{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T17:30:04Z","timestamp":1777656604026,"version":"3.51.4"},"publisher-location":"Cham","reference-count":52,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783031198144","type":"print"},{"value":"9783031198151","type":"electronic"}],"license":[{"start":{"date-parts":[[2022,1,1]],"date-time":"2022-01-01T00:00:00Z","timestamp":1640995200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2022,1,1]],"date-time":"2022-01-01T00:00:00Z","timestamp":1640995200000},"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":[[2022]]},"DOI":"10.1007\/978-3-031-19815-1_19","type":"book-chapter","created":{"date-parts":[[2022,10,19]],"date-time":"2022-10-19T23:11:54Z","timestamp":1666221114000},"page":"322-338","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":41,"title":["Levenshtein OCR"],"prefix":"10.1007","author":[{"given":"Cheng","family":"Da","sequence":"first","affiliation":[]},{"given":"Peng","family":"Wang","sequence":"additional","affiliation":[]},{"given":"Cong","family":"Yao","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2022,10,20]]},"reference":[{"key":"19_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 - 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":"19_CR2","doi-asserted-by":"crossref","unstructured":"Baek, J., et al.: What is wrong with scene text recognition model comparisons? dataset and model analysis. In: ICCV, pp. 4714\u20134722 (2019)","DOI":"10.1109\/ICCV.2019.00481"},{"key":"19_CR3","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"213","DOI":"10.1007\/978-3-030-58452-8_13","volume-title":"Computer Vision \u2013 ECCV 2020","author":"N Carion","year":"2020","unstructured":"Carion, N., Massa, F., Synnaeve, G., Usunier, N., Kirillov, A., Zagoruyko, S.: End-to-end object detection with transformers. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12346, pp. 213\u2013229. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58452-8_13"},{"issue":"2","key":"19_CR4","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3440756","volume":"54","author":"X Chen","year":"2021","unstructured":"Chen, X., Jin, L., Zhu, Y., Luo, C., Wang, T.: Text recognition in the wild: a survey. ACM Comput. Surv. (CSUR) 54(2), 1\u201335 (2021)","journal-title":"ACM Comput. Surv. (CSUR)"},{"key":"19_CR5","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"104","DOI":"10.1007\/978-3-030-58577-8_7","volume-title":"Computer Vision \u2013 ECCV 2020","author":"Y-C Chen","year":"2020","unstructured":"Chen, Y.-C., et al.: UNITER: UNiversal Image-TExt representation learning. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12375, pp. 104\u2013120. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58577-8_7"},{"key":"19_CR6","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: CVPR, pp. 5086\u20135094 (2017)","DOI":"10.1109\/ICCV.2017.543"},{"key":"19_CR7","unstructured":"Dosovitskiy, A., et al.: An image is worth 16x16 words: transformers for image recognition at scale. In: ICLR (2021)"},{"key":"19_CR8","doi-asserted-by":"crossref","unstructured":"Fang, S., Xie, H., Wang, Y., Mao, Z., Zhang, Y.: Read like humans: autonomous, bidirectional and iterative language modeling for scene text recognition. In: CVPR, pp. 7098\u20137107 (2021)","DOI":"10.1109\/CVPR46437.2021.00702"},{"key":"19_CR9","unstructured":"Goodfellow, I.J., et al.: Generative adversarial nets. In: NeurIPS, pp. 2672\u20132680 (2014)"},{"key":"19_CR10","unstructured":"Gu, J., Wang, C., Zhao, J.: Levenshtein transformer. In: NeurIPS, pp. 11179\u201311189 (2019)"},{"key":"19_CR11","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":"19_CR12","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":"19_CR13","doi-asserted-by":"crossref","unstructured":"He, P., Huang, W., Qiao, Y., Loy, C.C., Tang, X.: Reading scene text in deep convolutional sequences. In: AAAI, pp. 3501\u20133508 (2016)","DOI":"10.1609\/aaai.v30i1.10465"},{"key":"19_CR14","doi-asserted-by":"crossref","unstructured":"He, Y., et al.: Visual semantics allow for textual reasoning better in scene text recognition. In: AAAI, pp. 888\u2013896 (2022)","DOI":"10.1609\/aaai.v36i1.19971"},{"key":"19_CR15","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":"19_CR16","unstructured":"Jaderberg, M., Simonyan, K., Vedaldi, A., Zisserman, A.: Synthetic data and artificial neural networks for natural scene text recognition. In: NIPS Deep Learning Workshop (2014)"},{"issue":"1","key":"19_CR17","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1007\/s11263-015-0823-z","volume":"116","author":"M Jaderberg","year":"2016","unstructured":"Jaderberg, M., Simonyan, K., Vedaldi, A., Zisserman, A.: Reading text in the wild with convolutional neural networks. Int. J. Comput. Vis. 116(1), 1\u201320 (2016)","journal-title":"Int. J. Comput. Vis."},{"key":"19_CR18","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":"19_CR19","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":"19_CR20","unstructured":"Kim, W., Son, B., Kim, I.: Vilt: vision-and-language transformer without convolution or region supervision. In: ICML, vol. 139, pp. 5583\u20135594 (2021)"},{"key":"19_CR21","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":"19_CR22","doi-asserted-by":"crossref","unstructured":"Lee, J., Park, S., Baek, J., Oh, S.J., Kim, S., Lee, H.: On recognizing texts of arbitrary shapes with 2d self-attention. In: CVPR Workshops, pp. 2326\u20132335 (2020)","DOI":"10.1109\/CVPRW50498.2020.00281"},{"key":"19_CR23","unstructured":"Li, M., et al.: Trocr: transformer-based optical character recognition with pre-trained models. CoRR abs\/2109.10282 (2021)"},{"issue":"2","key":"19_CR24","doi-asserted-by":"publisher","first-page":"532","DOI":"10.1109\/TPAMI.2019.2937086","volume":"43","author":"M Liao","year":"2021","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)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"19_CR25","doi-asserted-by":"crossref","unstructured":"Liao, M., et al.: Scene text recognition from two-dimensional perspective. In: AAAI, pp. 8714\u20138721 (2019)","DOI":"10.1609\/aaai.v33i01.33018714"},{"key":"19_CR26","doi-asserted-by":"crossref","unstructured":"Liu, H., et al.: Perceiving stroke-semantic context: hierarchical contrastive learning for robust scene text recognition. In: AAAI, pp. 1702\u20131710 (2022)","DOI":"10.1609\/aaai.v36i2.20062"},{"key":"19_CR27","doi-asserted-by":"crossref","unstructured":"Liu, Z., et al.: Swin transformer: hierarchical vision transformer using shifted windows. CoRR abs\/2103.14030 (2021)","DOI":"10.1109\/ICCV48922.2021.00986"},{"issue":"1","key":"19_CR28","doi-asserted-by":"publisher","first-page":"161","DOI":"10.1007\/s11263-020-01369-0","volume":"129","author":"S Long","year":"2021","unstructured":"Long, S., He, X., Yao, C.: Scene text detection and recognition: the deep learning era. IJCV 129(1), 161\u2013184 (2021)","journal-title":"IJCV"},{"key":"19_CR29","doi-asserted-by":"crossref","unstructured":"Lu, N., et al.: MASTER: multi-aspect non-local network for scene text recognition. PR 117, 107980 (2021)","DOI":"10.1016\/j.patcog.2021.107980"},{"key":"19_CR30","doi-asserted-by":"crossref","unstructured":"Mishra, A., Alahari, K., Jawahar, C.V.: Scene text recognition using higher order language priors. In: BMVC, pp. 1\u201311 (2012)","DOI":"10.5244\/C.26.127"},{"key":"19_CR31","doi-asserted-by":"crossref","unstructured":"Phan, T.Q., Shivakumara, P., Tian, S., Tan, C.L.: Recognizing text with perspective distortion in natural scenes. In: ICCV, pp. 569\u2013576 (2013)","DOI":"10.1109\/ICCV.2013.76"},{"key":"19_CR32","doi-asserted-by":"crossref","unstructured":"Qiao, Z., et al.: Pimnet: a parallel, iterative and mimicking network for scene text recognition. In: ACM MM, pp. 2046\u20132055 (2021)","DOI":"10.1145\/3474085.3475238"},{"key":"19_CR33","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. 13525\u201313534 (2020)","DOI":"10.1109\/CVPR42600.2020.01354"},{"issue":"18","key":"19_CR34","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."},{"key":"19_CR35","doi-asserted-by":"crossref","unstructured":"Sheng, F., Chen, Z., Xu, B.: NRTR: a no-recurrence sequence-to-sequence model for scene text recognition. In: ICDAR, pp. 781\u2013786 (2019)","DOI":"10.1109\/ICDAR.2019.00130"},{"issue":"11","key":"19_CR36","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. IEEE TPAMI 39(11), 2298\u20132304 (2017)","journal-title":"IEEE TPAMI"},{"issue":"9","key":"19_CR37","doi-asserted-by":"publisher","first-page":"2035","DOI":"10.1109\/TPAMI.2018.2848939","volume":"41","author":"B Shi","year":"2019","unstructured":"Shi, B., Yang, M., Wang, X., Lyu, P., Yao, C., Bai, X.: ASTER: an attentional scene text recognizer with flexible rectification. IEEE TPAMI 41(9), 2035\u20132048 (2019)","journal-title":"IEEE TPAMI"},{"key":"19_CR38","unstructured":"Su, W., et al.: VL-BERT: pre-training of generic visual-linguistic representations. In: ICLR (2020)"},{"key":"19_CR39","unstructured":"Vaswani, A., et al.: Attention is all you need. In: NeurIPS, pp. 5998\u20136008 (2017)"},{"key":"19_CR40","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, pp. 12120\u201312127 (2020)","DOI":"10.1609\/aaai.v34i07.6891"},{"key":"19_CR41","unstructured":"Wan, Z., Xie, F., Liu, Y., Bai, X., Yao, C.: 2d-ctc for scene text recognition. arXiv preprint arXiv:1907.09705 (2019)"},{"key":"19_CR42","doi-asserted-by":"crossref","unstructured":"Wan, Z., Zhang, J., Zhang, L., Luo, J., Yao, C.: On vocabulary reliance in scene text recognition. In: CVPR, pp. 11422\u201311431 (2020)","DOI":"10.1109\/CVPR42600.2020.01144"},{"key":"19_CR43","unstructured":"Wang, K., Babenko, B., Belongie, S.J.: End-to-end scene text recognition. In: ICCV, pp. 1457\u20131464 (2011)"},{"key":"19_CR44","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":"19_CR45","doi-asserted-by":"crossref","unstructured":"Wang, Y., Xie, H., Fang, S., Wang, J., Zhu, S., Zhang, Y.: From two to one: a new scene text recognizer with visual language modeling network. In: ICCV, pp. 1\u201310 (2021)","DOI":"10.1109\/ICCV48922.2021.01393"},{"key":"19_CR46","doi-asserted-by":"crossref","unstructured":"Yang, M., et al.: Symmetry-constrained rectification network for scene text recognition. In: ICCV, pp. 9146\u20139155 (2019)","DOI":"10.1109\/ICCV.2019.00924"},{"key":"19_CR47","doi-asserted-by":"crossref","unstructured":"Yu, D., et al.: Towards accurate scene text recognition with semantic reasoning networks. In: CVPR, pp. 12110\u201312119 (2020)","DOI":"10.1109\/CVPR42600.2020.01213"},{"key":"19_CR48","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":"19_CR49","unstructured":"Zeiler, M.D.: ADADELTA: an adaptive learning rate method. CoRR abs\/1212.5701 (2012)"},{"key":"19_CR50","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":"19_CR51","doi-asserted-by":"crossref","unstructured":"Zhang, X., Zhu, B., Yao, X., Sun, Q., Li, R., Yu, B.: Context-based contrastive learning for scene text recognition. In: AAAI, pp. 888\u2013896 (2022)","DOI":"10.1609\/aaai.v36i3.20245"},{"issue":"1","key":"19_CR52","doi-asserted-by":"publisher","first-page":"19","DOI":"10.1007\/s11704-015-4488-0","volume":"10","author":"Y Zhu","year":"2016","unstructured":"Zhu, Y., Yao, C., Bai, X.: Scene text detection and recognition: recent advances and future trends. Front. Comput. Sci. 10(1), 19\u201336 (2016)","journal-title":"Front. Comput. Sci."}],"container-title":["Lecture Notes in Computer Science","Computer Vision \u2013 ECCV 2022"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-19815-1_19","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,10,21]],"date-time":"2022-10-21T23:25:31Z","timestamp":1666394731000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-19815-1_19"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022]]},"ISBN":["9783031198144","9783031198151"],"references-count":52,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-19815-1_19","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022]]},"assertion":[{"value":"20 October 2022","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":"Tel Aviv","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Israel","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2022","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"23 October 2022","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"27 October 2022","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"17","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"eccv2022","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/eccv2022.ecva.net\/","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":"CMT","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"5804","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":"1645","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":"28% - 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":"3.21","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":"3.91","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":"Yes","order":9,"name":"external_reviewers_involved","label":"External Reviewers Involved","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}}]}}