{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,13]],"date-time":"2026-02-13T23:43:38Z","timestamp":1771026218636,"version":"3.50.1"},"publisher-location":"Cham","reference-count":45,"publisher":"Springer International Publishing","isbn-type":[{"value":"9783030210731","type":"print"},{"value":"9783030210748","type":"electronic"}],"license":[{"start":{"date-parts":[[2019,1,1]],"date-time":"2019-01-01T00:00:00Z","timestamp":1546300800000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2019]]},"DOI":"10.1007\/978-3-030-21074-8_11","type":"book-chapter","created":{"date-parts":[[2019,6,18]],"date-time":"2019-06-18T14:10:14Z","timestamp":1560867014000},"page":"127-143","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":53,"title":["E2E-MLT - An Unconstrained End-to-End Method for Multi-language Scene Text"],"prefix":"10.1007","author":[{"given":"Michal","family":"Bu\u0161ta","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yash","family":"Patel","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jiri","family":"Matas","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2019,6,19]]},"reference":[{"key":"11_CR1","unstructured":"Unicode table. https:\/\/unicode-table.com\/ . Accessed 30 Sept 2017"},{"issue":"5","key":"11_CR2","doi-asserted-by":"publisher","first-page":"898","DOI":"10.1109\/TPAMI.2010.161","volume":"33","author":"P Arbelaez","year":"2011","unstructured":"Arbelaez, P., Maire, M., Fowlkes, C., Malik, J.: Contour detection and hierarchical image segmentation. PAMI 33(5), 898\u2013916 (2011)","journal-title":"PAMI"},{"key":"11_CR3","doi-asserted-by":"crossref","unstructured":"Arbel\u00e1ez, P., Pont-Tuset, J., Barron, J.T., Marques, F., Malik, J.: Multiscale combinatorial grouping. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (2014)","DOI":"10.1109\/CVPR.2014.49"},{"key":"11_CR4","doi-asserted-by":"crossref","unstructured":"Bosch, A., Zisserman, A., Munoz, X.: Image classification using random forests and ferns. In: CVPR (2007)","DOI":"10.1109\/ICCV.2007.4409066"},{"key":"11_CR5","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: 2017 IEEE International Conference on Computer Vision (ICCV), pp. 2223\u20132231. IEEE (2017)","DOI":"10.1109\/ICCV.2017.242"},{"key":"11_CR6","unstructured":"Chen, T.Q., Schmidt, M.: Fast patch-based style transfer of arbitrary style. arXiv preprint arXiv:1612.04337 (2016)"},{"issue":"8","key":"11_CR7","doi-asserted-by":"publisher","first-page":"1532","DOI":"10.1109\/TPAMI.2014.2300479","volume":"36","author":"P Doll\u00e1r","year":"2014","unstructured":"Doll\u00e1r, P., Appel, R., Belongie, S., Perona, P.: Fast feature pyramids for object detection. PAMI 36(8), 1532\u20131545 (2014)","journal-title":"PAMI"},{"key":"11_CR8","doi-asserted-by":"crossref","unstructured":"Epshtein, B., Ofek, E., Wexler, Y.: Detecting text in natural scenes with stroke width transform. In: CVPR (2010)","DOI":"10.1109\/CVPR.2010.5540041"},{"issue":"6","key":"11_CR9","doi-asserted-by":"publisher","first-page":"381","DOI":"10.1145\/358669.358692","volume":"24","author":"MA Fischler","year":"1981","unstructured":"Fischler, M.A., Bolles, R.C.: Random sample consensus: a paradigm for model fitting with applications to image analysis and automated cartography. Commun. ACM 24(6), 381\u2013395 (1981)","journal-title":"Commun. ACM"},{"key":"11_CR10","doi-asserted-by":"crossref","unstructured":"Girshick, R.: Fast R-CNN. In: ICCV (2015)","DOI":"10.1109\/ICCV.2015.169"},{"key":"11_CR11","doi-asserted-by":"publisher","first-page":"60","DOI":"10.1016\/j.patcog.2017.04.027","volume":"70","author":"L G\u00f3mez","year":"2017","unstructured":"G\u00f3mez, L., Karatzas, D.: Textproposals: a text-specific selective search algorithm for word spotting in the wild. Pattern Recognit. 70, 60\u201374 (2017)","journal-title":"Pattern Recognit."},{"key":"11_CR12","doi-asserted-by":"publisher","first-page":"85","DOI":"10.1016\/j.patcog.2017.01.032","volume":"67","author":"L Gomez","year":"2017","unstructured":"Gomez, L., Nicolaou, A., Karatzas, D.: Improving patch-based scene text script identification with ensembles of conjoined networks. Pattern Recognit. 67, 85\u201396 (2017)","journal-title":"Pattern Recognit."},{"key":"11_CR13","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 (2006)","DOI":"10.1145\/1143844.1143891"},{"key":"11_CR14","doi-asserted-by":"crossref","unstructured":"Gupta, A., Vedaldi, A., Zisserman, A.: Synthetic data for text localisation in natural images. In: CVPR (2016)","DOI":"10.1109\/CVPR.2016.254"},{"key":"11_CR15","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: CVPR (2016)","DOI":"10.1109\/CVPR.2016.90"},{"issue":"1","key":"11_CR16","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. IJCV 116(1), 1\u201320 (2016)","journal-title":"IJCV"},{"key":"11_CR17","unstructured":"Jaderberg, M., Simonyan, K., Zisserman, A., et al.: Spatial transformer networks. In: NIPS (2015)"},{"key":"11_CR18","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"512","DOI":"10.1007\/978-3-319-10593-2_34","volume-title":"Computer Vision \u2013 ECCV 2014","author":"M Jaderberg","year":"2014","unstructured":"Jaderberg, M., Vedaldi, A., Zisserman, A.: Deep features for text spotting. In: Fleet, D., Pajdla, T., Schiele, B., Tuytelaars, T. (eds.) ECCV 2014. LNCS, vol. 8692, pp. 512\u2013528. Springer, Cham (2014). https:\/\/doi.org\/10.1007\/978-3-319-10593-2_34"},{"key":"11_CR19","doi-asserted-by":"crossref","unstructured":"Jain, M., Mathew, M., Jawahar, C.: Unconstrained scene text and video text recognition for Arabic script. In: ASAR (2017)","DOI":"10.1109\/ASAR.2017.8067754"},{"key":"11_CR20","doi-asserted-by":"crossref","unstructured":"Johnson, J., Karpathy, A., Fei-Fei, L.: Densecap: fully convolutional localization networks for dense captioning. In: CVPR (2016)","DOI":"10.1109\/CVPR.2016.494"},{"key":"11_CR21","doi-asserted-by":"crossref","unstructured":"Karatzas, D., et al.: ICDAR 2015 competition on robust reading. In: ICDAR (2015)","DOI":"10.1109\/ICDAR.2015.7333942"},{"key":"11_CR22","unstructured":"Kingma, D., Ba, J.: Adam: a method for stochastic optimization. arXiv preprint arXiv:1412.6980 (2014)"},{"issue":"11","key":"11_CR23","doi-asserted-by":"publisher","first-page":"2278","DOI":"10.1109\/5.726791","volume":"86","author":"Y LeCun","year":"1998","unstructured":"LeCun, Y., Bottou, L., Bengio, Y., Haffner, P.: Gradient-based learning applied to document recognition. Proc. IEEE 86(11), 2278\u20132324 (1998)","journal-title":"Proc. IEEE"},{"key":"11_CR24","doi-asserted-by":"crossref","unstructured":"Lee, C.Y., Osindero, S.: Recursive recurrent nets with attention modeling for OCR in the wild. In: CVPR (2016)","DOI":"10.1109\/CVPR.2016.245"},{"key":"11_CR25","doi-asserted-by":"crossref","unstructured":"Li, H., Wang, P., Shen, C.: Towards end-to-end text spotting with convolutional recurrent neural networks. In: ICCV (2017)","DOI":"10.1109\/ICCV.2017.560"},{"key":"11_CR26","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 (2017)","DOI":"10.1609\/aaai.v31i1.11196"},{"key":"11_CR27","doi-asserted-by":"crossref","unstructured":"Lin, T.Y., Doll\u00e1r, P., Girshick, R., He, K., Hariharan, B., Belongie, S.: Feature pyramid networks for object detection. In: CVPR (2017)","DOI":"10.1109\/CVPR.2017.106"},{"key":"11_CR28","doi-asserted-by":"crossref","unstructured":"Liu, F., Shen, C., Lin, G.: Deep convolutional neural fields for depth estimation from a single image. In: CVPR (2015)","DOI":"10.1109\/CVPR.2015.7299152"},{"key":"11_CR29","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"21","DOI":"10.1007\/978-3-319-46448-0_2","volume-title":"Computer Vision \u2013 ECCV 2016","author":"W Liu","year":"2016","unstructured":"Liu, W., et al.: SSD: single shot MultiBox detector. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) ECCV 2016. LNCS, vol. 9905, pp. 21\u201337. Springer, Cham (2016). https:\/\/doi.org\/10.1007\/978-3-319-46448-0_2"},{"key":"11_CR30","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: CVPR (2018)","DOI":"10.1109\/CVPR.2018.00595"},{"key":"11_CR31","unstructured":"Ma, J., et al.: Arbitrary-oriented scene text detection via rotation proposals. arXiv preprint arXiv:1703.01086 (2017)"},{"key":"11_CR32","doi-asserted-by":"crossref","unstructured":"Milletari, F., Navab, N., Ahmadi, S.A.: V-net: fully convolutional neural networks for volumetric medical image segmentation. In: 3DV (2016)","DOI":"10.1109\/3DV.2016.79"},{"key":"11_CR33","doi-asserted-by":"crossref","unstructured":"Nayef, N.: ICDAR 2017 competition on multi-lingual scene text detection and script identification (2017)","DOI":"10.1109\/ICDAR.2017.237"},{"key":"11_CR34","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"770","DOI":"10.1007\/978-3-642-19318-7_60","volume-title":"Computer Vision \u2013 ACCV 2010","author":"L Neumann","year":"2011","unstructured":"Neumann, L., Matas, J.: A method for text localization and recognition in real-world images. In: Kimmel, R., Klette, R., Sugimoto, A. (eds.) ACCV 2010. LNCS, vol. 6494, pp. 770\u2013783. Springer, Heidelberg (2011). https:\/\/doi.org\/10.1007\/978-3-642-19318-7_60"},{"key":"11_CR35","doi-asserted-by":"crossref","unstructured":"Neumann, L., Matas, J.: Real-time scene text localization and recognition. In: CVPR (2012)","DOI":"10.1109\/CVPR.2012.6248097"},{"key":"11_CR36","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"395","DOI":"10.1007\/978-3-319-46604-0_29","volume-title":"Computer Vision \u2013 ECCV 2016 Workshops","author":"Y Patel","year":"2016","unstructured":"Patel, Y., Gomez, L., Rusi\u00f1ol, M., Karatzas, D.: Dynamic lexicon generation for natural scene images. In: Hua, G., J\u00e9gou, H. (eds.) ECCV 2016. LNCS, vol. 9913, pp. 395\u2013410. Springer, Cham (2016). https:\/\/doi.org\/10.1007\/978-3-319-46604-0_29"},{"key":"11_CR37","doi-asserted-by":"crossref","unstructured":"Redmon, J., Divvala, S., Girshick, R., Farhadi, A.: You only look once: unified, real-time object detection. In: CVPR (2016)","DOI":"10.1109\/CVPR.2016.91"},{"key":"11_CR38","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"234","DOI":"10.1007\/978-3-319-24574-4_28","volume-title":"Medical Image Computing and Computer-Assisted Intervention \u2013 MICCAI 2015","author":"O Ronneberger","year":"2015","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"},{"issue":"11","key":"11_CR39","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. PAMI 39(11), 2298\u20132304 (2017)","journal-title":"PAMI"},{"key":"11_CR40","doi-asserted-by":"crossref","unstructured":"Shi, B., et al.: ICDAR 2017 competition on reading Chinese text in the wild (RCTW-17). arXiv preprint arXiv:1708.09585 (2017)","DOI":"10.1109\/ICDAR.2017.233"},{"key":"11_CR41","unstructured":"Simonyan, K., Zisserman, A.: Very deep convolutional networks for large-scale image recognition. arXiv preprint arXiv:1409.1556 (2014)"},{"key":"11_CR42","doi-asserted-by":"crossref","unstructured":"Szegedy, C., et al.: Going deeper with convolutions. In: CVPR (2015)","DOI":"10.1109\/CVPR.2015.7298594"},{"key":"11_CR43","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, Y.: Detecting text in natural image with connectionist text proposal network. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) ECCV 2016. LNCS, vol. 9912, pp. 56\u201372. Springer, Cham (2016). https:\/\/doi.org\/10.1007\/978-3-319-46484-8_4"},{"key":"11_CR44","doi-asserted-by":"crossref","unstructured":"Zhou, X., et al.: East: an efficient and accurate scene text detector. In: CVPR (2017)","DOI":"10.1109\/CVPR.2017.283"},{"key":"11_CR45","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"391","DOI":"10.1007\/978-3-319-10602-1_26","volume-title":"Computer Vision \u2013 ECCV 2014","author":"CL Zitnick","year":"2014","unstructured":"Zitnick, C.L., Doll\u00e1r, P.: Edge boxes: locating object proposals from edges. In: Fleet, D., Pajdla, T., Schiele, B., Tuytelaars, T. (eds.) ECCV 2014. LNCS, vol. 8693, pp. 391\u2013405. Springer, Cham (2014). https:\/\/doi.org\/10.1007\/978-3-319-10602-1_26"}],"container-title":["Lecture Notes in Computer Science","Computer Vision \u2013 ACCV 2018 Workshops"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-030-21074-8_11","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,9,21]],"date-time":"2022-09-21T02:32:15Z","timestamp":1663727535000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/978-3-030-21074-8_11"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019]]},"ISBN":["9783030210731","9783030210748"],"references-count":45,"URL":"https:\/\/doi.org\/10.1007\/978-3-030-21074-8_11","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2019]]},"assertion":[{"value":"19 June 2019","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ACCV","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Asian Conference on Computer Vision","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Perth, WA","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Australia","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2018","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2 December 2018","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"6 December 2018","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"14","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"accv2018","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"http:\/\/accv2018.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":"Microsoft CMT","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"979","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":"274","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","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":"2.7","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)"}}]}}