{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,3]],"date-time":"2026-04-03T19:51:36Z","timestamp":1775245896073,"version":"3.50.1"},"publisher-location":"Cham","reference-count":37,"publisher":"Springer International Publishing","isbn-type":[{"value":"9783030012632","type":"print"},{"value":"9783030012649","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\/978-3-030-01264-9_43","type":"book-chapter","created":{"date-parts":[[2018,10,8]],"date-time":"2018-10-08T04:20:53Z","timestamp":1538972453000},"page":"728-744","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":34,"title":["Single Shot Scene Text Retrieval"],"prefix":"10.1007","author":[{"given":"Llu\u00eds","family":"G\u00f3mez","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Andr\u00e9s","family":"Mafla","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Mar\u00e7al","family":"Rusi\u00f1ol","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Dimosthenis","family":"Karatzas","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2018,10,9]]},"reference":[{"key":"43_CR1","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., et al.: 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, Cham (2014). https:\/\/doi.org\/10.1007\/978-3-319-10602-1_48"},{"key":"43_CR2","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)"},{"issue":"7553","key":"43_CR3","doi-asserted-by":"publisher","first-page":"436","DOI":"10.1038\/nature14539","volume":"521","author":"Yann LeCun","year":"2015","unstructured":"LeCun, Y., Bengio, Y., Hinton, G.: Deep learning. Nature 521(7553) (2015)","journal-title":"Nature"},{"key":"43_CR4","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: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 1693\u20131702 (2015)","DOI":"10.1109\/CVPR.2015.7298778"},{"issue":"8","key":"43_CR5","doi-asserted-by":"publisher","first-page":"3965","DOI":"10.1109\/TIP.2017.2707805","volume":"26","author":"S Karaoglu","year":"2017","unstructured":"Karaoglu, S., Tao, R., van Gemert, J.C., Gevers, T.: Con-text: text detection for fine-grained object classification. IEEE Trans. Image Process. 26(8), 3965\u20133980 (2017)","journal-title":"IEEE Trans. Image Process."},{"key":"43_CR6","doi-asserted-by":"crossref","unstructured":"Bai, X., Yang, M., Lyu, P., Xu, Y.: Integrating scene text and visual appearance for fine-grained image classification with convolutional neural networks. arXiv preprint arXiv:1704.04613 (2017)","DOI":"10.1109\/ACCESS.2018.2878899"},{"key":"43_CR7","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":"43_CR8","doi-asserted-by":"crossref","unstructured":"Redmon, J., Divvala, S., Girshick, R., Farhadi, A.: You only look once: unified, real-time object detection. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 779\u2013788 (2016)","DOI":"10.1109\/CVPR.2016.91"},{"key":"43_CR9","doi-asserted-by":"crossref","unstructured":"Redmon, J., Farhadi, A.: YOLO9000: better, faster, stronger. arXiv preprint arXiv:1612.08242 (2016)","DOI":"10.1109\/CVPR.2017.690"},{"issue":"12","key":"43_CR10","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":"43_CR11","doi-asserted-by":"crossref","unstructured":"Sudholt, S., Fink, G.A.: PHOCNET: a deep convolutional neural network for word spotting in handwritten documents. In: Proceedings of the IEEE International Conference on Frontiers in Handwriting Recognition, pp. 277\u2013282 (2016)","DOI":"10.1109\/ICFHR.2016.0060"},{"issue":"1","key":"43_CR12","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":"43_CR13","doi-asserted-by":"crossref","unstructured":"Gupta, A., Vedaldi, A., Zisserman, A.: Synthetic data for text localisation in natural images. In: Proceeding of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 2315\u20132324 (2016)","DOI":"10.1109\/CVPR.2016.254"},{"key":"43_CR14","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 the AAAI Conference on Artificial Intelligence, pp. 4161\u20134167 (2017)","DOI":"10.1609\/aaai.v31i1.11196"},{"key":"43_CR15","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":"43_CR16","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"},{"issue":"11","key":"43_CR17","doi-asserted-by":"publisher","first-page":"2298","DOI":"10.1109\/TPAMI.2016.2646371","volume":"39","author":"Baoguang 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) (2017)","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"key":"43_CR18","doi-asserted-by":"crossref","unstructured":"Buvsta, M., Neumann, L., Matas, J.: Deep TextSpotter: an end-to-end trainable scene text localization and recognition framework. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 2204\u20132212 (2017)","DOI":"10.1109\/ICCV.2017.242"},{"key":"43_CR19","doi-asserted-by":"crossref","unstructured":"Li, H., Wang, P., Shen, C.: Towards end-to-end text spotting with convolutional recurrent neural networks. arXiv preprint arXiv:1707.03985 (2017)","DOI":"10.1109\/ICCV.2017.560"},{"key":"43_CR20","doi-asserted-by":"crossref","unstructured":"Aldavert, D., Rusi\u00f1ol, M., Toledo, R., Llad\u00f3s, J.: Integrating visual and textual cues for query-by-string word spotting. In: Proceedings of the IEEE International Conference on Document Analysis and Recognition, pp. 511\u2013515 (2013)","DOI":"10.1109\/ICDAR.2013.108"},{"key":"43_CR21","doi-asserted-by":"crossref","unstructured":"Ghosh, S.K., Valveny, E.: Query by string word spotting based on character bi-gram indexing. In: Proceedings of the IEEE International Conference on Document Analysis and Recognition, pp. 881\u2013885 (2015)","DOI":"10.1109\/ICDAR.2015.7333888"},{"key":"43_CR22","unstructured":"Ren, S., He, K., Girshick, R., Sun, J.: Faster R-CNN: towards real-time object detection with region proposal networks. In: Proceedings of the International Conference on Neural Information Processing Systems, pp. 91\u201399 (2015)"},{"key":"43_CR23","doi-asserted-by":"crossref","unstructured":"Lang, K., Mitchell, T.: Newsgroup 20 dataset (1999)","DOI":"10.1177\/0170840699202010"},{"key":"43_CR24","doi-asserted-by":"crossref","unstructured":"Karatzas, D., et al.: ICDAR 2013 robust reading competition. In: Proceedings of the IEEE International Conference on Document Analysis and Recognition, pp. 1484\u20131493 (2013)","DOI":"10.1109\/ICDAR.2013.221"},{"key":"43_CR25","doi-asserted-by":"crossref","unstructured":"Karatzas, D., et al.: ICDAR 2015 competition on robust reading. In: Proceedings of the IEEE International Conference on Document Analysis and Recognition, pp. 1156\u20131160 (2015)","DOI":"10.1109\/ICDAR.2015.7333942"},{"key":"43_CR26","doi-asserted-by":"crossref","unstructured":"Wang, K., Babenko, B., Belongie, S.: End-to-end scene text recognition. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 1457\u20131464 (2011)","DOI":"10.1109\/ICCV.2011.6126402"},{"key":"43_CR27","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. In: CVPR (2018)","DOI":"10.1109\/CVPR.2018.00527"},{"key":"43_CR28","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 Conference on Computer Vision and Pattern Recognition, pp. 2963\u20132970 (2010)","DOI":"10.1109\/CVPR.2010.5540041"},{"key":"43_CR29","doi-asserted-by":"crossref","unstructured":"Mishra, A., Alahari, K., Jawahar, C.: Top-down and bottom-up cues for scene text recognition. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 2687\u20132694 (2012)","DOI":"10.1109\/CVPR.2012.6247990"},{"key":"43_CR30","doi-asserted-by":"crossref","unstructured":"Neumann, L., Matas, J.: Real-time scene text localization and recognition. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (2012)","DOI":"10.1109\/CVPR.2012.6248097"},{"key":"43_CR31","doi-asserted-by":"crossref","unstructured":"Ghosh, S.K., Gomez, L., Karatzas, D., Valveny, E.: Efficient indexing for query by string text retrieval. In: Proceedings of the IEEE International Conference on Document Analysis and Recognition, pp. 1236\u20131240 (2015)","DOI":"10.1109\/ICDAR.2015.7333961"},{"key":"43_CR32","unstructured":"Mishra, A.: Understanding Text in Scene Images. Ph.D. thesis, International Institute of Information Technology Hyderabad (2016)"},{"key":"43_CR33","doi-asserted-by":"publisher","first-page":"60","DOI":"10.1016\/j.patcog.2017.04.027","volume":"70","author":"L G\u00f3mez","year":"2017","unstructured":"G\u00f3mez, L., Karatzas, D.: TextProposals: a text-specific selective search algorithm for word spotting in the wild. Pattern Recogn. 70, 60\u201374 (2017)","journal-title":"Pattern Recogn."},{"key":"43_CR34","unstructured":"Jaderberg, M., Simonyan, K., Vedaldi, A., Zisserman, A.: Synthetic data and artificial neural networks for natural scene text recognition. arXiv preprint arXiv:1406.2227 (2014)"},{"key":"43_CR35","unstructured":"Bernhardsson, E.: ANNOY: approximate nearest neighbors in C++\/Python optimized for memory usage and loading\/saving to disk (2013)"},{"key":"43_CR36","unstructured":"Malkov, Y.A., Yashunin, D.: Efficient and robust approximate nearest neighbor search using hierarchical navigable small world graphs. arXiv:1603.09320 (2016)"},{"key":"43_CR37","unstructured":"Andoni, A., Indyk, P., Laarhoven, T., Razenshteyn, I., Schmidt, L.: Practical and optimal LSH for angular distance. In: NIPS (2015)"}],"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\/978-3-030-01264-9_43","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,3]],"date-time":"2026-04-03T18:53:46Z","timestamp":1775242426000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-030-01264-9_43"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2018]]},"ISBN":["9783030012632","9783030012649"],"references-count":37,"URL":"https:\/\/doi.org\/10.1007\/978-3-030-01264-9_43","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":"9 October 2018","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"This content has been made available to all.","name":"free","label":"Free to read"}]}}