{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,3]],"date-time":"2026-04-03T19:18:13Z","timestamp":1775243893110,"version":"3.50.1"},"publisher-location":"Cham","reference-count":38,"publisher":"Springer International Publishing","isbn-type":[{"value":"9783030012274","type":"print"},{"value":"9783030012281","type":"electronic"}],"license":[{"start":{"date-parts":[[2018,1,1]],"date-time":"2018-01-01T00:00:00Z","timestamp":1514764800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2018,1,1]],"date-time":"2018-01-01T00:00:00Z","timestamp":1514764800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2018]]},"DOI":"10.1007\/978-3-030-01228-1_27","type":"book-chapter","created":{"date-parts":[[2018,10,6]],"date-time":"2018-10-06T01:03:51Z","timestamp":1538787831000},"page":"449-465","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":42,"title":["Synthetically Supervised Feature Learning for Scene Text Recognition"],"prefix":"10.1007","author":[{"given":"Yang","family":"Liu","sequence":"first","affiliation":[]},{"given":"Zhaowen","family":"Wang","sequence":"additional","affiliation":[]},{"given":"Hailin","family":"Jin","sequence":"additional","affiliation":[]},{"given":"Ian","family":"Wassell","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2018,10,6]]},"reference":[{"issue":"12","key":"27_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":"27_CR2","unstructured":"Berthelot, D., Schumm, T., Metz, L.: Began: boundary equilibrium generative adversarial networks. arXiv preprint arXiv:1703.10717 (2017)"},{"key":"27_CR3","doi-asserted-by":"crossref","unstructured":"Bissacco, A., Cummins, M., Netzer, Y., Neven, H.: PhotoOCR: reading text in uncontrolled conditions. In: 2013 IEEE International Conference on Computer Vision (ICCV), pp. 785\u2013792. IEEE (2013)","DOI":"10.1109\/ICCV.2013.102"},{"key":"27_CR4","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. In: 2017 IEEE International Conference on Computer Vision (ICCV), pp. 5086\u20135094. IEEE (2017)","DOI":"10.1109\/ICCV.2017.543"},{"key":"27_CR5","doi-asserted-by":"crossref","unstructured":"Ghosh, S.K., Valveny, E., Bagdanov, A.D.: Visual attention models for scene text recognition. In: ICDAR (2017)","DOI":"10.1109\/ICDAR.2017.158"},{"key":"27_CR6","doi-asserted-by":"crossref","unstructured":"Goel, V., Mishra, A., Alahari, K., Jawahar, C.: Whole is greater than sum of parts: recognizing scene text words. In: 2013 12th International Conference on Document Analysis and Recognition (ICDAR), pp. 398\u2013402. IEEE (2013)","DOI":"10.1109\/ICDAR.2013.87"},{"key":"27_CR7","unstructured":"Goodfellow, I., et al.: Generative adversarial nets. In: Advances in Neural Information Processing Systems, pp. 2672\u20132680 (2014)"},{"key":"27_CR8","doi-asserted-by":"crossref","unstructured":"Gordo, A.: Supervised mid-level features for word image representation. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 2956\u20132964 (2015)","DOI":"10.1109\/CVPR.2015.7298914"},{"key":"27_CR9","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":"27_CR10","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 (ICASSP), pp. 6645\u20136649. IEEE (2013)","DOI":"10.1109\/ICASSP.2013.6638947"},{"issue":"8","key":"27_CR11","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."},{"key":"27_CR12","unstructured":"https:\/\/www.freetype.org"},{"key":"27_CR13","doi-asserted-by":"crossref","unstructured":"Isola, P., Zhu, J.Y., Zhou, T., Efros, A.A.: Image-to-image translation with conditional adversarial networks. arXiv preprint (2017)","DOI":"10.1109\/CVPR.2017.632"},{"key":"27_CR14","unstructured":"Jaderberg, M., Simonyan, K., Vedaldi, A., Zisserman, A.: Synthetic data and artificial neural networks for natural scene text recognition. In: NIPS Deep Learning Workshop (2014)"},{"key":"27_CR15","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":"27_CR16","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":"27_CR17","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":"27_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 (ICDAR), pp. 1484\u20131493. IEEE (2013)","DOI":"10.1109\/ICDAR.2013.221"},{"key":"27_CR19","unstructured":"Kingma, D.P., Ba, J.: Adam: a method for stochastic optimization. In: ICLR (2015)"},{"key":"27_CR20","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"},{"issue":"2\u20133","key":"27_CR21","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. (IJDAR) 7(2\u20133), 105\u2013122 (2005)","journal-title":"Int. J. Doc. Anal. Recognit. (IJDAR)"},{"key":"27_CR22","unstructured":"Mirza, M., Osindero, S.: Conditional generative adversarial nets. arXiv preprint arXiv:1411.1784 (2014)"},{"key":"27_CR23","doi-asserted-by":"crossref","unstructured":"Mishra, A., Alahari, K., Jawahar, C.: Scene text recognition using higher order language priors. In: BMVC 2012\u201323rd British Machine Vision Conference. BMVA (2012)","DOI":"10.5244\/C.26.127"},{"key":"27_CR24","first-page":"12","volume":"20","author":"X Peng","year":"2017","unstructured":"Peng, X., Yu, X., Sohn, K., Metaxas, D.N., Chandraker, M.: Reconstruction-based disentanglement for pose-invariant face recognition. Intervals 20, 12 (2017)","journal-title":"Intervals"},{"key":"27_CR25","doi-asserted-by":"crossref","unstructured":"Phan, T.Q., Shivakumara, P., Tian, S., Tan, C.L.: Recognizing text with perspective distortion in natural scenes. In: 2013 IEEE International Conference on Computer Vision (ICCV), pp. 569\u2013576. IEEE (2013)","DOI":"10.1109\/ICCV.2013.76"},{"issue":"18","key":"27_CR26","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":"27_CR27","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":"27_CR28","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":"27_CR29","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. LNCS, vol. 9003, pp. 35\u201348. Springer, Cham (2015). https:\/\/doi.org\/10.1007\/978-3-319-16865-4_3"},{"key":"27_CR30","doi-asserted-by":"crossref","unstructured":"Tran, L., Yin, X., Liu, X.: Disentangled representation learning GAN for pose-invariant face recognition. In: CVPR (2017)","DOI":"10.1109\/CVPR.2017.141"},{"key":"27_CR31","doi-asserted-by":"crossref","unstructured":"Wang, K., Babenko, B., Belongie, S.: End-to-end scene text recognition. In: 2011 IEEE International Conference on Computer Vision (ICCV), pp. 1457\u20131464. IEEE (2011)","DOI":"10.1109\/ICCV.2011.6126402"},{"key":"27_CR32","unstructured":"Wang, T., Wu, D.J., Coates, A., Ng, A.Y.: End-to-end text recognition with convolutional neural networks. In: ICPR (2012)"},{"key":"27_CR33","doi-asserted-by":"crossref","unstructured":"Yao, C., Bai, X., Shi, B., Liu, W.: Strokelets: a learned multi-scale representation for scene text recognition. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 4042\u20134049 (2014)","DOI":"10.1109\/CVPR.2014.515"},{"issue":"7","key":"27_CR34","doi-asserted-by":"publisher","first-page":"1480","DOI":"10.1109\/TPAMI.2014.2366765","volume":"37","author":"Q Ye","year":"2015","unstructured":"Ye, Q., Doermann, D.: Text detection and recognition in imagery: a survey. IEEE Trans. Pattern Anal. Mach. Intell. 37(7), 1480\u20131500 (2015)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"27_CR35","doi-asserted-by":"crossref","unstructured":"Yim, J., Jung, H., Yoo, B., Choi, C., Park, D., Kim, J.: Rotating your face using multi-task deep neural network. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 676\u2013684 (2015)","DOI":"10.1109\/CVPR.2015.7298667"},{"issue":"6","key":"27_CR36","doi-asserted-by":"publisher","first-page":"2752","DOI":"10.1109\/TIP.2016.2554321","volume":"25","author":"XC Yin","year":"2016","unstructured":"Yin, X.C., Zuo, Z.Y., Tian, S., Liu, C.L.: Text detection, tracking and recognition in video: a comprehensive survey. IEEE Trans. Image Process. 25(6), 2752\u20132773 (2016)","journal-title":"IEEE Trans. Image Process."},{"key":"27_CR37","doi-asserted-by":"crossref","unstructured":"Zhou, X., et al.: East: an efficient and accurate scene text detector. arXiv preprint arXiv:1704.03155 (2017)","DOI":"10.1109\/CVPR.2017.283"},{"key":"27_CR38","doi-asserted-by":"publisher","first-page":"19","DOI":"10.1007\/s11704-015-4488-0","volume":"10","author":"Y Zhu","year":"2016","unstructured":"Zhu, Y., Yao, C., Bai, X.: Scene text detection and recognition: recent advances and future trends. Front. Comput. Sci. 10, 19\u201336 (2016)","journal-title":"Front. Comput. Sci."}],"container-title":["Lecture Notes in Computer Science","Computer Vision \u2013 ECCV 2018"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-030-01228-1_27","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,3]],"date-time":"2026-04-03T18:43:18Z","timestamp":1775241798000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-030-01228-1_27"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2018]]},"ISBN":["9783030012274","9783030012281"],"references-count":38,"URL":"https:\/\/doi.org\/10.1007\/978-3-030-01228-1_27","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2018]]},"assertion":[{"value":"6 October 2018","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":"Munich","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Germany","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":"8 September 2018","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"14 September 2018","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"15","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"eccv2018","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/eccv2018.org\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"This content has been made available to all.","name":"free","label":"Free to read"}]}}