{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,29]],"date-time":"2026-07-29T14:53:43Z","timestamp":1785336823315,"version":"3.55.0"},"publisher-location":"Cham","reference-count":37,"publisher":"Springer International Publishing","isbn-type":[{"value":"9783030861971","type":"print"},{"value":"9783030861988","type":"electronic"}],"license":[{"start":{"date-parts":[[2021,1,1]],"date-time":"2021-01-01T00:00:00Z","timestamp":1609459200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2021,1,1]],"date-time":"2021-01-01T00:00:00Z","timestamp":1609459200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2021]]},"DOI":"10.1007\/978-3-030-86198-8_14","type":"book-chapter","created":{"date-parts":[[2021,9,3]],"date-time":"2021-09-03T20:33:19Z","timestamp":1630701199000},"page":"182-197","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":15,"title":["Transfer Learning for Scene Text\u00a0Recognition in Indian Languages"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-3332-8355","authenticated-orcid":false,"given":"Sanjana","family":"Gunna","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0773-3480","authenticated-orcid":false,"given":"Rohit","family":"Saluja","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6767-7057","authenticated-orcid":false,"given":"C. V.","family":"Jawahar","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2021,9,4]]},"reference":[{"key":"14_CR1","doi-asserted-by":"crossref","unstructured":"Bu\u0161ta, M., Neumann, L., Matas, J.: Deep textspotter: an end-to-end trainable scene text localization and recognition framework. In: ICCV (2017)","DOI":"10.1109\/ICCV.2017.242"},{"key":"14_CR2","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"127","DOI":"10.1007\/978-3-030-21074-8_11","volume-title":"Computer Vision \u2013 ACCV 2018 Workshops","author":"M Bu\u0161ta","year":"2019","unstructured":"Bu\u0161ta, M., Patel, Y., Matas, J.: E2E-MLT - an unconstrained end-to-end method for multi-language scene text. In: Carneiro, G., You, S. (eds.) ACCV 2018. LNCS, vol. 11367, pp. 127\u2013143. Springer, Cham (2019). https:\/\/doi.org\/10.1007\/978-3-030-21074-8_11"},{"key":"14_CR3","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":"14_CR4","doi-asserted-by":"crossref","unstructured":"Huang, Z., Zhong, Z., Sun, L., Huo, Q.: Mask R-CNN with pyramid attention network for scene text detection. In: WACV, pp. 764\u2013772. IEEE (2019)","DOI":"10.1109\/WACV.2019.00086"},{"key":"14_CR5","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"440","DOI":"10.1007\/978-3-319-46604-0_32","volume-title":"Computer Vision \u2013 ECCV 2016 Workshops","author":"M Iwamura","year":"2016","unstructured":"Iwamura, M., Matsuda, T., Morimoto, N., Sato, H., Ikeda, Y., Kise, K.: Downtown Osaka scene text dataset. In: Hua, G., J\u00e9gou, H. (eds.) ECCV 2016, Part I. LNCS, vol. 9913, pp. 440\u2013455. Springer, Cham (2016). https:\/\/doi.org\/10.1007\/978-3-319-46604-0_32"},{"key":"14_CR6","unstructured":"Jaderberg, M., Simonyan, K., Vedaldi, A., Zisserman, A.: Synthetic data and artificial neural networks for natural scene text recognition. In: Workshop on Deep Learning, NIPS (2014)"},{"issue":"1","key":"14_CR7","doi-asserted-by":"publisher","first-page":"78","DOI":"10.4218\/etrij.11.1510.0029","volume":"33","author":"J Jung","year":"2011","unstructured":"Jung, J., Lee, S., Cho, M.S., Kim, J.H.: Touch TT: scene text extractor using touchscreen interface. ETRI J. 33(1), 78\u201388 (2011)","journal-title":"ETRI J."},{"key":"14_CR8","doi-asserted-by":"crossref","unstructured":"Karatzas, D., et al.: ICDAR 2015 competition on robust reading. In: 2015 ICDAR, pp. 1156\u20131160. IEEE (2015)","DOI":"10.1109\/ICDAR.2015.7333942"},{"key":"14_CR9","doi-asserted-by":"crossref","unstructured":"Lee, C.Y., Osindero, S.: Recursive recurrent nets with attention modeling for OCR in the wild. In: CVPR, pp. 2231\u20132239 (2016)","DOI":"10.1109\/CVPR.2016.245"},{"key":"14_CR10","doi-asserted-by":"crossref","unstructured":"Liao, M., Shi, B., Bai, X., Wang, X., Liu, W.: Textboxes: a fast text detector with a single deep neural network. In: AAAI, pp. 4161\u20134167 (2017)","DOI":"10.1609\/aaai.v31i1.11196"},{"key":"14_CR11","doi-asserted-by":"crossref","unstructured":"Liu, W., Chen, C., Wong, K.Y.K., Su, Z., Han, J.: STAR-Net: a spatial attention residue network for scene text recognition. In: BMVC, vol. 2 (2016)","DOI":"10.5244\/C.30.43"},{"key":"14_CR12","doi-asserted-by":"crossref","unstructured":"Liu, X., Liang, D., Yan, S., Chen, D., Qiao, Y., Yan, J.: FOTS: fast oriented text spotting with a unified network. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 5676\u20135685 (2018)","DOI":"10.1109\/CVPR.2018.00595"},{"key":"14_CR13","doi-asserted-by":"crossref","unstructured":"Mathew, M., Jain, M., Jawahar, C.: Benchmarking scene text recognition in Devanagari, Telugu and Malayalam. In: ICDAR, vol. 7, pp. 42\u201346. IEEE (2017)","DOI":"10.1109\/ICDAR.2017.364"},{"key":"14_CR14","doi-asserted-by":"crossref","unstructured":"Nayef, N., et al.: ICDAR2019 robust reading challenge on multi-lingual scene text detection and recognition-RRC-MLT-2019. In: 2019 International Conference on Document Analysis and Recognition (ICDAR), pp. 1582\u20131587. IEEE (2019)","DOI":"10.1109\/ICDAR.2019.00254"},{"key":"14_CR15","doi-asserted-by":"crossref","unstructured":"Nayef, N., et al.: Robust reading challenge on multi-lingual scene text detection and script identification - RRC-MLT. In: 14th ICDAR, vol. 1, pp. 1454\u20131459. IEEE (2017)","DOI":"10.1109\/ICDAR.2017.237"},{"key":"14_CR16","doi-asserted-by":"crossref","unstructured":"Reddy, S., Mathew, M., Gomez, L., Rusinol, M., Karatzas, D., Jawahar, C.: RoadText-1K: text detection & recognition dataset for driving videos. In: 2020 IEEE International Conference on Robotics and Automation (ICRA), pp. 11074\u201311080. IEEE (2020)","DOI":"10.1109\/ICRA40945.2020.9196577"},{"key":"14_CR17","unstructured":"Ren, S., He, K., Girshick, R., Sun, J.: Faster R-CNN: towards real-time object detection with region proposal networks. arXiv preprint arXiv:1506.01497 (2015)"},{"issue":"1","key":"14_CR18","doi-asserted-by":"publisher","first-page":"263","DOI":"10.1109\/TITS.2017.2750080","volume":"19","author":"E Romera","year":"2017","unstructured":"Romera, E., Alvarez, J.M., Bergasa, L.M., Arroyo, R.: ERFnet: efficient residual factorized ConvNet for real-time semantic segmentation. IEEE Trans. Intell. Transp. Syst. 19(1), 263\u2013272 (2017)","journal-title":"IEEE Trans. Intell. Transp. Syst."},{"issue":"3","key":"14_CR19","doi-asserted-by":"publisher","first-page":"211","DOI":"10.1007\/s11263-015-0816-y","volume":"115","author":"O Russakovsky","year":"2015","unstructured":"Russakovsky, O., et al.: Imagenet large scale visual recognition challenge. Int. J. Comput. Vis. 115(3), 211\u2013252 (2015)","journal-title":"Int. J. Comput. Vis."},{"key":"14_CR20","doi-asserted-by":"crossref","unstructured":"Saluja, R., Maheshwari, A., Ramakrishnan, G., Chaudhuri, P., Carman, M.: OCR On-the-Go: robust end-to-end systems for reading license plates and street signs. In: 15th IAPR International Conference on Document Analysis and Recognition (ICDAR), pp. 154\u2013159. IEEE (2019)","DOI":"10.1109\/ICDAR.2019.00033"},{"issue":"11","key":"14_CR21","doi-asserted-by":"publisher","first-page":"2298","DOI":"10.1109\/TPAMI.2016.2646371","volume":"39","author":"B Shi","year":"2016","unstructured":"Shi, B., Bai, X., Yao, C.: An end-to-end trainable neural network for image-based sequence recognition and its application to scene text recognition. IEEE Trans. Pattern Anal. Mach. Intell. 39(11), 2298\u20132304 (2016)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"14_CR22","doi-asserted-by":"publisher","first-page":"2035","DOI":"10.1109\/TPAMI.2018.2848939","volume":"41","author":"B Shi","year":"2018","unstructured":"Shi, B., Yang, M., Wang, X., Lyu, P., Yao, C., Bai, X.: ASTER: an attentional scene text recognizer with flexible rectification. IEEE Trans. Pattern Anal. Mach. Intell. 41, 2035\u20132048 (2018)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"14_CR23","doi-asserted-by":"crossref","unstructured":"Shi, B., et al.: ICDAR2017 competition on reading Chinese text in the wild (RCTW-17). In: 14th ICDAR, vol. 1, pp. 1429\u20131434. IEEE (2017)","DOI":"10.1109\/ICDAR.2017.233"},{"key":"14_CR24","unstructured":"Simonyan, K., Zisserman, A.: Very deep convolutional networks for large-scale image recognition. arXiv preprint arXiv:1409.1556 (2014)"},{"key":"14_CR25","doi-asserted-by":"crossref","unstructured":"Sun, Y., et al.: ICDAR 2019 competition on large-scale street view text with partial labeling - RRC-LSVT. In: 2019 International Conference on Document Analysis and Recognition (ICDAR), pp. 1557\u20131562. IEEE (2019)","DOI":"10.1109\/ICDAR.2019.00250"},{"key":"14_CR26","doi-asserted-by":"crossref","unstructured":"Szegedy, C., Ioffe, S., Vanhoucke, V., Alemi, A.: Inception-v4, Inception-Resnet and the impact of residual connections on learning. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 31 (2017)","DOI":"10.1609\/aaai.v31i1.11231"},{"key":"14_CR27","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"56","DOI":"10.1007\/978-3-319-46484-8_4","volume-title":"Computer Vision \u2013 ECCV 2016","author":"Z Tian","year":"2016","unstructured":"Tian, Z., Huang, W., He, T., He, P., Qiao, Yu.: Detecting text in natural image with connectionist text proposal network. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) ECCV 2016, Part VIII. LNCS, vol. 9912, pp. 56\u201372. Springer, Cham (2016). https:\/\/doi.org\/10.1007\/978-3-319-46484-8_4"},{"key":"14_CR28","doi-asserted-by":"crossref","unstructured":"Tounsi, M., Moalla, I., Alimi, A.M., Lebouregois, F.: Arabic characters recognition in natural scenes using sparse coding for feature representations. In: 13th ICDAR, pp. 1036\u20131040. IEEE (2015)","DOI":"10.1109\/ICDAR.2015.7333919"},{"key":"14_CR29","doi-asserted-by":"crossref","unstructured":"Vinitha, V., Jawahar, C.: Error detection in indic OCRs. In: 2016 12th IAPR Workshop on Document Analysis Systems (DAS), pp. 180\u2013185. IEEE (2016)","DOI":"10.1109\/DAS.2016.31"},{"key":"14_CR30","unstructured":"Wang, K., Babenko, B., Belongie, S.: End-to-end scene text recognition. In: ICCV, pp. 1457\u20131464. IEEE (2011)"},{"key":"14_CR31","doi-asserted-by":"crossref","unstructured":"Yousfi, S., Berrani, S.A., Garcia, C.: ALIF: a dataset for Arabic embedded text recognition in TV broadcast. In: 2015 13th International Conference on Document Analysis and Recognition (ICDAR), pp. 1221\u20131225. IEEE (2015)","DOI":"10.1109\/ICDAR.2015.7333958"},{"key":"14_CR32","unstructured":"Yu, F., Xian, W., Chen, Y., Liu, F., Liao, M., Madhavan, V., Darrell, T.: BDD100K: a diverse driving video database with scalable annotation tooling. arXiv preprint arXiv:1805.04687, vol. 2, no. 5, p. 6 (2018)"},{"issue":"3","key":"14_CR33","doi-asserted-by":"publisher","first-page":"509","DOI":"10.1007\/s11390-019-1923-y","volume":"34","author":"T Yuan","year":"2019","unstructured":"Yuan, T., Zhu, Z., Xu, K., Li, C., Mu, T., Hu, S.: A large Chinese text dataset in the wild. J. Comput. Sci. Technol. 34(3), 509\u2013521 (2019)","journal-title":"J. Comput. Sci. Technol."},{"key":"14_CR34","unstructured":"Zeiler, M.: ADADELTA: an adaptive learning rate method, p. 1212 (December 2012)"},{"key":"14_CR35","doi-asserted-by":"crossref","unstructured":"Zhang, R., et al.: ICDAR 2019 robust reading challenge on reading Chinese text on signboard. In: 2019 International Conference on Document Analysis and Recognition (ICDAR), pp. 1577\u20131581. IEEE (2019)","DOI":"10.1109\/ICDAR.2019.00253"},{"key":"14_CR36","unstructured":"Zhang, Y., Gueguen, L., Zharkov, I., Zhang, P., Seifert, K., Kadlec, B.: Uber-text: a large-scale dataset for optical character recognition from street-level imagery. In: SUNw: Scene Understanding Workshop-CVPR, vol. 2017 (2017)"},{"key":"14_CR37","doi-asserted-by":"crossref","unstructured":"Zhou, X., et al.: East: an efficient and accurate scene text detector. In: CVPR, pp. 2642\u20132651 (2017)","DOI":"10.1109\/CVPR.2017.283"}],"container-title":["Lecture Notes in Computer Science","Document Analysis and Recognition \u2013 ICDAR 2021 Workshops"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-030-86198-8_14","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,9,2]],"date-time":"2025-09-02T22:14:21Z","timestamp":1756851261000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-030-86198-8_14"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021]]},"ISBN":["9783030861971","9783030861988"],"references-count":37,"URL":"https:\/\/doi.org\/10.1007\/978-3-030-86198-8_14","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2021]]},"assertion":[{"value":"4 September 2021","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ICDAR","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Document Analysis and Recognition","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Lausanne","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Switzerland","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2021","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"5 September 2021","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"10 September 2021","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"16","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"icdar2021","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"http:\/\/iapr.org\/icdar2021","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Double-blind","order":1,"name":"type","label":"Type","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"EasyChair","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"340","order":3,"name":"number_of_submissions_sent_for_review","label":"Number of Submissions Sent for Review","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"182","order":4,"name":"number_of_full_papers_accepted","label":"Number of Full Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"0","order":5,"name":"number_of_short_papers_accepted","label":"Number of Short Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"54% - The value is computed by the equation \"Number of Full Papers Accepted \/ Number of Submissions Sent for Review * 100\" and then rounded to a whole number.","order":6,"name":"acceptance_rate_of_full_papers","label":"Acceptance Rate of Full Papers","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"2.9","order":7,"name":"average_number_of_reviews_per_paper","label":"Average Number of Reviews per Paper","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"4.9","order":8,"name":"average_number_of_papers_per_reviewer","label":"Average Number of Papers per Reviewer","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"No","order":9,"name":"external_reviewers_involved","label":"External Reviewers Involved","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"Additionally, 13 competition reports are included.","order":10,"name":"additional_info_on_review_process","label":"Additional Info on Review Process","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}}]}}