{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,9,2]],"date-time":"2025-09-02T22:40:14Z","timestamp":1756852814705,"version":"3.44.0"},"publisher-location":"Cham","reference-count":45,"publisher":"Springer International Publishing","isbn-type":[{"type":"print","value":"9783030863364"},{"type":"electronic","value":"9783030863371"}],"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.springernature.com\/gp\/researchers\/text-and-data-mining"},{"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.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2021]]},"DOI":"10.1007\/978-3-030-86337-1_10","type":"book-chapter","created":{"date-parts":[[2021,9,3]],"date-time":"2021-09-03T20:48:12Z","timestamp":1630702092000},"page":"140-155","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["A Multi-level Progressive Rectification Mechanism for Irregular Scene Text Recognition"],"prefix":"10.1007","author":[{"given":"Qianying","family":"Liao","sequence":"first","affiliation":[]},{"given":"Qingxiang","family":"Lin","sequence":"additional","affiliation":[]},{"given":"Lianwen","family":"Jin","sequence":"additional","affiliation":[]},{"given":"Canjie","family":"Luo","sequence":"additional","affiliation":[]},{"given":"Jiaxin","family":"Zhang","sequence":"additional","affiliation":[]},{"given":"Dezhi","family":"Peng","sequence":"additional","affiliation":[]},{"given":"Tianwei","family":"Wang","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2021,9,2]]},"reference":[{"issue":"6","key":"10_CR1","doi-asserted-by":"publisher","first-page":"567","DOI":"10.1109\/34.24792","volume":"11","author":"FL Bookstein","year":"1989","unstructured":"Bookstein, F.L.: Principal warps: thin-plate splines and the decomposition of deformations. TPAMI 11(6), 567\u2013585 (1989)","journal-title":"TPAMI"},{"key":"10_CR2","doi-asserted-by":"crossref","unstructured":"Cheng, Z., Bai, F., Xu, Y., Zheng, G., Pu, S., Zhou, S.: Focusing attention: towards accurate text recognition in natural images. In: ICCV, pp. 5086\u20135094 (2017)","DOI":"10.1109\/ICCV.2017.543"},{"key":"10_CR3","doi-asserted-by":"crossref","unstructured":"Cheng, Z., Xu, Y., Bai, F., Niu, Y., Pu, S., Zhou, S.: AON: towards arbitrarily-oriented text recognition. In: CVPR, pp. 5571\u20135579 (2018)","DOI":"10.1109\/CVPR.2018.00584"},{"key":"10_CR4","doi-asserted-by":"crossref","unstructured":"Cho, K., et al.: Learning phrase representations using RNN encoder-decoder for statistical machine translation. In: Proceedings of EMNLPS, pp. 1724\u20131734 (2014)","DOI":"10.3115\/v1\/D14-1179"},{"issue":"5","key":"10_CR5","doi-asserted-by":"publisher","first-page":"855","DOI":"10.1109\/TPAMI.2008.137","volume":"31","author":"A Graves","year":"2009","unstructured":"Graves, A., Liwicki, M., Fern\u00e1ndez, S., Bertolami, R., Bunke, H., Schmidhuber, J.: A novel connectionist system for unconstrained handwriting recognition. TPAMI 31(5), 855\u2013868 (2009)","journal-title":"TPAMI"},{"key":"10_CR6","doi-asserted-by":"crossref","unstructured":"Graves, A., Fern\u00e1ndez, S., Gomez, F., Schmidhuber, J.: Connectionist temporal classification: labelling unsegmented sequence data with recurrent neural networks. In: ICML, pp. 369\u2013376 (2006)","DOI":"10.1145\/1143844.1143891"},{"key":"10_CR7","doi-asserted-by":"crossref","unstructured":"Gupta, A., Vedaldi, A., Zisserman, A.: Synthetic data for text localisation in natural images. In: CVPR, pp. 2315\u20132324 (2016)","DOI":"10.1109\/CVPR.2016.254"},{"key":"10_CR8","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: CVPR, pp. 770\u2013778 (2016)","DOI":"10.1109\/CVPR.2016.90"},{"key":"10_CR9","doi-asserted-by":"crossref","unstructured":"Hu, W., Cai, X., Hou, J., Yi, S., Lin, Z.: GTC: guided training of CTC towards efficient and accurate scene text recognition. In: AAAI, pp. 11005\u201311012 (2020)","DOI":"10.1609\/aaai.v34i07.6735"},{"key":"10_CR10","doi-asserted-by":"crossref","unstructured":"Huang, Y., Luo, C., Jin, L., Lin, Q., Zhou, W.: Attention after attention: reading text in the wild with cross attention. In: ICDAR, pp. 274\u2013280 (2019)","DOI":"10.1109\/ICDAR.2019.00052"},{"key":"10_CR11","unstructured":"Jaderberg, M., Simonyan, K., Vedaldi, A., Zisserman, A.: Synthetic data and artificial neural networks for natural scene text recognition. arXiv preprint arXiv:1406.2227 (2014)"},{"key":"10_CR12","unstructured":"Jaderberg, M., Simonyan, K., Zisserman, A., et al.: Spatial transformer networks. In: NeurIPS, vol. 28, pp. 2017\u20132025 (2015)"},{"key":"10_CR13","doi-asserted-by":"crossref","unstructured":"Karatzas, D., et al.: ICDAR 2015 competition on robust reading. In: ICDAR, pp. 1156\u20131160 (2015)","DOI":"10.1109\/ICDAR.2015.7333942"},{"key":"10_CR14","doi-asserted-by":"crossref","unstructured":"Karatzas, D., et al.: ICDAR 2013 robust reading competition. In: ICDAR, pp. 1484\u20131493 (2013)","DOI":"10.1109\/ICDAR.2013.221"},{"key":"10_CR15","doi-asserted-by":"crossref","unstructured":"Lee, C., 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":"10_CR16","doi-asserted-by":"crossref","unstructured":"Li, H., Wang, P., Shen, C., Zhang, G.: Show, attend and read: A simple and strong baseline for irregular text recognition. In: AAAI, vol. 33, 8610\u20138617 (2019)","DOI":"10.1609\/aaai.v33i01.33018610"},{"key":"10_CR17","doi-asserted-by":"publisher","unstructured":"Liao, M., Lyu, P., He, M., Yao, C., Wu, W., Bai, X.: Mask TextSpotter: an end-to-end trainable neural network for spotting text with arbitrary shapes. IEEE Trans. Pattern Anal. Mach. Intell. 43(2), 532\u2013548 (2021). https:\/\/doi.org\/10.1109\/TPAMI.2019.2937086","DOI":"10.1109\/TPAMI.2019.2937086"},{"key":"10_CR18","doi-asserted-by":"crossref","unstructured":"Liao, M., et al.: Scene text recognition from two-dimensional perspective. In: AAAI, vol. 33, pp. 8714\u20138721 (2019)","DOI":"10.1609\/aaai.v33i01.33018714"},{"key":"10_CR19","doi-asserted-by":"publisher","first-page":"107692","DOI":"10.1016\/j.patcog.2020.107692","volume":"111","author":"Q Lin","year":"2021","unstructured":"Lin, Q., Luo, C., Jin, L., Lai, S.: STAN: A sequential transformation attention-based network for scene text recognition. Pattern Recogn. 111, 107692 (2021)","journal-title":"Pattern Recogn."},{"key":"10_CR20","doi-asserted-by":"crossref","unstructured":"Litman, R., Anschel, O., Tsiper, S., Litman, R., Mazor, S., Manmatha, R.: SCATTER: selective context attentional scene text recognizer. In: CVPR, pp. 11962\u201311972 (2020)","DOI":"10.1109\/CVPR42600.2020.01198"},{"key":"10_CR21","doi-asserted-by":"crossref","unstructured":"Liu, W., Chen, C., Wong, K.Y.K.: Char-Net: a character-aware neural network for distorted scene text recognition. In: AAAI, vol. 1, p. 4 (2018)","DOI":"10.1609\/aaai.v32i1.12246"},{"key":"10_CR22","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, p. 7 (2016)"},{"key":"10_CR23","doi-asserted-by":"crossref","unstructured":"Liu, Y., Wang, Z., Jin, H., Wassell, I.: Synthetically supervised feature learning for scene text recognition. In: ECCV, pp. 435\u2013451 (2018)","DOI":"10.1007\/978-3-030-01228-1_27"},{"key":"10_CR24","doi-asserted-by":"publisher","first-page":"109","DOI":"10.1016\/j.patcog.2019.01.020","volume":"90","author":"C Luo","year":"2019","unstructured":"Luo, C., Jin, L., Sun, Z.: MORAN: a multi-object rectified attention network for scene text recognition. Pattern Recogn. 90, 109\u2013118 (2019)","journal-title":"Pattern Recogn."},{"key":"10_CR25","doi-asserted-by":"publisher","unstructured":"Luo, C., Lin, Q., Liu, Y., Jin, L., Shen, C.: Separating content from style using adversarial learning for recognizing text in the wild. Int. J. Comput. Vis. 129, 960\u2013976 (2021). https:\/\/doi.org\/10.1007\/s11263-020-01411-1","DOI":"10.1007\/s11263-020-01411-1"},{"key":"10_CR26","doi-asserted-by":"crossref","unstructured":"Mishra, A., Srivastava, V.: Cognition based selection and categorization of maintenance engineer (agent) using artificial neural net and data mining methods. In: 2012 CSI Sixth International Conference on Software Engineering, pp. 1\u201311 (2012)","DOI":"10.1109\/CONSEG.2012.6349509"},{"key":"10_CR27","doi-asserted-by":"crossref","unstructured":"Qiao, Z., Zhou, Y., Yang, D., Zhou, Y., Wang, W.: SEED: semantics enhanced encoder-decoder framework for scene text recognition. In: CVPR, pp. 13528\u201313537 (2020)","DOI":"10.1109\/CVPR42600.2020.01354"},{"key":"10_CR28","doi-asserted-by":"crossref","unstructured":"Quy Phan, T., Shivakumara, P., Tian, S., Lim Tan, C.: Recognizing text with perspective distortion in natural scenes. In: ICCV, pp. 569\u2013576 (2013)","DOI":"10.1109\/ICCV.2013.76"},{"issue":"18","key":"10_CR29","doi-asserted-by":"publisher","first-page":"8027","DOI":"10.1016\/j.eswa.2014.07.008","volume":"41","author":"A Risnumawan","year":"2014","unstructured":"Risnumawan, A., Shivakumara, P., Chan, C.S., Tan, C.L.: A robust arbitrary text detection system for natural scene images. Expert Syst. Appl. 41(18), 8027\u20138048 (2014)","journal-title":"Expert Syst. Appl."},{"issue":"11","key":"10_CR30","doi-asserted-by":"publisher","first-page":"2298","DOI":"10.1109\/TPAMI.2016.2646371","volume":"39","author":"B Shi","year":"2017","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. TPAMI 39(11), 2298\u20132304 (2017)","journal-title":"TPAMI"},{"key":"10_CR31","doi-asserted-by":"crossref","unstructured":"Shi, B., Wang, X., Lyu, P., Yao, C., Bai, X.: Robust scene text recognition with automatic rectification. In: CVPR, pp. 4168\u20134176 (2016)","DOI":"10.1109\/CVPR.2016.452"},{"issue":"9","key":"10_CR32","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. TPAMI 41(9), 2035\u20132048 (2018)","journal-title":"TPAMI"},{"key":"10_CR33","doi-asserted-by":"crossref","unstructured":"Wan, Z., He, M., Chen, H., Bai, X., Yao, C.: TextScanner: reading characters in order for robust scene text recognition. In: AAAI, vol. 34, pp. 12120\u201312127 (2020)","DOI":"10.1609\/aaai.v34i07.6891"},{"key":"10_CR34","unstructured":"Wan, Z., Xie, F., Liu, Y., Bai, X., Yao, C.: 2D-CTC for scene text recognition. arXiv preprint arXiv:1907.09705 (2019)"},{"key":"10_CR35","unstructured":"Wang, K., Babenko, B., Belongie, S.: End-to-end scene text recognition. In: ICCV, pp. 1457\u20131464 (2011)"},{"key":"10_CR36","doi-asserted-by":"crossref","unstructured":"Wang, T., et al.: Decoupled attention network for text recognition. In: AAAI, pp. 12216\u201312224 (2020)","DOI":"10.1609\/aaai.v34i07.6903"},{"key":"10_CR37","doi-asserted-by":"crossref","unstructured":"Xie, Z., Huang, Y., Zhu, Y., Jin, L., Liu, Y., Xie, L.: Aggregation cross-entropy for sequence recognition. In: CVPR, pp. 6538\u20136547 (2019)","DOI":"10.1109\/CVPR.2019.00670"},{"key":"10_CR38","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"158","DOI":"10.1007\/978-3-030-58555-6_10","volume-title":"Computer Vision \u2013 ECCV 2020","author":"Y Mou","year":"2020","unstructured":"Mou, Y., et al.: PlugNet: degradation aware scene text recognition supervised by a pluggable super-resolution unit. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12360, pp. 158\u2013174. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58555-6_10"},{"key":"10_CR39","doi-asserted-by":"crossref","unstructured":"Yang, M., et al.: Symmetry-constrained rectification network for scene text recognition. In: ICCV, pp. 9147\u20139156 (2019)","DOI":"10.1109\/ICCV.2019.00924"},{"key":"10_CR40","doi-asserted-by":"crossref","unstructured":"Yu, D., et al.: Towards accurate scene text recognition with semantic reasoning networks. In: CVPR, pp. 12113\u201312122 (2020)","DOI":"10.1109\/CVPR42600.2020.01213"},{"key":"10_CR41","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"135","DOI":"10.1007\/978-3-030-58529-7_9","volume-title":"Computer Vision \u2013 ECCV 2020","author":"X Yue","year":"2020","unstructured":"Yue, X., Kuang, Z., Lin, C., Sun, H., Zhang, W.: RobustScanner: dynamically enhancing positional clues for robust text recognition. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12364, pp. 135\u2013151. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58529-7_9"},{"key":"10_CR42","unstructured":"Zeiler, M.D.: ADADELTA: an adaptive learning rate method. arXiv preprint arXiv:1212.5701 (2012)"},{"key":"10_CR43","doi-asserted-by":"crossref","unstructured":"Zhan, F., Lu, S.: ESIR: end-to-end scene text recognition via iterative image rectification. In: CVPR, pp. 2059\u20132068 (2019)","DOI":"10.1109\/CVPR.2019.00216"},{"key":"10_CR44","doi-asserted-by":"crossref","unstructured":"Zhang, H., Yao, Q., Yang, M., Xu, Y., Bai, X.: Efficient backbone search for scene text recognition. In: ECCV (2020)","DOI":"10.1007\/978-3-030-58586-0_44"},{"key":"10_CR45","doi-asserted-by":"publisher","first-page":"196","DOI":"10.1016\/j.patcog.2017.06.017","volume":"71","author":"J Zhang","year":"2017","unstructured":"Zhang, J., et al.: Watch, attend and parse: an end-to-end neural network based approach to handwritten mathematical expression recognition. Pattern Recogn. 71, 196\u2013206 (2017)","journal-title":"Pattern Recogn."}],"container-title":["Lecture Notes in Computer Science","Document Analysis and Recognition \u2013 ICDAR 2021"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-030-86337-1_10","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,9,2]],"date-time":"2025-09-02T22:04:12Z","timestamp":1756850652000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-030-86337-1_10"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021]]},"ISBN":["9783030863364","9783030863371"],"references-count":45,"URL":"https:\/\/doi.org\/10.1007\/978-3-030-86337-1_10","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2021]]},"assertion":[{"value":"2 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)"}}]}}