{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,26]],"date-time":"2025-03-26T23:14:43Z","timestamp":1743030883650,"version":"3.40.3"},"publisher-location":"Cham","reference-count":27,"publisher":"Springer International Publishing","isbn-type":[{"type":"print","value":"9783030208721"},{"type":"electronic","value":"9783030208738"}],"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\/978-3-030-20873-8_17","type":"book-chapter","created":{"date-parts":[[2019,5,25]],"date-time":"2019-05-25T20:32:03Z","timestamp":1558816323000},"page":"260-275","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Large Scale Scene Text Verification with Guided Attention"],"prefix":"10.1007","author":[{"given":"Dafang","family":"He","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yeqing","family":"Li","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Alexander","family":"Gorban","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Derrall","family":"Heath","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Julian","family":"Ibarz","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Qian","family":"Yu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Daniel","family":"Kifer","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"C. Lee","family":"Giles","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2019,5,26]]},"reference":[{"key":"17_CR1","doi-asserted-by":"crossref","unstructured":"Antol, S., et al.: VQA: visual question answering. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 2425\u20132433 (2015)","DOI":"10.1109\/ICCV.2015.279"},{"key":"17_CR2","unstructured":"Chen, X., Yuille, A.L.: Detecting and reading text in natural scenes. In: Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition, CVPR, vol. 2, p. II-366. IEEE (2004)"},{"key":"17_CR3","doi-asserted-by":"crossref","unstructured":"Epshtein, B., Ofek, E., Wexler, Y.: Detecting text in natural scenes with stroke width transform. In: Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition, CVPR, pp. 2963\u20132970. IEEE (2010)","DOI":"10.1109\/CVPR.2010.5540041"},{"key":"17_CR4","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":"17_CR5","doi-asserted-by":"crossref","unstructured":"He, D., et al.: Multi-scale FCN with cascaded instance aware segmentation for arbitrary oriented word spotting in the wild. In: The IEEE Conference on Computer Vision and Pattern Recognition (CVPR), July 2017","DOI":"10.1109\/CVPR.2017.58"},{"key":"17_CR6","doi-asserted-by":"crossref","unstructured":"He, P., Huang, W., Qiao, Y., Loy, C., Tang, X.: Reading scene text in deep convolutional sequences. In: AAAI Conference on Artificial Intelligence (2016)","DOI":"10.1609\/aaai.v30i1.10465"},{"issue":"8","key":"17_CR7","doi-asserted-by":"publisher","first-page":"1735","DOI":"10.1162\/neco.1997.9.8.1735","volume":"9","author":"S Hochreiter","year":"1997","unstructured":"Hochreiter, S., Schmidhuber, J.: Long short-term memory. Neural Comput. 9(8), 1735\u20131780 (1997)","journal-title":"Neural Comput."},{"issue":"1","key":"17_CR8","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."},{"issue":"5","key":"17_CR9","doi-asserted-by":"publisher","first-page":"1063","DOI":"10.1109\/TMM.2016.2638622","volume":"19","author":"S Karaoglu","year":"2017","unstructured":"Karaoglu, S., Tao, R., Gevers, T., Smeulders, A.W.: Words matter: scene text for image classification and retrieval. IEEE Trans. Multimed. 19(5), 1063\u20131076 (2017)","journal-title":"IEEE Trans. Multimed."},{"key":"17_CR10","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":"17_CR11","doi-asserted-by":"crossref","unstructured":"Mishra, A., Alahari, K., Jawahar, C.: Image retrieval using textual cues. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 3040\u20133047 (2013)","DOI":"10.1109\/ICCV.2013.378"},{"key":"17_CR12","doi-asserted-by":"crossref","unstructured":"Neumann, L., Matas, J.: Real-time scene text localization and recognition. In: Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition, CVPR, pp. 3538\u20133545. IEEE (2012)","DOI":"10.1109\/CVPR.2012.6248097"},{"key":"17_CR13","doi-asserted-by":"crossref","unstructured":"Shi, B., Bai, X., Belongie, S.: Detecting oriented text in natural images by linking segments. In: The IEEE Conference on Computer Vision and Pattern Recognition (CVPR), July 2017","DOI":"10.1109\/CVPR.2017.371"},{"key":"17_CR14","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":"17_CR15","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":"17_CR16","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"411","DOI":"10.1007\/978-3-319-46604-0_30","volume-title":"Computer Vision \u2013 ECCV 2016 Workshops","author":"R Smith","year":"2016","unstructured":"Smith, R., et al.: End-to-end interpretation of the French street name signs dataset. In: Hua, G., J\u00e9gou, H. (eds.) ECCV 2016. LNCS, vol. 9913, pp. 411\u2013426. Springer, Cham (2016). https:\/\/doi.org\/10.1007\/978-3-319-46604-0_30"},{"key":"17_CR17","doi-asserted-by":"crossref","unstructured":"Szegedy, C., Vanhoucke, V., Ioffe, S., Shlens, J., Wojna, Z.: Rethinking the inception architecture for computer vision. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 2818\u20132826 (2016)","DOI":"10.1109\/CVPR.2016.308"},{"key":"17_CR18","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":"17_CR19","unstructured":"Vinyals, O., Kaiser, \u0141., Koo, T., Petrov, S., Sutskever, I., Hinton, G.: Grammar as a foreign language. In: Advances in Neural Information Processing Systems, pp. 2773\u20132781 (2015)"},{"key":"17_CR20","doi-asserted-by":"crossref","unstructured":"Vinyals, O., Toshev, A., Bengio, S., Erhan, D.: Show and tell: a neural image caption generator. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 3156\u20133164 (2015)","DOI":"10.1109\/CVPR.2015.7298935"},{"key":"17_CR21","doi-asserted-by":"crossref","unstructured":"Wojna, Z., et al.: Attention-based extraction of structured information from street view imagery. arXiv preprint arXiv:1704.03549 (2017)","DOI":"10.1109\/ICDAR.2017.143"},{"key":"17_CR22","doi-asserted-by":"publisher","unstructured":"Yang, X., He, D., Zhou, Z., Kifer, D., Giles, C.L.: Learning to read irregular text with attention mechanisms. In: Proceedings of the Twenty-Sixth International Joint Conference on Artificial Intelligence, IJCAI 2017, pp. 3280\u20133286 (2017). https:\/\/doi.org\/10.24963\/ijcai.2017\/458","DOI":"10.24963\/ijcai.2017\/458"},{"key":"17_CR23","doi-asserted-by":"crossref","unstructured":"Yan, F., Mikolajczyk, K.: Deep correlation for matching images and text. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 3441\u20133450 (2015)","DOI":"10.1109\/CVPR.2015.7298966"},{"key":"17_CR24","unstructured":"Yu, Q., et al.: Large scale business discovery from street level imagery. arXiv preprint arXiv:1512.05430 (2015)"},{"key":"17_CR25","unstructured":"Zhang, Y., Gueguen, L., Zharkov, I., Zhang, P., Seifert, K., Kadlec, B.: Uber-text: a large-scale dataset for optical character recognition from street-level imagery. In: SUNw: Scene Understanding Workshop - CVPR 2017, Hawaii, USA (2017)"},{"key":"17_CR26","doi-asserted-by":"crossref","unstructured":"Zhang, Z., Zhang, C., Shen, W., Yao, C., Liu, W., Bai, X.: Multi-oriented text detection with fully convolutional networks. In: Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition, CVPR, June 2016","DOI":"10.1109\/CVPR.2016.451"},{"key":"17_CR27","doi-asserted-by":"crossref","unstructured":"Zhou, X., et al.: East: an efficient and accurate scene text detector. In: The IEEE Conference on Computer Vision and Pattern Recognition (CVPR), July 2017","DOI":"10.1109\/CVPR.2017.283"}],"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\/978-3-030-20873-8_17","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,9,18]],"date-time":"2022-09-18T17:16:58Z","timestamp":1663521418000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/978-3-030-20873-8_17"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019]]},"ISBN":["9783030208721","9783030208738"],"references-count":27,"URL":"https:\/\/doi.org\/10.1007\/978-3-030-20873-8_17","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":"26 May 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"}}]}}