{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,23]],"date-time":"2026-03-23T13:09:49Z","timestamp":1774271389788,"version":"3.50.1"},"publisher-location":"Cham","reference-count":45,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783031250682","type":"print"},{"value":"9783031250699","type":"electronic"}],"license":[{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"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":[[2023]]},"DOI":"10.1007\/978-3-031-25069-9_18","type":"book-chapter","created":{"date-parts":[[2023,2,14]],"date-time":"2023-02-14T00:15:46Z","timestamp":1676333746000},"page":"263-279","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":9,"title":["On Calibration of\u00a0Scene-Text Recognition Models"],"prefix":"10.1007","author":[{"given":"Ron","family":"Slossberg","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Oron","family":"Anschel","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Amir","family":"Markovitz","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ron","family":"Litman","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Aviad","family":"Aberdam","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Shahar","family":"Tsiper","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Shai","family":"Mazor","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jon","family":"Wu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"R.","family":"Manmatha","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2023,2,14]]},"reference":[{"key":"18_CR1","doi-asserted-by":"crossref","unstructured":"Baek, J., et al.: What is wrong with scene text recognition model comparisons? dataset and model analysis. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 4715\u20134723 (2019)","DOI":"10.1109\/ICCV.2019.00481"},{"key":"18_CR2","unstructured":"Bahdanau, D., Cho, K., Bengio, Y.: Neural machine translation by jointly learning to align and translate. In: 3rd International Conference on Learning Representations, ICLR 2015 (2015)"},{"key":"18_CR3","unstructured":"Bartz, C., Bethge, J., Yang, H., Meinel, C.: Kiss: Keeping it simple for scene text recognition (2019)"},{"key":"18_CR4","doi-asserted-by":"crossref","unstructured":"Borisyuk, F., Gordo, A., Sivakumar, V.: Rosetta: large scale system for text detection and recognition in images. In: Proceedings of the 24th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining, pp. 71\u201379 (2018)","DOI":"10.1145\/3219819.3219861"},{"issue":"1","key":"18_CR5","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1175\/1520-0493(1950)078<0001:VOFEIT>2.0.CO;2","volume":"78","author":"GW Brier","year":"1950","unstructured":"Brier, G.W.: Verification of forecasts expressed in terms of probability. Mon. Weather Rev. 78(1), 1\u20133 (1950)","journal-title":"Mon. Weather Rev."},{"key":"18_CR6","doi-asserted-by":"publisher","unstructured":"Cho, K., et al.: Learning phrase representations using RNN encoder-decoder for statistical machine translation. In: Proceedings of the 2014 Conference on Empirical Methods in Natural Language Processing (EMNLP), pp. 1724\u20131734. Association for Computational Linguistics, Doha, Qatar (2014). https:\/\/doi.org\/10.3115\/v1\/D14-1179. https:\/\/www.aclweb.org\/anthology\/D14-1179","DOI":"10.3115\/v1\/D14-1179"},{"issue":"1\u20132","key":"18_CR7","first-page":"12","volume":"32","author":"MH DeGroot","year":"1983","unstructured":"DeGroot, M.H., Fienberg, S.E.: The comparison and evaluation of forecasters. J. Roy. Statist. Soc.: Ser. D (The Statistician) 32(1\u20132), 12\u201322 (1983)","journal-title":"J. Roy. Statist. Soc.: Ser. D (The Statistician)"},{"key":"18_CR8","doi-asserted-by":"crossref","unstructured":"Desai, S., Durrett, G.: Calibration of pre-trained transformers. In: Proceedings of the Conference on Empirical Methods in Natural Language Processing (EMNLP) (2020)","DOI":"10.18653\/v1\/2020.emnlp-main.21"},{"key":"18_CR9","doi-asserted-by":"publisher","unstructured":"Devlin, J., Chang, M.W., Lee, K., Toutanova, K.: BERT: pre-training of deep bidirectional transformers for language understanding. In: Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers), pp. 4171\u20134186. Association for Computational Linguistics, Minneapolis, Minnesota (2019). https:\/\/doi.org\/10.18653\/v1\/N19-1423. https:\/\/www.aclweb.org\/anthology\/N19-1423","DOI":"10.18653\/v1\/N19-1423"},{"key":"18_CR10","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: Proceedings of the 23rd international conference on Machine learning, pp. 369\u2013376. ACM (2006)","DOI":"10.1145\/1143844.1143891"},{"key":"18_CR11","doi-asserted-by":"crossref","unstructured":"Graves, A., Mohamed, A.R., Hinton, G.: Speech recognition with deep recurrent neural networks. In: 2013 IEEE International Conference on Acoustics, Speech and Signal Processing, pp. 6645\u20136649. IEEE (2013)","DOI":"10.1109\/ICASSP.2013.6638947"},{"key":"18_CR12","doi-asserted-by":"crossref","unstructured":"Guo, C., Pleiss, G., Sun, Y., Weinberger, K.Q.: On calibration of modern neural networks. In: Proceedings of the 34th International Conference on Machine Learning - Volume 70, pp. 1321\u20131330. ICML2017, JMLR.org (2017)","DOI":"10.1109\/WACV.2018.00149"},{"key":"18_CR13","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":"18_CR14","unstructured":"Hendrycks, D., Gimpel, K.: A baseline for detecting misclassified and out-of-distribution examples in neural networks (2017)"},{"key":"18_CR15","unstructured":"Jaderberg, M., Simonyan, K., Zisserman, A., et al.: Spatial transformer networks. In: Advances in neural information processing systems, pp. 2017\u20132025 (2015)"},{"key":"18_CR16","doi-asserted-by":"crossref","unstructured":"Ji, B., Jung, H., Yoon, J., Kim, K., et al.: Bin-wise temperature scaling (bts): Improvement in confidence calibration performance through simple scaling techniques. In: 2019 IEEE\/CVF International Conference on Computer Vision Workshop (ICCVW), pp. 4190\u20134196. IEEE (2019)","DOI":"10.1109\/ICCVW.2019.00515"},{"key":"18_CR17","doi-asserted-by":"crossref","unstructured":"Karatzas, D., et al.: 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"},{"key":"18_CR18","doi-asserted-by":"crossref","unstructured":"Karatzas, D., et al.: ICDAR 2013 robust reading competition. In: 2013 12th International Conference on Document Analysis and Recognition, pp. 1484\u20131493. IEEE (2013)","DOI":"10.1109\/ICDAR.2013.221"},{"key":"18_CR19","unstructured":"Kuleshov, V., Liang, P.S.: Calibrated structured prediction. In: Advances in Neural Information Processing Systems, pp. 3474\u20133482 (2015)"},{"key":"18_CR20","unstructured":"Kumar, A., Sarawagi, S.: Calibration of encoder decoder models for neural machine translation. arXiv preprint arXiv:1903.00802 (2019)"},{"key":"18_CR21","unstructured":"Lakshminarayanan, B., Pritzel, A., Blundell, C.: Simple and scalable predictive uncertainty estimation using deep ensembles. In: Advances in Neural Information Processing Systems, pp. 6402\u20136413 (2017)"},{"key":"18_CR22","unstructured":"Leathart, T., Polaczuk, M.: Temporal probability calibration. arXiv preprint arXiv:2002.02644 (2020)"},{"key":"18_CR23","doi-asserted-by":"crossref","unstructured":"Lee, C.Y., Osindero, S.: Recursive recurrent nets with attention modeling for OCR in the wild. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 2231\u20132239 (2016)","DOI":"10.1109\/CVPR.2016.245"},{"key":"18_CR24","unstructured":"Levenshtein, V.I.: Binary codes capable of correcting deletions, insertions, and reversals. In: Soviet physics doklady, vol. 10, pp. 707\u2013710 (1966)"},{"key":"18_CR25","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: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR) (2020)","DOI":"10.1109\/CVPR42600.2020.01198"},{"issue":"1\u20133","key":"18_CR26","doi-asserted-by":"publisher","first-page":"503","DOI":"10.1007\/BF01589116","volume":"45","author":"DC Liu","year":"1989","unstructured":"Liu, D.C., Nocedal, J.: On the limited memory BFGS method for large scale optimization. Math. Program. 45(1\u20133), 503\u2013528 (1989)","journal-title":"Math. Program."},{"key":"18_CR27","doi-asserted-by":"crossref","unstructured":"Liu, W., Chen, C., Wong, K., Su, Z., Han, J.: Star-Net: a spatial attention residue network for scene text recognition. In: BMVC (2016)","DOI":"10.5244\/C.30.43"},{"key":"18_CR28","doi-asserted-by":"crossref","unstructured":"Lucas, S.M., Panaretos, A., Sosa, L., Tang, A., Wong, S., Young, R.: ICDAR 2003 robust reading competitions. In: Seventh International Conference on Document Analysis and Recognition, pp. 682\u2013687 (2003). Proceedings, CiteSeer (2003)","DOI":"10.1109\/ICDAR.2003.1227749"},{"key":"18_CR29","doi-asserted-by":"crossref","unstructured":"Mishra, A., Alahari, K., Jawahar, C.: Scene text recognition using higher order language priors (2012)","DOI":"10.5244\/C.26.127"},{"issue":"4","key":"18_CR30","doi-asserted-by":"publisher","first-page":"595","DOI":"10.1175\/1520-0450(1973)012<0595:ANVPOT>2.0.CO;2","volume":"12","author":"AH Murphy","year":"1973","unstructured":"Murphy, A.H.: A new vector partition of the probability score. J. Appl. Meteorol. 12(4), 595\u2013600 (1973)","journal-title":"J. Appl. Meteorol."},{"key":"18_CR31","unstructured":"Naeini, M.P., Cooper, G.F., Hauskrecht, M.: Obtaining well calibrated probabilities using bayesian binning. In: Proceedings of the AAAI Conference on Artificial Intelligence. AAAI Conference on Artificial Intelligence, vol. 2015, p. 2901. NIH Public Access (2015)"},{"key":"18_CR32","doi-asserted-by":"crossref","unstructured":"Nguyen, K., O\u2019Connor, B.: Posterior calibration and exploratory analysis for natural language processing models. In: EMNLP (2015)","DOI":"10.18653\/v1\/D15-1182"},{"key":"18_CR33","doi-asserted-by":"crossref","unstructured":"Niculescu-Mizil, A., Caruana, R.: Predicting good probabilities with supervised learning. In: Proceedings of the 22nd International Conference on Machine Learning, pp. 625\u2013632 (2005)","DOI":"10.1145\/1102351.1102430"},{"key":"18_CR34","unstructured":"Nixon, J., Dusenberry, M.W., Zhang, L., Jerfel, G., Tran, D.: Measuring calibration in deep learning. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops (2019)"},{"key":"18_CR35","unstructured":"Ovadia, Y., et al.: Can you trust your model\u2019s uncertainty? evaluating predictive uncertainty under dataset shift. In: Advances in Neural Information Processing Systems, pp. 13991\u201314002 (2019)"},{"key":"18_CR36","unstructured":"Pereyra, G., Tucker, G., Chorowski, J., Kaiser, \u0141., Hinton, G.: Regularizing neural networks by penalizing confident output distributions. arXiv preprint arXiv:1701.06548 (2017)"},{"issue":"3","key":"18_CR37","first-page":"61","volume":"10","author":"J Platt","year":"1999","unstructured":"Platt, J., et al.: Probabilistic outputs for support vector machines and comparisons to regularized likelihood methods. Adv. Large Margin Class. 10(3), 61\u201374 (1999)","journal-title":"Adv. Large Margin Class."},{"key":"18_CR38","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: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 13528\u201313537 (2020)","DOI":"10.1109\/CVPR42600.2020.01354"},{"key":"18_CR39","doi-asserted-by":"crossref","unstructured":"Quy Phan, T., Shivakumara, P., Tian, S., Lim Tan, C.: Recognizing text with perspective distortion in natural scenes. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 569\u2013576 (2013)","DOI":"10.1109\/ICCV.2013.76"},{"issue":"18","key":"18_CR40","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":"18_CR41","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":"18_CR42","doi-asserted-by":"crossref","unstructured":"Shi, B., Wang, X., Lyu, P., Yao, C., Bai, X.: Robust scene text recognition with automatic rectification. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 4168\u20134176 (2016)","DOI":"10.1109\/CVPR.2016.452"},{"key":"18_CR43","doi-asserted-by":"crossref","unstructured":"Shi, B., Yang, M., Wang, X., Lyu, P., Yao, C., Bai, X.: Aster: an attentional scene text recognizer with flexible rectification. IEEE Transactions on Pattern Analysis and Machine Intelligence (2018)","DOI":"10.1109\/TPAMI.2018.2848939"},{"key":"18_CR44","doi-asserted-by":"crossref","unstructured":"Wan, Z., Zhang, J., Zhang, L., Luo, J., Yao, C.: On vocabulary reliance in scene text recognition. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 11425\u201311434 (2020)","DOI":"10.1109\/CVPR42600.2020.01144"},{"key":"18_CR45","unstructured":"Wang, K., Babenko, B., Belongie, S.: End-to-end scene text recognition. In: 2011 International Conference on Computer Vision, pp. 1457\u20131464. IEEE (2011)"}],"container-title":["Lecture Notes in Computer Science","Computer Vision \u2013 ECCV 2022 Workshops"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-25069-9_18","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,10,14]],"date-time":"2024-10-14T04:13:52Z","timestamp":1728879232000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-25069-9_18"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023]]},"ISBN":["9783031250682","9783031250699"],"references-count":45,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-25069-9_18","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023]]},"assertion":[{"value":"14 February 2023","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)"}},{"value":"From the workshops, 367 reviewed full papers have been selected for publication","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)"}}]}}