{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,14]],"date-time":"2025-10-14T01:09:24Z","timestamp":1760404164235},"publisher-location":"Cham","reference-count":36,"publisher":"Springer International Publishing","isbn-type":[{"type":"print","value":"9783030208899"},{"type":"electronic","value":"9783030208905"}],"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\/978-3-030-20890-5_13","type":"book-chapter","created":{"date-parts":[[2019,6,1]],"date-time":"2019-06-01T11:18:34Z","timestamp":1559387914000},"page":"196-211","update-policy":"http:\/\/dx.doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":5,"title":["SAFE: Scale Aware Feature Encoder for Scene Text Recognition"],"prefix":"10.1007","author":[{"given":"Wei","family":"Liu","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Chaofeng","family":"Chen","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Kwan-Yee K.","family":"Wong","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2019,6,2]]},"reference":[{"issue":"12","key":"13_CR1","doi-asserted-by":"publisher","first-page":"2552","DOI":"10.1109\/TPAMI.2014.2339814","volume":"36","author":"J Almaz\u00e1n","year":"2014","unstructured":"Almaz\u00e1n, J., Gordo, A., Forn\u00e9s, A., Valveny, E.: Word spotting and recognition with embedded attributes. IEEE Trans. Pattern Anal. Mach. Intell. 36(12), 2552\u20132566 (2014)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"13_CR2","unstructured":"Bahdanau, D., Cho, K., Bengio, Y.: Neural machine translation by jointly learning to align and translate (2014). arXiv preprint: arXiv:1409.0473"},{"key":"13_CR3","unstructured":"Bai, F., Cheng, Z., Niu, Y., Pu, S., Zhou, S.: Edit probability for scene text recognition (2018). arXiv preprint: arXiv:1805.03384"},{"key":"13_CR4","doi-asserted-by":"crossref","unstructured":"Bissacco, A., Cummins, M., Netzer, Y., Neven, H.: PhotoOCR: reading text in uncontrolled conditions. In: IEEE International Conference on Computer Vision (2013)","DOI":"10.1109\/ICCV.2013.102"},{"key":"13_CR5","doi-asserted-by":"crossref","unstructured":"Chen, L.C., Yang, Y., Wang, J., Xu, W., Yuille, A.L.: Attention to scale: scale-aware semantic image segmentation. In: IEEE Conference on Computer Vision and Pattern Recognition (2016)","DOI":"10.1109\/CVPR.2016.396"},{"key":"13_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 (2017). arXiv preprint: arXiv:1709.02054v3","DOI":"10.1109\/ICCV.2017.543"},{"key":"13_CR7","unstructured":"Cheng, Z., Liu, X., Bai, F., Niu, Y., Pu, S., Zhou, S.: Arbitrarily-oriented text recognition (2017). arXiv preprint: arXiv:1711.04226"},{"key":"13_CR8","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: International Conference on Machine Learning (2006)","DOI":"10.1145\/1143844.1143891"},{"key":"13_CR9","doi-asserted-by":"crossref","unstructured":"Gupta, A., Vedaldi, A., Zisserman, A.: Synthetic data for text localisation in natural images. In: IEEE Conference on Computer Vision and Pattern Recognition (2016)","DOI":"10.1109\/CVPR.2016.254"},{"key":"13_CR10","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 Conference on Artificial Intelligence (2016)","DOI":"10.1609\/aaai.v30i1.10465"},{"key":"13_CR11","unstructured":"Ioffe, S., Szegedy, C.: Batch normalization: accelerating deep network training by reducing internal covariate shift. In: International Conference on Machine Learning (2015)"},{"key":"13_CR12","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, Advances in Neural Information Processing Systems (2014)"},{"key":"13_CR13","unstructured":"Jaderberg, M., Simonyan, K., Vedaldi, A., Zisserman, A.: Deep structured output learning for unconstrained text recognition. In: International Conference on Learning Representations (2015)"},{"issue":"1","key":"13_CR14","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":"13_CR15","unstructured":"Jaderberg, M., Simonyan, K., Zisserman, A., Kavukcuoglu, K.: Spatial transformer networks. In: Advances in Neural Information Processing Systems (2015)"},{"key":"13_CR16","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, Part IV. LNCS, vol. 8692, pp. 512\u2013528. Springer, Cham (2014). https:\/\/doi.org\/10.1007\/978-3-319-10593-2_34"},{"key":"13_CR17","doi-asserted-by":"crossref","unstructured":"Karatzas, D., et al.: ICDAR 2015 competition on robust reading. In: IEEE International Conference on Document Analysis and Recognition (2015)","DOI":"10.1109\/ICDAR.2015.7333942"},{"key":"13_CR18","doi-asserted-by":"crossref","unstructured":"Karatzas, D., et al.: ICDAR 2013 robust reading competition. In: IEEE International Conference on Document Analysis and Recognition (2013)","DOI":"10.1109\/ICDAR.2013.221"},{"key":"13_CR19","doi-asserted-by":"crossref","unstructured":"Lee, C.Y., Bhardwaj, A., Di, W., Jagadeesh, V., Piramuthu, R.: Region-based discriminative feature pooling for scene text recognition. In: IEEE Conference on Computer Vision and Pattern Recognition (2014)","DOI":"10.1109\/CVPR.2014.516"},{"key":"13_CR20","doi-asserted-by":"crossref","unstructured":"Lee, C.Y., Osindero, S.: Recursive recurrent nets with attention modeling for OCR in the wild. In: IEEE Conference on Computer Vision and Pattern Recognition (2016)","DOI":"10.1109\/CVPR.2016.245"},{"key":"13_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 Conference on Artificial Intelligence (2018)","DOI":"10.1609\/aaai.v32i1.12246"},{"key":"13_CR22","doi-asserted-by":"crossref","unstructured":"Liu, W., Chen, C., Wong, K.K., Su, Z., Han, J.: STAR-Net: a spatial attention residue network for scene text recognition. In: British Machine Vision Conference (2016)","DOI":"10.5244\/C.30.43"},{"issue":"2\u20133","key":"13_CR23","doi-asserted-by":"publisher","first-page":"105","DOI":"10.1007\/s10032-004-0134-3","volume":"7","author":"SM Lucas","year":"2005","unstructured":"Lucas, S.M., et al.: ICDAR 2003 robust reading competitions: entries, results, and future directions. Int. J. Doc. Anal. Recognit. 7(2\u20133), 105\u2013122 (2005)","journal-title":"Int. J. Doc. Anal. Recognit."},{"key":"13_CR24","unstructured":"Luo, W., Li, Y., Urtasun, R., Zemel, R.: Understanding the effective receptive field in deep convolutional neural networks. In: Advances in Neural Information Processing Systems (2016)"},{"key":"13_CR25","doi-asserted-by":"crossref","unstructured":"Mishra, A., Alahari, K., Jawahar, C.: Scene text recognition using higher order language priors. In: British Machine Vision Conference (2012)","DOI":"10.5244\/C.26.127"},{"key":"13_CR26","doi-asserted-by":"crossref","unstructured":"Neumann, L., Matas, J.: Real-time scene text localization and recognition. In: IEEE Conference on Computer Vision and Pattern Recognition (2012)","DOI":"10.1109\/CVPR.2012.6248097"},{"key":"13_CR27","doi-asserted-by":"crossref","unstructured":"Phan, T., Shivakumara, P., Tian, S., Tan, C.: Recognizing text with perspective distortion in natural scenes. In: IEEE International Conference on Computer Vision (2013)","DOI":"10.1109\/ICCV.2013.76"},{"key":"13_CR28","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, 2298\u20132304 (2016)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"13_CR29","doi-asserted-by":"crossref","unstructured":"Shi, B., Wang, X., Lyu, P., Yao, C., Bai, X.: Robust scene text recognition with automatic rectification. In: IEEE Conference on Computer Vision and Pattern Recognition (2016)","DOI":"10.1109\/CVPR.2016.452"},{"key":"13_CR30","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"35","DOI":"10.1007\/978-3-319-16865-4_3","volume-title":"Computer Vision \u2013 ACCV 2014","author":"B Su","year":"2015","unstructured":"Su, B., Lu, S.: Accurate scene text recognition based on recurrent neural network. In: Cremers, D., Reid, I., Saito, H., Yang, M.-H. (eds.) ACCV 2014, Part I. LNCS, vol. 9003, pp. 35\u201348. Springer, Cham (2015). https:\/\/doi.org\/10.1007\/978-3-319-16865-4_3"},{"key":"13_CR31","unstructured":"Wang, K., Babenko, B., Belongie, S.: End-to-end scene text recognition. In: IEEE International Conference on Computer Vision (2011)"},{"key":"13_CR32","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"591","DOI":"10.1007\/978-3-642-15549-9_43","volume-title":"Computer Vision \u2013 ECCV 2010","author":"K Wang","year":"2010","unstructured":"Wang, K., Belongie, S.: Word spotting in the wild. In: Daniilidis, K., Maragos, P., Paragios, N. (eds.) ECCV 2010, Part I. LNCS, vol. 6311, pp. 591\u2013604. Springer, Heidelberg (2010). https:\/\/doi.org\/10.1007\/978-3-642-15549-9_43"},{"key":"13_CR33","unstructured":"Wang, T., Wu, D.J., Coates, A., Ng, A.Y.: End-to-end text recognition with convolutional neural networks. In: IEEE International Conference on Pattern Recognition (2012)"},{"key":"13_CR34","doi-asserted-by":"crossref","unstructured":"Yang, X., He, D., Zhou, Z., Kifer, D., Giles, C.L.: Learning to read irregular text with attention mechanisms. In: Twenty-Sixth International Joint Conference on Artificial Intelligence, IJCAI 2017 (2017)","DOI":"10.24963\/ijcai.2017\/458"},{"key":"13_CR35","doi-asserted-by":"crossref","unstructured":"Yao, C., Bai, X., Shi, B., Liu, W.: Strokelets: a learned multi-scale representation for scene text recognition. In: IEEE Conference on Computer Vision and Pattern Recognition (2014)","DOI":"10.1109\/CVPR.2014.515"},{"key":"13_CR36","unstructured":"Zeiler, M.D.: ADADELTA: an adaptive learning rate method (2012). arXiv preprint: arXiv:1212.5701"}],"container-title":["Lecture Notes in Computer Science","Computer Vision \u2013 ACCV 2018"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-030-20890-5_13","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,9,18]],"date-time":"2022-09-18T22:44:53Z","timestamp":1663541093000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/978-3-030-20890-5_13"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019]]},"ISBN":["9783030208899","9783030208905"],"references-count":36,"URL":"https:\/\/doi.org\/10.1007\/978-3-030-20890-5_13","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2019]]},"assertion":[{"value":"2 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"}},{"value":"Microsoft CMT","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information"}},{"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"}},{"value":"274","order":4,"name":"number_of_full_papers_accepted","label":"Number of Full Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information"}},{"value":"0","order":5,"name":"number_of_short_papers_accepted","label":"Number of Short Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information"}},{"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"}},{"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"}},{"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"}},{"value":"No","order":9,"name":"external_reviewers_involved","label":"External Reviewers Involved","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information"}}]}}