{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,14]],"date-time":"2026-01-14T21:28:22Z","timestamp":1768426102253,"version":"3.49.0"},"publisher-location":"Cham","reference-count":45,"publisher":"Springer International Publishing","isbn-type":[{"value":"9783030208929","type":"print"},{"value":"9783030208936","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\/978-3-030-20893-6_6","type":"book-chapter","created":{"date-parts":[[2019,5,28]],"date-time":"2019-05-28T07:25:52Z","timestamp":1559028352000},"page":"83-99","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":22,"title":["TextNet: Irregular Text Reading from Images with an End-to-End Trainable Network"],"prefix":"10.1007","author":[{"given":"Yipeng","family":"Sun","sequence":"first","affiliation":[]},{"given":"Chengquan","family":"Zhang","sequence":"additional","affiliation":[]},{"given":"Zuming","family":"Huang","sequence":"additional","affiliation":[]},{"given":"Jiaming","family":"Liu","sequence":"additional","affiliation":[]},{"given":"Junyu","family":"Han","sequence":"additional","affiliation":[]},{"given":"Errui","family":"Ding","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2019,5,29]]},"reference":[{"key":"6_CR1","unstructured":"Bahdanau, D., Cho, K., Bengio, Y.: Neural machine translation by jointly learning to align and translate. arXiv preprint arXiv:1409.0473 (2014)"},{"key":"6_CR2","doi-asserted-by":"crossref","unstructured":"Bissacco, A., Cummins, M., Netzer, Y., Neven, H.: Photo-OCR: reading text in uncontrolled conditions. In: Proceedings of ICCV, pp. 785\u2013792 (2013)","DOI":"10.1109\/ICCV.2013.102"},{"key":"6_CR3","unstructured":"Bluche, T.: Joint line segmentation and transcription for end-to-end handwritten paragraph recognition. In: Proceedings of NIPS, pp. 838\u2013846 (2016)"},{"key":"6_CR4","doi-asserted-by":"crossref","unstructured":"Bluche, T., Louradour, J., Messina, R.: Scan, attend and read: end-to-end handwritten paragraph recognition with mdlstm attention. arXiv preprint arXiv:1604.03286 (2016)","DOI":"10.1109\/ICDAR.2017.174"},{"key":"6_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: Proceedings of ICCV (2017)","DOI":"10.1109\/ICCV.2017.242"},{"key":"6_CR6","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: Proceedings of CVPR, pp. 3640\u20133649 (2016)","DOI":"10.1109\/CVPR.2016.396"},{"key":"6_CR7","doi-asserted-by":"crossref","unstructured":"Chng, C.K., Chan, C.S.: Total-text: a comprehensive dataset for scene text detection and recognition. In: Proceedings of ICDAR (2017)","DOI":"10.1109\/ICDAR.2017.157"},{"key":"6_CR8","doi-asserted-by":"crossref","unstructured":"Dai, Y., Huang, Z., Gao, Y., Chen, K.: Fused text segmentation networks for multi-oriented scene text detection. arXiv preprint arXiv:1709.03272 (2017)","DOI":"10.1109\/ICPR.2018.8546066"},{"key":"6_CR9","doi-asserted-by":"crossref","unstructured":"Girshick, R.: Fast R-CNN. arXiv preprint arXiv:1504.08083 (2015)","DOI":"10.1109\/ICCV.2015.169"},{"key":"6_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 ICML, pp. 369\u2013376. ACM (2006)","DOI":"10.1145\/1143844.1143891"},{"key":"6_CR11","doi-asserted-by":"crossref","unstructured":"Graves, A., Mohamed, A.R., Hinton, G.: Speech recognition with deep recurrent neural networks. In: Proceedings of ICASSP, pp. 6645\u20136649 (2013)","DOI":"10.1109\/ICASSP.2013.6638947"},{"key":"6_CR12","doi-asserted-by":"crossref","unstructured":"Gupta, A., Vedaldi, A., Zisserman, A.: Synthetic data for text localisation in natural images. In: Proceedings of CVPR, pp. 2315\u20132324 (2016)","DOI":"10.1109\/CVPR.2016.254"},{"key":"6_CR13","doi-asserted-by":"crossref","unstructured":"He, K., Gkioxari, G., Doll\u00e1r, P., Girshick, R.: Mask R-CNN. In: Proceedings of ICCV, pp. 2980\u20132988 (2017)","DOI":"10.1109\/ICCV.2017.322"},{"key":"6_CR14","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: Proceedings of CVPR, pp. 770\u2013778 (2016)","DOI":"10.1109\/CVPR.2016.90"},{"key":"6_CR15","doi-asserted-by":"crossref","unstructured":"He, P., Huang, W., Qiao, Y., Loy, C.C., Tang, X.: Reading scene text in deep convolutional sequences. In: Proceedings of AAAI, vol. 16, pp. 3501\u20133508 (2016)","DOI":"10.1609\/aaai.v30i1.10465"},{"key":"6_CR16","doi-asserted-by":"crossref","unstructured":"He, T., Tian, Z., Huang, W., Shen, C., Qiao, Y., Sun, C.: An end-to-end textspotter with explicit alignment and attention. CoRR abs\/1803.03474 (2018)","DOI":"10.1109\/CVPR.2018.00527"},{"key":"6_CR17","doi-asserted-by":"crossref","unstructured":"He, W., Zhang, X.Y., Yin, F., Liu, C.L.: Deep direct regression for multi-oriented scene text detection. In: Proceedings of ICCV (2017)","DOI":"10.1109\/ICCV.2017.87"},{"key":"6_CR18","doi-asserted-by":"crossref","unstructured":"Hu, H., Zhang, C., Luo, Y., Wang, Y., Han, J., Ding, E.: Wordsup: exploiting word annotations for character based text detection. In: Proceedings of ICCV (2017)","DOI":"10.1109\/ICCV.2017.529"},{"key":"6_CR19","unstructured":"Huang, L., Yang, Y., Deng, Y., Yu, Y.: Densebox: unifying landmark localization with end to end object detection. arXiv preprint arXiv:1509.04874 (2015)"},{"issue":"1","key":"6_CR20","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":"6_CR21","unstructured":"Jaderberg, M., Simonyan, K., Zisserman, A., et al.: Spatial transformer networks. In: Proceedings of NIPS, pp. 2017\u20132025 (2015)"},{"key":"6_CR22","doi-asserted-by":"crossref","unstructured":"Jiang, Y., et al.: R2CNN: rotational region CNN for orientation robust scene text detection. arXiv preprint arXiv:1706.09579 (2017)","DOI":"10.1109\/ICPR.2018.8545598"},{"key":"6_CR23","doi-asserted-by":"crossref","unstructured":"Karatzas, D., et al.: ICDAR 2015 competition on robust reading. In: Proceedings of ICDAR, pp. 1156\u20131160. IEEE (2015)","DOI":"10.1109\/ICDAR.2015.7333942"},{"key":"6_CR24","doi-asserted-by":"crossref","unstructured":"Lee, C.Y., Osindero, S.: Recursive recurrent nets with attention modeling for OCR in the wild. In: Proceedings of CVPR, pp. 2231\u20132239 (2016)","DOI":"10.1109\/CVPR.2016.245"},{"key":"6_CR25","doi-asserted-by":"crossref","unstructured":"Li, H., Wang, P., Shen, C.: Towards end-to-end text spotting with convolutional recurrent neural networks. In: Proceedings of ICCV (2017)","DOI":"10.1109\/ICCV.2017.560"},{"key":"6_CR26","doi-asserted-by":"crossref","unstructured":"Liao, M., Shi, B., Bai, X.: Textboxes++: a single-shot oriented scene text detector. arXiv preprint arXiv:1801.02765 (2018)","DOI":"10.1109\/TIP.2018.2825107"},{"key":"6_CR27","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: Proceedings of AAAI, pp. 4161\u20134167 (2017)","DOI":"10.1609\/aaai.v31i1.11196"},{"key":"6_CR28","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: Proceedings of CVPR (2017)","DOI":"10.1109\/CVPR.2017.106"},{"key":"6_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":"6_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. arXiv preprint arXiv:1801.01671 (2018)","DOI":"10.1109\/CVPR.2018.00595"},{"key":"6_CR31","doi-asserted-by":"crossref","unstructured":"Liu, Y., Jin, L.: Deep matching prior network: toward tighter multi-oriented text detection. In: Proceedings of CVPR (2017)","DOI":"10.1109\/CVPR.2017.368"},{"key":"6_CR32","unstructured":"Ma, J., et al.: Arbitrary-oriented scene text detection via rotation proposals. arXiv preprint arXiv:1703.01086 (2017)"},{"key":"6_CR33","doi-asserted-by":"crossref","unstructured":"Neumann, L., Matas, J.: Real-time scene text localization and recognition. In: Proceedings of CVPR, pp. 3538\u20133545 (2012)","DOI":"10.1109\/CVPR.2012.6248097"},{"key":"6_CR34","doi-asserted-by":"crossref","unstructured":"Redmon, J., Farhadi, A.: Yolo9000: better, faster, stronger. arXiv preprint 1612 (2016)","DOI":"10.1109\/CVPR.2017.690"},{"key":"6_CR35","unstructured":"Ren, S., He, K., Girshick, R., Sun, J.: Faster R-CNN: towards real-time object detection with region proposal networks. In: Proceedings of NIPS, pp. 91\u201399 (2015)"},{"key":"6_CR36","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"},{"key":"6_CR37","doi-asserted-by":"crossref","unstructured":"Shi, B., Bai, X., Belongie, S.: Detecting oriented text in natural images by linking segments. In: Proceedings of CVPR (2017)","DOI":"10.1109\/CVPR.2017.371"},{"issue":"11","key":"6_CR38","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 Trans. Pattern Anal. Mach. Intell. 39(11), 2298\u20132304 (2017)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"6_CR39","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 CVPR, pp. 4168\u20134176 (2016)","DOI":"10.1109\/CVPR.2016.452"},{"key":"6_CR40","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":"6_CR41","unstructured":"Wang, T., Wu, D.J., Coates, A., Ng, A.Y.: End-to-end text recognition with convolutional neural networks. In: Proceedings of ICPR, pp. 3304\u20133308 (2012)"},{"key":"6_CR42","doi-asserted-by":"crossref","unstructured":"Wojna, Z., et al.: Attention-based extraction of structured information from street view imagery. In: Proceedings of ICDAR (2017)","DOI":"10.1109\/ICDAR.2017.143"},{"key":"6_CR43","unstructured":"Xu, K., et al.: Show, attend and tell: Neural image caption generation with visual attention. In: Proceedings of ICML, pp. 2048\u20132057 (2015)"},{"key":"6_CR44","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: Proceedings of IJCAI (2017)","DOI":"10.24963\/ijcai.2017\/458"},{"key":"6_CR45","doi-asserted-by":"crossref","unstructured":"Zhou, X., et al.: EAST: an efficient and accurate scene text detector. In: Proceedings of CVPR (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\/978-3-030-20893-6_6","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,9,18]],"date-time":"2022-09-18T18:43:38Z","timestamp":1663526618000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/978-3-030-20893-6_6"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019]]},"ISBN":["9783030208929","9783030208936"],"references-count":45,"URL":"https:\/\/doi.org\/10.1007\/978-3-030-20893-6_6","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":"29 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"}}]}}