al.: Shape robust text detection with progressive scale expansion network. In: CVPR, pp. 9336\u20139345 (2019)","DOI":"10.1109\/CVPR.2019.00956"},{"key":"13_CR16","doi-asserted-by":"crossref","unstructured":"Wang, W., et al.: Efficient and accurate arbitrary-shaped text detection with pixel aggregation network. In: CVPR, pp. 8440\u20138449 (2019)","DOI":"10.1109\/ICCV.2019.00853"},{"key":"13_CR17","doi-asserted-by":"crossref","unstructured":"Xue, C., Zhang, W., Hao, Y., Lu, S., Torr, P.H., Bai, S.: Language matters: a weakly supervised vision-language pre-training approach for scene text detection and spotting. In: European Conference on Computer Vision. Springer (2022)","DOI":"10.1007\/978-3-031-19815-1_17"},{"key":"13_CR18","doi-asserted-by":"crossref","unstructured":"Yang, G., Lei, J., Zhu, Z., Cheng, S., Feng, Z., Liang, R.: AFPN: asymptotic feature pyramid network for object detection. In: 2023 IEEE International Conference on Systems, Man, and Cybernetics (SMC), pp. 2184\u20132189. IEEE (2023)","DOI":"10.1109\/SMC53992.2023.10394415"},{"key":"13_CR19","doi-asserted-by":"crossref","unstructured":"Ye, M., Zhang, J., Zhao, S., Liu, J., Du, B., Tao, D.: DPText-DETR: towards better scene text detection with dynamic points in transformer. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol.\u00a037, pp. 3241\u20133249 (2023)","DOI":"10.1609\/aaai.v37i3.25430"},{"key":"13_CR20","doi-asserted-by":"crossref","unstructured":"Ye, M., et al.: Deepsolo++: let transformer decoder with explicit points solo for multilingual text spotting (2023)","DOI":"10.1109\/CVPR52729.2023.01854"},{"key":"13_CR21","doi-asserted-by":"crossref","unstructured":"Yu, W., Liu, Y., Hua, W., Jiang, D., Ren, B., Bai, X.: Turning a clip model into a scene text detector. In: CVPR, pp. 6978\u20136988 (2023)","DOI":"10.1109\/CVPR52729.2023.00674"},{"key":"13_CR22","unstructured":"Zeng, Y.X., Hsieh, J.W., Li, X., Chang, M.C.: Mixnet: toward accurate detection of challenging scene text in the wild. arXiv preprint arXiv:2308.12817 (2023)"},{"key":"13_CR23","doi-asserted-by":"crossref","unstructured":"Zhang, C., et al.: Look more than once: an accurate detector for text of arbitrary shapes. In: CVPR (2019)","DOI":"10.1109\/CVPR.2019.01080"},{"key":"13_CR24","doi-asserted-by":"crossref","unstructured":"Zhang, X., Su, Y., Tripathi, S., Tu, Z.: Text spotting transformers. In: Proceedings of IEEE Conference on Computer Vision and Pattern Recognition, pp. 9519\u20139528 (2022)","DOI":"10.1109\/CVPR52688.2022.00930"},{"key":"13_CR25","doi-asserted-by":"crossref","unstructured":"Zhou, X., et al.: East: an efficient and accurate scene text detector. In: CVPR, pp. 5551\u20135560 (2017)","DOI":"10.1109\/CVPR.2017.283"},{"key":"13_CR26","doi-asserted-by":"crossref","unstructured":"Zhu, Y., Chen, J., Liang, L., Kuang, Z., Jin, L., Zhang, W.: Fourier contour embedding for arbitrary-shaped text detection. In: CVPR, pp. 3123\u20133131 (2021)","DOI":"10.1109\/CVPR46437.2021.00314"}],"container-title":["Lecture Notes in Computer Science","Advanced Concepts for Intelligent Vision Systems"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-032-07343-3_13","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,1,2]],"date-time":"2026-01-02T00:11:14Z","timestamp":1767312674000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-032-07343-3_13"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"ISBN":["9783032073426","9783032073433"],"references-count":26,"URL":"https:\/\/doi.org\/10.1007\/978-3-032-07343-3_13","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026]]},"assertion":[{"value":"2 January 2026","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ACIVS","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Advanced Concepts for Intelligent Vision Systems","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Tokyo","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Japan","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2025","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"28 July 2025","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"30 July 2025","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"22","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"acivs2025","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/www.acivs2025.com","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}