{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,2]],"date-time":"2026-01-02T07:39:41Z","timestamp":1767339581983},"reference-count":59,"publisher":"Springer Science and Business Media LLC","issue":"3","license":[{"start":{"date-parts":[[2014,12,23]],"date-time":"2014-12-23T00:00:00Z","timestamp":1419292800000},"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":["Int J Comput Vis"],"published-print":{"date-parts":[[2015,7]]},"DOI":"10.1007\/s11263-014-0793-6","type":"journal-article","created":{"date-parts":[[2014,12,22]],"date-time":"2014-12-22T13:57:03Z","timestamp":1419256623000},"page":"193-207","update-policy":"http:\/\/dx.doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":74,"title":["Label Embedding: A Frugal Baseline for Text Recognition"],"prefix":"10.1007","volume":"113","author":[{"given":"Jose A.","family":"Rodriguez-Serrano","sequence":"first","affiliation":[]},{"given":"Albert","family":"Gordo","sequence":"additional","affiliation":[]},{"given":"Florent","family":"Perronnin","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2014,12,23]]},"reference":[{"key":"793_CR1","doi-asserted-by":"crossref","unstructured":"Almaz\u00e1n, J., Gordo, A., Forn\u00e9s, A., & Valveny, E. (2013). Handwritten word spotting with corrected attributes. In ICCV.","DOI":"10.1109\/ICCV.2013.130"},{"key":"793_CR2","doi-asserted-by":"crossref","unstructured":"Almaz\u00e1n, J., Gordo, A., Forn\u00e9s, A., & Valveny, E. (2014). Word spotting and recognition with embedded attributes. IEEE Transactions on Pattern Analysis and Machine Intelligence, 36(12), 2552\u20132566.","DOI":"10.1109\/TPAMI.2014.2339814"},{"key":"793_CR3","doi-asserted-by":"crossref","unstructured":"Bai, B., Weston, J., Grangier, D., Collobert, R., Chapelle, O., & Weinberger, K. (2009). Supervised semantic indexing. In CIKM.","DOI":"10.1145\/1645953.1645979"},{"issue":"6","key":"793_CR4","doi-asserted-by":"crossref","first-page":"495","DOI":"10.1109\/34.771314","volume":"21","author":"I Bazzi","year":"1999","unstructured":"Bazzi, I., Schwartz, R., & Makhoul, J. (1999). An omnifont open-vocabulary ocr system for english and arabic. IEEE Transactions on Pattern Analysis and Machine Intelligence, 21(6), 495\u2013504.","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"key":"793_CR5","doi-asserted-by":"crossref","unstructured":"Bishop, C. (1995) Training with noise is equivalent to Tikhonov regularization. Neural Computation.","DOI":"10.1162\/neco.1995.7.1.108"},{"key":"793_CR6","volume-title":"Pattern recognition and machine learning","author":"CM Bishop","year":"2006","unstructured":"Bishop, C. M. (2006). Pattern recognition and machine learning. New York: Springer."},{"key":"793_CR7","doi-asserted-by":"crossref","unstructured":"Bissacco, A., Cummins, M., Netzer, Y., & Neven, H. (2013) Photoocr: Reading text in uncontrolled conditions. In ICCV.","DOI":"10.1109\/ICCV.2013.102"},{"key":"793_CR8","first-page":"103","volume-title":"Handwritten address recognition using hidden markov models. Reading and Learning","author":"A Brakensiek","year":"2004","unstructured":"Brakensiek, A., & Rigoll, G. (2004). Handwritten address recognition using hidden markov models. Reading and Learning (pp. 103\u2013122). Berlin: Springer."},{"key":"793_CR9","unstructured":"Brakensiek, A., Rottland, J., Kosmala, A., & Rigoll, G. (2000). Off-line handwriting recognition using various hybrid modeling techniques and character n-grams. In ICFHR."},{"key":"793_CR10","doi-asserted-by":"crossref","unstructured":"Breuel, T. M. (2001). Segmentation of handprinted letter strings using a dynamic programming algorithm. In ICDAR.","DOI":"10.1109\/ICDAR.2001.953902"},{"issue":"9","key":"793_CR11","doi-asserted-by":"crossref","first-page":"1399","DOI":"10.1016\/0031-3203(95)00013-P","volume":"28","author":"H Bunke","year":"1995","unstructured":"Bunke, H., Roth, M., & Schukat-Talamazzini, E. G. (1995). Off-line cursive handwriting recognition using hidden Markov models. Pattern Recognition, 28(9), 1399\u20131413.","journal-title":"Pattern Recognition"},{"issue":"3","key":"793_CR12","doi-asserted-by":"crossref","first-page":"291","DOI":"10.1016\/S0734-189X(87)80183-4","volume":"39","author":"GL Cash","year":"1987","unstructured":"Cash, G. L., & Hatamian, M. (1987). Optical character recognition by the method of moments. Computer Vision, Graphics, and Image Processing, 39(3), 291\u2013310.","journal-title":"Computer Vision, Graphics, and Image Processing"},{"key":"793_CR13","doi-asserted-by":"crossref","unstructured":"Chatfield, K., Lempitsky, V., Vedaldi, A., & Zisserman, A. (2011). The devil is in the details: an evaluation of recent feature encoding methods. In BMVC.","DOI":"10.5244\/C.25.76"},{"issue":"5","key":"793_CR14","doi-asserted-by":"crossref","first-page":"481","DOI":"10.1109\/34.291449","volume":"16","author":"MY Chen","year":"1994","unstructured":"Chen, M. Y., Kundu, A., & Zhou, J. (1994). Off-line handwritten word recognition using a hidden Markov model type stochastic network. IEEE Transactions on Pattern Analysis and Machine Intelligence, 16(5), 481\u2013496. doi: 10.1109\/34.291449 .","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"key":"793_CR15","unstructured":"Csurka, G., Dance, C., Fan, L., Willamowski, J., & Bray, C. (2004) Visual categorization with bags of keypoints. In ECCV SLCV workshop."},{"key":"793_CR16","doi-asserted-by":"crossref","unstructured":"Dutta, S., Sankaran, N., Sankar, K. P., & Jawahar, C. V. (2012). Robust recognition of degraded documents using character n-grams. In DAS.","DOI":"10.1109\/DAS.2012.76"},{"issue":"8","key":"793_CR17","doi-asserted-by":"crossref","first-page":"752","DOI":"10.1109\/34.784288","volume":"21","author":"A El-Yacoubi","year":"1999","unstructured":"El-Yacoubi, A., Sabourin, R., Suen, C. Y., & Gilloux, M. (1999). An HMM-based approach for off-line unconstrained handwritten word modeling and recognition. IEEE Transactions on Pattern Analysis and Machine Intelligence, 21(8), 752\u2013760.","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"key":"793_CR18","unstructured":"Hinton, G., Srivastava, N., Krizhevsky, A., Sutskever, I., & Salakhutdinov, R. (2012). Improving neural networks by preventing co-adaptation of feature detectors. arXiv."},{"key":"793_CR19","doi-asserted-by":"crossref","unstructured":"Jain, R. & Jawahar, C. (2010). Towards more effective distance functions for word image matching. In DAS (pp. 363\u2013370). ACM.","DOI":"10.1145\/1815330.1815377"},{"issue":"9","key":"793_CR20","doi-asserted-by":"crossref","first-page":"1704","DOI":"10.1109\/TPAMI.2011.235","volume":"34","author":"H J\u00e9gou","year":"2012","unstructured":"J\u00e9gou, H., Perronnin, F., Douze, M., S\u00e1nchez, J., P\u00e9rez, P., & Schmid, C. (2012). Aggregating local image descriptors into compact codes. IEEE Transactions on Pattern Analysis and Machine Intelligence, 34(9), 1704\u20131716.","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"key":"793_CR21","doi-asserted-by":"crossref","unstructured":"Joachims, T. (2002). Optimizing search engines using clickthrough data. In SIGKDD.","DOI":"10.1145\/775047.775067"},{"key":"793_CR22","unstructured":"Kedem, D., Tyree, S., Sha, F., Lanckriet, G. R., & Weinberger, K. Q. (2012). Non-linear metric learning. In NIPS."},{"issue":"3","key":"793_CR23","doi-asserted-by":"crossref","first-page":"404","DOI":"10.1006\/cviu.1998.0685","volume":"70","author":"S Knerr","year":"1998","unstructured":"Knerr, S., Augustin, E., Baret, O., & Price, D. (1998). Hidden Markov model based word recognition and its application to legal amount reading on French checks. Computer Vision and Image Understanding, 70(3), 404\u2013419.","journal-title":"Computer Vision and Image Understanding"},{"issue":"2","key":"793_CR24","doi-asserted-by":"crossref","first-page":"97","DOI":"10.1007\/s10044-002-0169-3","volume":"6","author":"AL Koerich","year":"2003","unstructured":"Koerich, A. L., Sabourin, R., & Suen, C. Y. (2003). Large vocabulary off-line handwriting recognition: A survey. Pattern Analysis and Applications, 6(2), 97\u2013121.","journal-title":"Pattern Analysis and Applications"},{"key":"793_CR25","unstructured":"Larochelle, H., Erhan, D., & Bengio, Y. (2008). Zero-data learning of new tasks. In AAAI."},{"key":"793_CR26","doi-asserted-by":"crossref","unstructured":"Lazebnik, S., Schmid, C., & Ponce, J. (2006). Beyond bags of features: Spatial pyramid matching for recognizing natural scene categories. In CVPR.","DOI":"10.1109\/CVPR.2006.68"},{"key":"793_CR27","volume-title":"Neural networks: Tricks of the trade","author":"Y LeCun","year":"1998","unstructured":"LeCun, Y., Bottou, L., Orr, G., & Muller, K. (1998). Efficient backprop. In G. Orr & K. Muller (Eds.), Neural networks: Tricks of the trade. New York: Springer."},{"key":"793_CR28","first-page":"419","volume":"2","author":"H Lodhi","year":"2002","unstructured":"Lodhi, H., Saunders, C., Shawe-Taylor, J., Cristianini, N., & Watkins, C. (2002). Text classification using string kernels. J. Mach. Learn. Res., 2, 419\u2013444.","journal-title":"J. Mach. Learn. Res."},{"issue":"2","key":"793_CR29","doi-asserted-by":"crossref","first-page":"91","DOI":"10.1023\/B:VISI.0000029664.99615.94","volume":"60","author":"D Lowe","year":"2004","unstructured":"Lowe, D. (2004). Distinctive image features from scale-invariant keypoints. International Journal of Computer Vision, 60(2), 91\u2013110.","journal-title":"International Journal of Computer Vision"},{"issue":"2","key":"793_CR30","doi-asserted-by":"crossref","first-page":"149","DOI":"10.1109\/34.908966","volume":"23","author":"S Madhvanath","year":"2001","unstructured":"Madhvanath, S., & Govindaraju, V. (2001). The role of holistic paradigms in handwritten word recognition. IEEE Transactions on Pattern Analysis and Machine Intelligence, 23(2), 149\u2013164.","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"key":"793_CR31","doi-asserted-by":"crossref","first-page":"65","DOI":"10.1142\/S0218001401000848","volume":"15","author":"UV Marti","year":"2001","unstructured":"Marti, U. V., & Bunke, H. (2001). Using a statistical language model to improve the performance of an HMM-based cursive handwriting recognition system. International Journal of Pattern Recognition and Artificial Intelligence, 15, 65\u201390.","journal-title":"International Journal of Pattern Recognition and Artificial Intelligence"},{"key":"793_CR32","doi-asserted-by":"crossref","unstructured":"Mensink, T., Verbeek, J., Perronnin, F., & Csurka, G. (2012). Metric learning for large scale image classification: Generalizing to new classes at near-zero cost. In ECCV.","DOI":"10.1007\/978-3-642-33709-3_35"},{"key":"793_CR33","unstructured":"Mikolov, T., Sutskever, I., Chen, K., Corrado, G., & Dean, J. (2013). Distributed representations of words and phrases and their compositionality. In NIPS."},{"key":"793_CR34","doi-asserted-by":"crossref","unstructured":"Mishra, A., Alahari, K., & Jawahar, C. V. (2012). Scene text recognition using higher order language priors. In BMVC.","DOI":"10.5244\/C.26.127"},{"key":"793_CR35","doi-asserted-by":"crossref","unstructured":"Mishra, A., Alahari, K., & Jawahar, C. V. (2012). Top-down and bottom-up cues for scene text recognition. In CVPR.","DOI":"10.1109\/CVPR.2012.6247990"},{"issue":"5","key":"793_CR36","doi-asserted-by":"crossref","first-page":"548","DOI":"10.1109\/34.494644","volume":"18","author":"MA Mohamed","year":"1996","unstructured":"Mohamed, M. A., & Gader, P. D. (1996). Handwritten word recognition using segmentation-free hidden Markov modeling and segmentation-based dynamic programming techniques. IEEE Transactions on Pattern Analysis and Machine Intelligence, 18(5), 548\u2013554. doi: 10.1109\/34.494644 .","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"key":"793_CR37","volume-title":"Optical character recognition","author":"S Mori","year":"1999","unstructured":"Mori, S., Nishida, H., & Yamada, H. (1999). Optical character recognition. New York: Wiley."},{"issue":"1","key":"793_CR38","doi-asserted-by":"crossref","first-page":"38","DOI":"10.1109\/34.824820","volume":"22","author":"G Nagy","year":"2000","unstructured":"Nagy, G. (2000). Twenty years of document image analysis in pami. IEEE Transactions on Pattern Analysis and Machine Intelligence, 22(1), 38\u201362.","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"key":"793_CR39","doi-asserted-by":"crossref","unstructured":"Neumann, L., & Matas, J. (2012). Real-time scene text localization and recognition. In CVPR.","DOI":"10.1109\/CVPR.2012.6248097"},{"key":"793_CR40","doi-asserted-by":"crossref","unstructured":"Novikova, T., Barinova, O., Kohli, P., & Lempitsky, V. (2012). Large-lexicon attribute-consistent text recognition in natural images. In ECCV.","DOI":"10.1007\/978-3-642-33783-3_54"},{"key":"793_CR41","unstructured":"Nowozin, S., & Lampert, C. (2011). Structured learning and prediction in computer vision. Foundations and trends in computer graphics and vision."},{"key":"793_CR42","doi-asserted-by":"crossref","unstructured":"Perronnin, F., & Dance, C. (2007). Fisher kernels on visual vocabularies for image categorization. In CVPR.","DOI":"10.1109\/CVPR.2007.383266"},{"key":"793_CR43","doi-asserted-by":"crossref","unstructured":"Perronnin, F., Liu, Y., S\u00e1nchez, J., & Poirier, H. (2010). Large-scale image retrieval with compressed Fisher vectors. In CVPR.","DOI":"10.1109\/CVPR.2010.5540009"},{"key":"793_CR44","doi-asserted-by":"crossref","unstructured":"Perronnin, F., S\u00e1nchez, J., & Liu, Y. (2010). Large-scale image categorization with explicit data embedding. In CVPR.","DOI":"10.1109\/CVPR.2010.5539914"},{"key":"793_CR45","doi-asserted-by":"crossref","unstructured":"Perronnin, F., S\u00e1nchez, J., & Mensink, T. (2010). Improving the Fisher kernel for large-scale image classification. In ECCV.","DOI":"10.1007\/978-3-642-15561-1_11"},{"key":"793_CR46","doi-asserted-by":"crossref","unstructured":"Rath, T. M., & Manmatha, R. (2003). Word image matching using dynamic time warping. In CVPR.","DOI":"10.1109\/CVPR.2003.1211511"},{"issue":"11","key":"793_CR47","doi-asserted-by":"crossref","first-page":"2108","DOI":"10.1109\/TPAMI.2012.25","volume":"34","author":"JA Rodr\u00edguez-Serrano","year":"2012","unstructured":"Rodr\u00edguez-Serrano, J. A., & Perronnin, F. (2012). A model-based sequence similarity with application to handwritten word spotting. IEEE Transactions on Pattern Analysis and Machine Intelligence, 34(11), 2108\u20132120.","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"key":"793_CR48","unstructured":"Rodriguez-Serrano, J. A., & Perronnin, F. (2013). Label embedding for text recognition. In BMVC."},{"key":"793_CR49","doi-asserted-by":"crossref","unstructured":"Rodr\u00edguez-Serrano, J. A., Sandhawalia, H., Bala, R., Perronnin, F., & Saunders, C. (2012). Data-driven vehicle identification by image matching. In ECCV Workshop on Computer Vision for Vehicle Technology.","DOI":"10.1007\/978-3-642-33868-7_53"},{"key":"793_CR50","doi-asserted-by":"crossref","unstructured":"Sankar, K., Manmatha, R., Jawahar, C. V., & Manmatha, R. (2010). Nearest neighbor based collection ocr. In DAS.","DOI":"10.1145\/1815330.1815357"},{"key":"793_CR51","doi-asserted-by":"crossref","unstructured":"Sch\u00f6lkopf, B., Smola, A., & M\u00fcller, K. R. (1998). Non-linear component analysis as a kernel eigenvalue problem. In Neural Computation.","DOI":"10.1162\/089976698300017467"},{"issue":"3","key":"793_CR52","doi-asserted-by":"crossref","first-page":"309","DOI":"10.1109\/34.667887","volume":"20","author":"AW Senior","year":"1998","unstructured":"Senior, A. W., & Robinson, A. J. (1998). An off-line cursive handwriting recognition system. IEEE Transactions on Pattern Analysis and Machine Intelligence, 20(3), 309\u2013321. doi: 10.1109\/34.667887 .","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"issue":"6","key":"793_CR53","doi-asserted-by":"crossref","first-page":"709","DOI":"10.1109\/TPAMI.2004.14","volume":"26","author":"A Vinciarelli","year":"2004","unstructured":"Vinciarelli, A., Bengio, S., & Bunke, H. (2004). Offline recognition of unconstrained handwritten texts using HMMs and statistical language models. IEEE Transactions on Pattern Analysis and Machine Intelligence, 26(6), 709\u2013720.","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"key":"793_CR54","unstructured":"Wang, K., Babenko, B., & Belongie, S. (2011). End-to-end scene text recognition. In ICCV."},{"key":"793_CR55","doi-asserted-by":"crossref","unstructured":"Wang, K., & Belongie, S. (2010). Word spotting in the wild. In ECCV.","DOI":"10.1007\/978-3-642-15549-9_43"},{"key":"793_CR56","unstructured":"Weston, J., Bengio, S., & Usunier, N. (2010). Learning to rank with joint word-image embeddings. ECML: Large scale image annotation."},{"key":"793_CR57","unstructured":"Williams, C., & Seeger, M. (2001). Using the Nystr\u00f6m method to speed up kernel machines. In NIPS."},{"key":"793_CR58","doi-asserted-by":"crossref","unstructured":"Yao, C., Bai, X., Shi, B., & Liu, W. (2014). Strokelets: A learned multi-scale representation for scene text recognition. In CVPR.","DOI":"10.1109\/CVPR.2014.515"},{"issue":"5","key":"793_CR59","doi-asserted-by":"crossref","first-page":"818","DOI":"10.1109\/TPAMI.2006.103","volume":"28","author":"M Zimmermann","year":"2006","unstructured":"Zimmermann, M., Chappelier, J. C., & Bunke, H. (2006). Offline grammar-based recognition of handwritten sentences. IEEE Transactions on Pattern Analysis and Machine Intelligence, 28(5), 818\u2013821.","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"}],"container-title":["International Journal of Computer Vision"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s11263-014-0793-6.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/article\/10.1007\/s11263-014-0793-6\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s11263-014-0793-6","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2019,8,18]],"date-time":"2019-08-18T17:57:47Z","timestamp":1566151067000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/s11263-014-0793-6"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2014,12,23]]},"references-count":59,"journal-issue":{"issue":"3","published-print":{"date-parts":[[2015,7]]}},"alternative-id":["793"],"URL":"https:\/\/doi.org\/10.1007\/s11263-014-0793-6","relation":{},"ISSN":["0920-5691","1573-1405"],"issn-type":[{"value":"0920-5691","type":"print"},{"value":"1573-1405","type":"electronic"}],"subject":[],"published":{"date-parts":[[2014,12,23]]}}}