{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,9,3]],"date-time":"2025-09-03T10:47:47Z","timestamp":1756896467061,"version":"3.41.0"},"publisher-location":"Cham","reference-count":29,"publisher":"Springer International Publishing","isbn-type":[{"type":"print","value":"9783319466033"},{"type":"electronic","value":"9783319466040"}],"license":[{"start":{"date-parts":[[2016,1,1]],"date-time":"2016-01-01T00:00:00Z","timestamp":1451606400000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2016,1,1]],"date-time":"2016-01-01T00:00:00Z","timestamp":1451606400000},"content-version":"vor","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":[[2016]]},"DOI":"10.1007\/978-3-319-46604-0_29","type":"book-chapter","created":{"date-parts":[[2016,9,17]],"date-time":"2016-09-17T03:31:55Z","timestamp":1474083115000},"page":"395-410","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":11,"title":["Dynamic Lexicon Generation for Natural Scene Images"],"prefix":"10.1007","author":[{"given":"Yash","family":"Patel","sequence":"first","affiliation":[]},{"given":"Lluis","family":"Gomez","sequence":"additional","affiliation":[]},{"given":"Mar\u00e7al","family":"Rusi\u00f1ol","sequence":"additional","affiliation":[]},{"given":"Dimosthenis","family":"Karatzas","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2016,9,18]]},"reference":[{"key":"29_CR1","doi-asserted-by":"crossref","unstructured":"Karatzas, D., Shafait, F., Uchida, S., Iwamura, M., i Bigorda, L.G., Mestre, S.R., Mas, J., Mota, D.F., Almazan, J.A., de las Heras, L.P.: ICDAR 2013 robust reading competition. In: 2013 12th International Conference on Document Analysis and Recognition, pp. 1484\u20131493. IEEE (2013)","DOI":"10.1109\/ICDAR.2013.221"},{"key":"29_CR2","doi-asserted-by":"crossref","unstructured":"Karatzas, D., Gomez-Bigorda, L., Nicolaou, A., Ghosh, S., Bagdanov, A., Iwamura, M., Matas, J., Neumann, L., Chandrasekhar, V.R., Lu, S., 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":"29_CR3","unstructured":"Li, H., Shen, C.: Reading car license plates using deep convolutional neural networks and lstms. arXiv preprint arXiv:1601.05610 (2016)"},{"issue":"1","key":"29_CR4","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. Vision 116(1), 1\u201320 (2016)","journal-title":"Int. J. Comput. Vision"},{"key":"29_CR5","doi-asserted-by":"crossref","unstructured":"Gomez-Bigorda, L., Karatzas, D.: Textproposals: a text-specific selective search algorithm for word spotting in the wild. arXiv preprint arXiv:1604.02619 (2016)","DOI":"10.1016\/j.patcog.2017.04.027"},{"key":"29_CR6","unstructured":"Wang, T., Wu, D.J., Coates, A., Ng, A.Y.: End-to-end text recognition with convolutional neural networks. In: 2012 21st International Conference on Pattern Recognition (ICPR), pp. 3304\u20133308. IEEE (2012)"},{"key":"29_CR7","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. LNCS, vol. 6311, pp. 591\u2013604. Springer, Heidelberg (2010). doi: 10.1007\/978-3-642-15549-9_43"},{"key":"29_CR8","doi-asserted-by":"crossref","unstructured":"Frinken, V., Karatzas, D., Fischer, A.: A cache language model for whole document handwriting recognition. In: 2014 11th IAPR International Workshop on Document Analysis Systems (DAS), pp. 166\u2013170. IEEE (2014)","DOI":"10.1109\/DAS.2014.56"},{"key":"29_CR9","doi-asserted-by":"crossref","unstructured":"Xiu, P., Baird, H.S.: Towards whole-book recognition. In: The Eighth IAPR International Workshop on Document Analysis Systems, DAS 2008, pp. 629\u2013636. IEEE (2008)","DOI":"10.1109\/DAS.2008.50"},{"key":"29_CR10","first-page":"993","volume":"3","author":"DM Blei","year":"2003","unstructured":"Blei, D.M., Ng, A.Y., Jordan, M.I.: Latent dirichlet allocation. J. Mach. Learn. Res. 3, 993\u20131022 (2003)","journal-title":"J. Mach. Learn. Res."},{"issue":"7","key":"29_CR11","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":"29_CR12","doi-asserted-by":"crossref","unstructured":"Neumann, L., Matas, J.: On combining multiple segmentations in scene text recognition. In: 2013 12th International Conference on Document Analysis and Recognition, pp. 523\u2013527. IEEE (2013)","DOI":"10.1109\/ICDAR.2013.110"},{"key":"29_CR13","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, Heidelberg (2014). doi: 10.1007\/978-3-319-10593-2_34"},{"key":"29_CR14","doi-asserted-by":"crossref","unstructured":"Bissacco, A., Cummins, M., Netzer, Y., Neven, H.: Photoocr: reading text in uncontrolled conditions. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 785\u2013792 (2013)","DOI":"10.1109\/ICCV.2013.102"},{"key":"29_CR15","doi-asserted-by":"crossref","unstructured":"Mishra, A., Alahari, K., Jawahar, C.: Top-down and bottom-up cues for scene text recognition. In: 2012 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 2687\u20132694. IEEE (2012)","DOI":"10.1109\/CVPR.2012.6247990"},{"key":"29_CR16","doi-asserted-by":"crossref","unstructured":"Milyaev, S., Barinova, O., Novikova, T., Kohli, P., Lempitsky, V.: Image binarization for end-to-end text understanding in natural images. In: 2013 12th International Conference on Document Analysis and Recognition, pp. 128\u2013132. IEEE (2013)","DOI":"10.1109\/ICDAR.2013.33"},{"key":"29_CR17","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"157","DOI":"10.1007\/978-3-319-16631-5_12","volume-title":"Computer Vision - ACCV 2014 Workshops","author":"L G\u00f3mez","year":"2015","unstructured":"G\u00f3mez, L., Karatzas, D.: Scene text recognition: no country for old\u00a0men? In: Jawahar, C.V., Shan, S. (eds.) ACCV 2014. LNCS, vol. 9009, pp. 157\u2013168. Springer, Heidelberg (2015). doi: 10.1007\/978-3-319-16631-5_12"},{"key":"29_CR18","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"494","DOI":"10.1007\/978-3-319-16865-4_32","volume-title":"Computer Vision \u2013 ACCV 2014","author":"U Roy","year":"2015","unstructured":"Roy, U., Mishra, A., Alahari, K., Jawahar, C.V.: Scene text recognition and retrieval for large lexicons. In: Cremers, D., Reid, I., Saito, H., Yang, M.-H. (eds.) ACCV 2014. LNCS, vol. 9003, pp. 494\u2013508. Springer, Heidelberg (2015). doi: 10.1007\/978-3-319-16865-4_32"},{"key":"29_CR19","doi-asserted-by":"crossref","unstructured":"Movshovitz-Attias, Y., Yu, Q., Stumpe, M.C., Shet, V., Arnoud, S., Yatziv, L.: Ontological supervision for fine grained classification of street view storefronts. In: 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 1693\u20131702. IEEE (2015)","DOI":"10.1109\/CVPR.2015.7298778"},{"key":"29_CR20","unstructured":"Feng, Y., Lapata, M.: Topic models for image annotation and text illustration. In: Human Language Technologies: The 2010 Annual Conference of the North American Chapter of the Association for Computational Linguistics, Association for Computational Linguistics, pp. 831\u2013839 (2010)"},{"key":"29_CR21","doi-asserted-by":"crossref","unstructured":"Papadimitriou, C.H., Tamaki, H., Raghavan, P., Vempala, S.: Latent semantic indexing: a probabilistic analysis. In: Proceedings of the Seventeenth ACM SIGACT-SIGMOD-SIGART Symposium on Principles of Database Systems, pp. 159\u2013168. ACM (1998)","DOI":"10.1145\/275487.275505"},{"key":"29_CR22","doi-asserted-by":"crossref","unstructured":"Fei-Fei, L., Perona, P.: A bayesian hierarchical model for learning natural scene categories. In: 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR 2005). vol. 2, pp. 524\u2013531. IEEE (2005)","DOI":"10.1109\/CVPR.2005.16"},{"key":"29_CR23","doi-asserted-by":"crossref","unstructured":"Zhang, D., Luo, T., Wang, D., Liu, R.: Learning from lda using deep neural networks. arXiv preprint arXiv:1508.01011 (2015)","DOI":"10.1007\/978-3-319-50496-4_59"},{"key":"29_CR24","unstructured":"Hinton, G., Vinyals, O., Dean, J.: Distilling the knowledge in a neural network. arXiv preprint arXiv:1503.02531 (2015)"},{"key":"29_CR25","doi-asserted-by":"crossref","unstructured":"Szegedy, C., Vanhoucke, V., Ioffe, S., Shlens, J., Wojna, Z.: Rethinking the inception architecture for computer vision. arXiv preprint arXiv:1512.00567 (2015)","DOI":"10.1109\/CVPR.2016.308"},{"key":"29_CR26","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"740","DOI":"10.1007\/978-3-319-10602-1_48","volume-title":"Computer Vision \u2013 ECCV 2014","author":"T-Y Lin","year":"2014","unstructured":"Lin, T.-Y., Maire, M., Belongie, S., Hays, J., Perona, P., Ramanan, D., Doll\u00e1r, P., Zitnick, C.L.: Microsoft COCO: common objects in context. In: Fleet, D., Pajdla, T., Schiele, B., Tuytelaars, T. (eds.) ECCV 2014. LNCS, vol. 8693, pp. 740\u2013755. Springer, Heidelberg (2014). doi: 10.1007\/978-3-319-10602-1_48"},{"key":"29_CR27","unstructured":"Veit, A., Matera, T., Neumann, L., Matas, J., Belongie, S.: Coco-text: Dataset and benchmark for text detection and recognition in natural images. arXiv preprint. arXiv:1601.07140 (2016)"},{"key":"29_CR28","unstructured":"Rehurek, R., Sojka, P.: Software framework for topic modelling with large corpora. In: Proceedings of the LREC 2010 Workshop on New Challenges for NLP Frameworks (2010)"},{"key":"29_CR29","unstructured":"Abadi, M., Agarwal, A., Barham, P., Brevdo, E., Chen, Z., Citro, C., Corrado, G.S., Davis, A., Dean, J., Devin, M., et al.: Tensorflow: Large-scale machine learning on heterogeneous distributed systems. arXiv preprint arXiv:1603.04467 (2016)"}],"container-title":["Lecture Notes in Computer Science","Computer Vision \u2013 ECCV 2016 Workshops"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-319-46604-0_29","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,10]],"date-time":"2025-06-10T19:35:42Z","timestamp":1749584142000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/978-3-319-46604-0_29"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2016]]},"ISBN":["9783319466033","9783319466040"],"references-count":29,"URL":"https:\/\/doi.org\/10.1007\/978-3-319-46604-0_29","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2016]]},"assertion":[{"value":"18 September 2016","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":"Amsterdam","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"The Netherlands","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2016","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"8 October 2016","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"16 October 2016","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":"eccv2016","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"http:\/\/www.eccv2016.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"}]}}