{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,21]],"date-time":"2026-05-21T06:56:12Z","timestamp":1779346572802,"version":"3.51.4"},"publisher-location":"Singapore","reference-count":33,"publisher":"Springer Nature Singapore","isbn-type":[{"value":"9789819543779","type":"print"},{"value":"9789819543786","type":"electronic"}],"license":[{"start":{"date-parts":[[2025,11,9]],"date-time":"2025-11-09T00:00:00Z","timestamp":1762646400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2025,11,9]],"date-time":"2025-11-09T00:00:00Z","timestamp":1762646400000},"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\/978-981-95-4378-6_13","type":"book-chapter","created":{"date-parts":[[2025,11,10]],"date-time":"2025-11-10T15:53:05Z","timestamp":1762789985000},"page":"181-195","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["Scene Text Reconstructor: A Contextual-Aware Masking Framework for\u00a0Pre-training Text Detectors"],"prefix":"10.1007","author":[{"given":"Yaohou","family":"Fan","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Tomo","family":"Miyazaki","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhengmi","family":"Tang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Juan","family":"Wang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yongsong","family":"Huang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Shinichiro","family":"Omachi","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2025,11,9]]},"reference":[{"key":"13_CR1","doi-asserted-by":"crossref","unstructured":"Ch\u2019ng, C.K., Chan, C.S., Liu, C.L.: Total-text: toward orientation robustness in scene text detection. Int. J. Docum. Anal. Recog. (IJDAR) 23(1), 31\u201352 (2020)","DOI":"10.1007\/s10032-019-00334-z"},{"key":"13_CR2","unstructured":"Dosovitskiy, A., et\u00a0al.: An image is worth 16x16 words: transformers for image recognition at scale. arXiv preprint arXiv:2010.11929 (2020)"},{"key":"13_CR3","doi-asserted-by":"crossref","unstructured":"Duan, C., Fu, P., Guo, S., Jiang, Q., Wei, X.: ODM: a text-image further alignment pre-training approach for scene text detection and spotting. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 15587\u201315597 (2024)","DOI":"10.1109\/CVPR52733.2024.01476"},{"key":"13_CR4","doi-asserted-by":"crossref","unstructured":"Gupta, A., Vedaldi, A., Zisserman, A.: Synthetic data for text localisation in natural images. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 2315\u20132324 (2016)","DOI":"10.1109\/CVPR.2016.254"},{"key":"13_CR5","doi-asserted-by":"crossref","unstructured":"Gupta, A., Vedaldi, A., Zisserman, A.: Synthetic data for text localisation in natural images. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 2315\u20132324 (2016)","DOI":"10.1109\/CVPR.2016.254"},{"key":"13_CR6","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":"13_CR7","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 770\u2013778 (2016)","DOI":"10.1109\/CVPR.2016.90"},{"key":"13_CR8","doi-asserted-by":"crossref","unstructured":"Karatzas, D., et\u00a0al.: ICDAR 2015 competition on robust reading. In: 2015 13th International Conference on Document Analysis and Recognition (ICDAR), pp. 1156\u20131160. IEEE (2015)","DOI":"10.1109\/ICDAR.2015.7333942"},{"issue":"8","key":"13_CR9","doi-asserted-by":"publisher","first-page":"3676","DOI":"10.1109\/TIP.2018.2825107","volume":"27","author":"M Liao","year":"2018","unstructured":"Liao, M., Shi, B., Bai, X.: Textboxes++: a single-shot oriented scene text detector. IEEE Trans. Image Process. 27(8), 3676\u20133690 (2018)","journal-title":"IEEE Trans. Image Process."},{"key":"13_CR10","doi-asserted-by":"crossref","unstructured":"Liao, M., Wan, Z., Yao, C., Chen, K., Bai, X.: Real-time scene text detection with differentiable binarization. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol.\u00a034, pp. 11474\u201311481 (2020)","DOI":"10.1609\/aaai.v34i07.6812"},{"key":"13_CR11","unstructured":"Liu, B., Wang, M., Foroosh, H., Tappen, M., Pensky, M.: Sparse convolutional neural networks. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 806\u2013814 (2015)"},{"key":"13_CR12","unstructured":"Radford, A., et\u00a0al.: Learning transferable visual models from natural language supervision. In: International Conference on Machine Learning, pp. 8748\u20138763. PMLR (2021)"},{"key":"13_CR13","unstructured":"Radford, A., et\u00a0al.: Learning transferable visual models from natural language supervision. In: International Conference on Machine Learning, pp. 8748\u20138763. PMLR (2021)"},{"key":"13_CR14","doi-asserted-by":"publisher","unstructured":"Ronneberger, O., Fischer, P., Brox, T.: U-Net: convolutional networks for biomedical image segmentation. In: Navab, N., Hornegger, J., Wells, W.M., Frangi, A.F. (eds.) MICCAI 2015. LNCS, vol. 9351, pp. 234\u2013241. Springer, Cham (2015). https:\/\/doi.org\/10.1007\/978-3-319-24574-4_28","DOI":"10.1007\/978-3-319-24574-4_28"},{"key":"13_CR15","doi-asserted-by":"crossref","unstructured":"Song, S., et al.: Vision-language pre-training for boosting scene text detectors. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 15681\u201315691 (2022)","DOI":"10.1109\/CVPR52688.2022.01523"},{"key":"13_CR16","unstructured":"Tan, M., Le, Q.: EfficientNet: rethinking model scaling for convolutional neural networks. In: International Conference on Machine Learning, pp. 6105\u20136114. PMLR (2019)"},{"key":"13_CR17","doi-asserted-by":"publisher","first-page":"5837","DOI":"10.1109\/TIP.2023.3326685","volume":"32","author":"Z Tang","year":"2023","unstructured":"Tang, Z., Miyazaki, T., Omachi, S.: A scene-text synthesis engine achieved through learning from decomposed real-world data. IEEE Trans. Image Process. 32, 5837\u20135851 (2023)","journal-title":"IEEE Trans. Image Process."},{"key":"13_CR18","doi-asserted-by":"publisher","DOI":"10.1016\/j.knosys.2025.113306","volume":"315","author":"Z Tang","year":"2025","unstructured":"Tang, Z., Miyazaki, T., Wang, Z., Huang, Y., Mailoa, J.P., Omachi, S.: VQ-STE: scene text erasing with mask refinement and vector-quantized texture dictionary. Knowl.-Based Syst. 315, 113306 (2025)","journal-title":"Knowl.-Based Syst."},{"key":"13_CR19","unstructured":"Tian, K., Jiang, Y., Diao, Q., Lin, C., Wang, L., Yuan, Z.: Designing BERT for convolutional networks: sparse and hierarchical masked modeling. arXiv preprint arXiv:2301.03580 (2023)"},{"key":"13_CR20","doi-asserted-by":"crossref","unstructured":"Wan, Q., Ji, H., Shen, L.: Self-attention based text knowledge mining for text detection. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 5983\u20135992 (2021)","DOI":"10.1109\/CVPR46437.2021.00592"},{"key":"13_CR21","doi-asserted-by":"crossref","unstructured":"Wang, K., et al.: Masked text modeling: a self-supervised pre-training method for scene text detection. In: Proceedings of the 31st ACM International Conference on Multimedia, pp. 2006\u20132015 (2023)","DOI":"10.1145\/3581783.3612370"},{"key":"13_CR22","doi-asserted-by":"crossref","unstructured":"Wang, Wet al.: Shape robust text detection with progressive scale expansion network. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 9336\u20139345 (2019)","DOI":"10.1109\/CVPR.2019.00956"},{"key":"13_CR23","doi-asserted-by":"crossref","unstructured":"Wang, W., et al.: Efficient and accurate arbitrary-shaped text detection with pixel aggregation network. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 8440\u20138449 (2019)","DOI":"10.1109\/ICCV.2019.00853"},{"key":"13_CR24","doi-asserted-by":"crossref","unstructured":"Wang, Y., Xie, H., Zha, Z.J., Xing, M., Fu, Z., Zhang, Y.: ContourNet: taking a further step toward accurate arbitrary-shaped scene text detection. In: proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 11753\u201311762 (2020)","DOI":"10.1109\/CVPR42600.2020.01177"},{"key":"13_CR25","doi-asserted-by":"crossref","unstructured":"Wei, C., Fan, H., Xie, S., Wu, C.Y., Yuille, A., Feichtenhofer, C.: Masked feature prediction for self-supervised visual pre-training. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 14668\u201314678 (2022)","DOI":"10.1109\/CVPR52688.2022.01426"},{"key":"13_CR26","doi-asserted-by":"crossref","unstructured":"Xie, Z., et al.: SimMIM: a simple framework for masked image modeling. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 9653\u20139663 (2022)","DOI":"10.1109\/CVPR52688.2022.00943"},{"key":"13_CR27","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, pp. 284\u2013302. Springer (2022)","DOI":"10.1007\/978-3-031-19815-1_17"},{"key":"13_CR28","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: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 6978\u20136988 (2023)","DOI":"10.1109\/CVPR52729.2023.00674"},{"key":"13_CR29","unstructured":"Yuliang, L., Lianwen, J., Shuaitao, Z., Sheng, Z.: Detecting curve text in the wild: new dataset and new solution. arXiv preprint arXiv:1712.02170 (2017)"},{"key":"13_CR30","doi-asserted-by":"crossref","unstructured":"Zhan, F., Lu, S., Xue, C.: Verisimilar image synthesis for accurate detection and recognition of texts in scenes. In: Proceedings of the European Conference on Computer Vision (ECCV), pp. 249\u2013266 (2018)","DOI":"10.1007\/978-3-030-01237-3_16"},{"key":"13_CR31","doi-asserted-by":"crossref","unstructured":"Zhang, C., et al.: Look more than once: an accurate detector for text of arbitrary shapes. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 10552\u201310561 (2019)","DOI":"10.1109\/CVPR.2019.01080"},{"key":"13_CR32","doi-asserted-by":"crossref","unstructured":"Zhou, X., et al: East: an efficient and accurate scene text detector. In: Proceedings of the IEEE conference on Computer Vision and Pattern Recognition, pp. 5551\u20135560 (2017)","DOI":"10.1109\/CVPR.2017.283"},{"key":"13_CR33","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: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 3123\u20133131 (2021)","DOI":"10.1109\/CVPR46437.2021.00314"}],"container-title":["Lecture Notes in Computer Science","Neural Information Processing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-981-95-4378-6_13","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,1,9]],"date-time":"2026-01-09T05:58:51Z","timestamp":1767938331000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-981-95-4378-6_13"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,11,9]]},"ISBN":["9789819543779","9789819543786"],"references-count":33,"URL":"https:\/\/doi.org\/10.1007\/978-981-95-4378-6_13","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,11,9]]},"assertion":[{"value":"9 November 2025","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ICONIP","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Neural Information Processing","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Okinawa","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":"20 November 2025","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"24 November 2025","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"32","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"iconip2025","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/iconip2025.apnns.org\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}