{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,5]],"date-time":"2026-03-05T03:12:44Z","timestamp":1772680364056,"version":"3.50.1"},"reference-count":68,"publisher":"Springer Science and Business Media LLC","issue":"4","license":[{"start":{"date-parts":[[2021,1,5]],"date-time":"2021-01-05T00:00:00Z","timestamp":1609804800000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2021,1,5]],"date-time":"2021-01-05T00:00:00Z","timestamp":1609804800000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61936003"],"award-info":[{"award-number":["61936003"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100003453","name":"Natural Science Foundation of Guangdong Province","doi-asserted-by":"publisher","award":["2017A030312006"],"award-info":[{"award-number":["2017A030312006"]}],"id":[{"id":"10.13039\/501100003453","id-type":"DOI","asserted-by":"publisher"}]},{"name":"the National Key Research and Development Program of China","award":["2016YFB1001405"],"award-info":[{"award-number":["2016YFB1001405"]}]},{"DOI":"10.13039\/501100012226","name":"Fundamental Research Funds for the Central Universities","doi-asserted-by":"publisher","award":["x2dxD2190570"],"award-info":[{"award-number":["x2dxD2190570"]}],"id":[{"id":"10.13039\/501100012226","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61771199"],"award-info":[{"award-number":["61771199"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Int J Comput Vis"],"published-print":{"date-parts":[[2021,4]]},"DOI":"10.1007\/s11263-020-01411-1","type":"journal-article","created":{"date-parts":[[2021,1,5]],"date-time":"2021-01-05T10:04:41Z","timestamp":1609841081000},"page":"960-976","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":34,"title":["Separating Content from Style Using Adversarial Learning for Recognizing Text in the Wild"],"prefix":"10.1007","volume":"129","author":[{"given":"Canjie","family":"Luo","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Qingxiang","family":"Lin","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yuliang","family":"Liu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5456-0957","authenticated-orcid":false,"given":"Lianwen","family":"Jin","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Chunhua","family":"Shen","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2021,1,5]]},"reference":[{"key":"1411_CR1","unstructured":"Arjovsky, M., Chintala, S., Bottou, L. (2017) Wasserstein generative adversarial networks. In: International Conference on Machine Learning (ICML), pp 214\u2013223."},{"key":"1411_CR2","doi-asserted-by":"crossref","unstructured":"Azadi, S., Fisher, M., Kim, VG., Wang, Z., Shechtman, E., Darrell, T. (2018) Multi-content gan for few-shot font style transfer. In: IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp 7564\u20137573.","DOI":"10.1109\/CVPR.2018.00789"},{"key":"1411_CR3","unstructured":"Bahdanau, D., Cho, K., Bengio, Y. (2015) Neural machine translation by jointly learning to align and translate. In: International Conference on Learning Representations (ICLR)."},{"key":"1411_CR4","doi-asserted-by":"crossref","unstructured":"Bai, F., Cheng, Z., Niu, Y., Pu, S., Zhou, S. (2018) Edit probability for scene text recognition. In: IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp 1508\u20131516.","DOI":"10.1109\/CVPR.2018.00163"},{"key":"1411_CR5","doi-asserted-by":"crossref","unstructured":"Bau, D., Zhu, JY., Wulff, J., Peebles, W., Strobelt, H., Zhou, B., Torralba, A. (2019) Seeing what a gan cannot generate. In: IEEE International Conference on Computer Vision (ICCV), pp 4502\u20134511.","DOI":"10.1109\/ICCV.2019.00460"},{"key":"1411_CR6","unstructured":"Berthelot, D., Schumm, T., Metz, L. (2017) BEGAN: boundary equilibrium generative adversarial networks. CoRR abs\/1703.10717."},{"key":"1411_CR7","doi-asserted-by":"crossref","unstructured":"Bissacco, A., Cummins, M., Netzer, Y., Neven, H. (2013) PhotoOCR: Reading text in uncontrolled conditions. In: IEEE International Conference on Computer Vision (ICCV), pp 785\u2013792.","DOI":"10.1109\/ICCV.2013.102"},{"issue":"7","key":"1411_CR8","doi-asserted-by":"publisher","first-page":"690","DOI":"10.1109\/34.506792","volume":"18","author":"RG Casey","year":"1996","unstructured":"Casey, R. G., & Lecolinet, E. (1996). A survey of methods and strategies in character segmentation. IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI), 18(7), 690\u2013706.","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI)"},{"key":"1411_CR9","doi-asserted-by":"publisher","first-page":"909","DOI":"10.1109\/TIP.2019.2936746","volume":"29","author":"MM Cheng","year":"2019","unstructured":"Cheng, M. M., Liu, X. C., Wang, J., Lu, S. P., Lai, Y. K., & Rosin, P. L. (2019). Structure-Preserving Neural Style Transfer. IEEE Transactions on Image Processing (TIP), 29, 909\u2013920.","journal-title":"IEEE Transactions on Image Processing (TIP)"},{"key":"1411_CR10","doi-asserted-by":"crossref","unstructured":"Cheng, Z., Bai, F., Xu, Y., Zheng, G., Pu, S., Zhou, S. (2017) Focusing attention: Towards accurate text recognition in natural images. In: IEEE International Conference on Computer Vision (ICCV), pp 5086\u20135094.","DOI":"10.1109\/ICCV.2017.543"},{"key":"1411_CR11","doi-asserted-by":"crossref","unstructured":"Cheng, Z., Xu, Y., Bai, F., Niu, Y., Pu, S., Zhou, S. (2018) AON: Towards arbitrarily-oriented text recognition. In: IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp 5571\u20135579.","DOI":"10.1109\/CVPR.2018.00584"},{"key":"1411_CR12","doi-asserted-by":"crossref","unstructured":"Cong, F., Hu, W., Huo, Q., Guo, L. (2019) A comparative study of attention-based encoder-decoder approaches to natural scene text recognition. In: International Conference on Document Analysis and Recognition (ICDAR), pp 916\u2013921.","DOI":"10.1109\/ICDAR.2019.00151"},{"key":"1411_CR13","doi-asserted-by":"crossref","unstructured":"Dalal, N., Triggs, B. (2005) Histograms of oriented gradients for human detection. In: IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp 886\u2013893.","DOI":"10.1109\/CVPR.2005.177"},{"key":"1411_CR14","doi-asserted-by":"crossref","unstructured":"Fang, S., Xie, H., Chen, J., Tan, J., Zhang, Y. (2019) Learning to draw text in natural images with conditional adversarial networks. In: International Joint Conferences on Artificial Intelligence (IJCAI).","DOI":"10.24963\/ijcai.2019\/101"},{"key":"1411_CR15","unstructured":"Goodfellow, I., Pouget-Abadie, J., Mirza, M., Xu, B., Warde-Farley, D., Ozair, S., Courville, A., Bengio, Y. (2014) Generative adversarial nets. Neural Information Processing Systems (NeurIPS), pp 2672\u20132680."},{"key":"1411_CR16","doi-asserted-by":"crossref","unstructured":"Gordo, A. (2015) Supervised mid-level features for word image representation. In: IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp 2956\u20132964.","DOI":"10.1109\/CVPR.2015.7298914"},{"key":"1411_CR17","doi-asserted-by":"crossref","unstructured":"Gupta, A., Vedaldi, A., Zisserman, A. (2016) Synthetic data for text localisation in natural images. In: IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp 2315\u20132324.","DOI":"10.1109\/CVPR.2016.254"},{"key":"1411_CR18","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., Sun, J. (2016a) Deep residual learning for image recognition. In: IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp 770\u2013778.","DOI":"10.1109\/CVPR.2016.90"},{"key":"1411_CR19","doi-asserted-by":"crossref","unstructured":"He, P., Huang, W., Qiao, Y., Loy, CC., Tang, X. (2016b) Reading scene text in deep convolutional sequences. In: AAAI Conference on Artificial Intelligence (AAAI), pp 3501\u20133508.","DOI":"10.1609\/aaai.v30i1.10465"},{"key":"1411_CR20","first-page":"6626","volume":"30","author":"M Heusel","year":"2017","unstructured":"Heusel, M., Ramsauer, H., Unterthiner, T., Nessler, B., & Hochreiter, S. (2017). Gans trained by a two time-scale update rule converge to a local nash equilibrium. Neural Information Processing Systems (NeurIPS), 30, 6626\u20136637.","journal-title":"Neural Information Processing Systems (NeurIPS)"},{"key":"1411_CR21","doi-asserted-by":"crossref","unstructured":"Isola, P., Zhu, JY., Zhou, T., Efros, AA. (2017) Image-to-image translation with conditional adversarial networks. In: IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp 5967\u20135976.","DOI":"10.1109\/CVPR.2017.632"},{"key":"1411_CR22","unstructured":"Jaderberg, M., Simonyan, K., Vedaldi, A., Zisserman, A. (2014a) Synthetic data and artificial neural networks for natural scene text recognition. Neural Information Processing Systems (NeurIPS) Deep Learning Workshop."},{"key":"1411_CR23","doi-asserted-by":"crossref","unstructured":"Jaderberg, M., Vedaldi, A., Zisserman, A. (2014b) Deep features for text spotting. In: European Conference on Computer Vision (ECCV), pp 512\u2013528.","DOI":"10.1007\/978-3-319-10593-2_34"},{"key":"1411_CR24","unstructured":"Jaderberg, M., Simonyan, K., Vedaldi, A., Zisserman, A. (2015) Deep structured output learning for unconstrained text recognition. In: International Conference on Learning Representations (ICLR)."},{"issue":"1","key":"1411_CR25","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. (2016). Reading text in the wild with convolutional neural networks. International Journal of Computer Vision (IJCV), 116(1), 1\u201320.","journal-title":"International Journal of Computer Vision (IJCV)"},{"issue":"11","key":"1411_CR26","doi-asserted-by":"publisher","first-page":"3365","DOI":"10.1109\/TVCG.2019.2921336","volume":"26","author":"Y Jing","year":"2019","unstructured":"Jing, Y., Yang, Y., Feng, Z., Ye, J., Yu, Y., & Song, M. (2019). Neural style transfer: A review. IEEE Transactions on Visualization and Computer Graphics (TVCG), 26(11), 3365\u20133385.","journal-title":"IEEE Transactions on Visualization and Computer Graphics (TVCG)"},{"key":"1411_CR27","doi-asserted-by":"crossref","unstructured":"Johnson, J., Alahi, A., Fei-Fei, L. (2016) Perceptual losses for real-time style transfer and super-resolution. In: European Conference on Computer Vision (ECCV), pp 694\u2013711.","DOI":"10.1007\/978-3-319-46475-6_43"},{"key":"1411_CR28","doi-asserted-by":"crossref","unstructured":"Karatzas, D., Shafait, F., Uchida, S., Iwamura, M, i\u00a0Bigorda, LG., Mestre, SR., Mas, J., Mota, DF., Almazan, JA., De\u00a0Las\u00a0Heras, LP. (2013) ICDAR 2013 robust reading competition. In: International Conference on Document Analysis and Recognition (ICDAR), pp 1484\u20131493.","DOI":"10.1109\/ICDAR.2013.221"},{"key":"1411_CR29","doi-asserted-by":"crossref","unstructured":"Karatzas, D., Gomez-Bigorda, L., Nicolaou, A., Ghosh, S., Bagdanov, A., Iwamura, M., Matas, J., Neumann, L., Chandrasekhar, VR., Lu, S., et\u00a0al. (2015) ICDAR 2015 competition on robust reading. In: International Conference on Document Analysis and Recognition (ICDAR), pp 1156\u20131160.","DOI":"10.1109\/ICDAR.2015.7333942"},{"key":"1411_CR30","unstructured":"Kingma, D., Ba, L., et\u00a0al. (2015) Adam: A method for stochastic optimization. In: International Conference on Learning Representations (ICLR)."},{"key":"1411_CR31","doi-asserted-by":"crossref","unstructured":"Lee, CY., Osindero, S. (2016) Recursive recurrent nets with attention modeling for OCR in the wild. In: IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp 2231\u20132239.","DOI":"10.1109\/CVPR.2016.245"},{"key":"1411_CR32","doi-asserted-by":"crossref","unstructured":"Li,H., Wang, P., Shen, C., Zhang, G. (2019) Show, attend and read: A simple and strong baseline for irregular text recognition. In: AAAI Conference on Artificial Intelligence (AAAI).","DOI":"10.1609\/aaai.v33i01.33018610"},{"key":"1411_CR33","unstructured":"Liao, M., Lyu, P., He, M., Yao, C., Wu, W., Bai, X. (2019a) Mask textspotter: An end-to-end trainable neural network for spotting text with arbitrary shapes. IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI)."},{"key":"1411_CR34","doi-asserted-by":"crossref","unstructured":"Liao, M., Zhang, J., Wan, Z., Xie, F., Liang, J., Lyu, P., Yao, C., Bai, X. (2019b) Scene text recognition from two-dimensional perspective. In: AAAI Conference on Artificial Intelligence (AAAI).","DOI":"10.1609\/aaai.v33i01.33018714"},{"key":"1411_CR35","doi-asserted-by":"crossref","unstructured":"Lin, TY., Dollar, P., Girshick, R., He, K., Hariharan, B., Belongie, S. (2017) Feature pyramid networks for object detection. In: IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp 2117\u20132125.","DOI":"10.1109\/CVPR.2017.106"},{"key":"1411_CR36","doi-asserted-by":"crossref","unstructured":"Liu, W., Chen, C., Wong, KYK., Su, Z., Han, J. (2016) STAR-Net: A spatial attention residue network for scene text recognition. In: British Machine Vision Conference (BMVC), pp 7\u20137.","DOI":"10.5244\/C.30.43"},{"key":"1411_CR37","doi-asserted-by":"crossref","unstructured":"Liu, W., Chen, C., Wong, KYK. (2018a) Char-net: A character-aware neural network for distorted scene text recognition. In: AAAI Conference on Artificial Intelligence (AAAI).","DOI":"10.1609\/aaai.v32i1.12246"},{"key":"1411_CR38","doi-asserted-by":"crossref","unstructured":"Liu, Y., Wang, Z., Jin, H., Wassell, I. (2018b) Synthetically supervised feature learning for scene text recognition. In: European Conference on Computer Vision (ECCV), pp 435\u2013451.","DOI":"10.1007\/978-3-030-01228-1_27"},{"key":"1411_CR39","doi-asserted-by":"crossref","unstructured":"Liu, Z., Li, Y., Ren ,F., Goh, WL., Yu, H. (2018c) SqueezedText: A real-time scene text recognition by binary convolutional encoder-decoder network. In: AAAI Conference on Artificial Intelligence (AAAI).","DOI":"10.1609\/aaai.v32i1.12252"},{"key":"1411_CR40","doi-asserted-by":"crossref","unstructured":"Lucas, SM., Panaretos, A., Sosa, L., Tang, A., Wong, S., Young, R. (2003) ICDAR 2003 robust reading competitions. In: International Conference on Document Analysis and Recognition (ICDAR), pp 682\u2013687.","DOI":"10.1109\/ICDAR.2003.1227749"},{"key":"1411_CR41","doi-asserted-by":"publisher","first-page":"109","DOI":"10.1016\/j.patcog.2019.01.020","volume":"90","author":"C Luo","year":"2019","unstructured":"Luo, C., Jin, L., & Sun, Z. (2019). MORAN: A multi-object rectified attention network for scene text recognition. Pattern Recognition, 90, 109\u2013118.","journal-title":"Pattern Recognition"},{"key":"1411_CR42","doi-asserted-by":"crossref","unstructured":"Mao, X., Li, Q., Xie, H., Lau, RY., Wang, Z., Smolley, SP. (2017). Least squares generative adversarial networks. In: IEEE International Conference on Computer Vision (ICCV), pp 2813\u20132821.","DOI":"10.1109\/ICCV.2017.304"},{"key":"1411_CR43","doi-asserted-by":"crossref","unstructured":"Mishra, A., Alahari, K., Jawahar, C. (2012). Scene text recognition using higher order language priors. In: British Machine Vision Conference (BMVC), pp 1\u201311.","DOI":"10.5244\/C.26.127"},{"key":"1411_CR44","doi-asserted-by":"crossref","unstructured":"Neumann, L., Matas, J. (2012). Real-time scene text localization and recognition. In: IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp 3538\u20133545.","DOI":"10.1109\/CVPR.2012.6248097"},{"key":"1411_CR45","unstructured":"Odena, A., Olah, C., Shlens, J. (2017). Conditional image synthesis with auxiliary classifier GANs. In: International Conference on Machine Learning (ICML), pp 2642\u20132651."},{"issue":"1","key":"1411_CR46","doi-asserted-by":"publisher","first-page":"62","DOI":"10.1109\/TSMC.1979.4310076","volume":"9","author":"N Otsu","year":"1979","unstructured":"Otsu, N. (1979). A threshold selection method from gray-level histograms. IEEE Transactions on Systems, Man, and Cybernetics (TSMC), 9(1), 62\u201366.","journal-title":"IEEE Transactions on Systems, Man, and Cybernetics (TSMC)"},{"key":"1411_CR47","unstructured":"Paszke, A., Gross, S., Chintala, S., Chanan, G., Yang, E., DeVito, Z., Lin, Z., Desmaison, A., Antiga, L., Lerer, A. (2017). Automatic differentiation in PyTorch. Neural Information Processing Systems (NeurIPS) Autodiff Workshop."},{"key":"1411_CR48","unstructured":"Quy\u00a0Phan, T., Shivakumara, P., Tian, S., Lim\u00a0Tan, C. (2013) Recognizing text with perspective distortion in natural scenes. In: IEEE International Conference on Computer Vision (ICCV), pp 569\u2013576."},{"issue":"18","key":"1411_CR49","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. (2014). A robust arbitrary text detection system for natural scene images. Expert Systems with Applications, 41(18), 8027\u20138048.","journal-title":"Expert Systems with Applications"},{"issue":"3","key":"1411_CR50","doi-asserted-by":"publisher","first-page":"193","DOI":"10.1007\/s11263-014-0793-6","volume":"113","author":"JA Rodriguez-Serrano","year":"2015","unstructured":"Rodriguez-Serrano, J. A., Gordo, A., & Perronnin, F. (2015). Label embedding: A frugal baseline for text recognition. International Journal of Computer Vision (IJCV), 113(3), 193\u2013207.","journal-title":"International Journal of Computer Vision (IJCV)"},{"key":"1411_CR51","unstructured":"Salimans, T., Goodfellow, I., Zaremba, W., Cheung, V., Radford, A., Chen, X. (2016). Improved techniques for training GANs. Neural Information Processing Systems (NeurIPS), pp 2234\u20132242."},{"key":"1411_CR52","doi-asserted-by":"crossref","unstructured":"Shi, B., Wang, X., Lyu, P., Yao, C., Bai, X. (2016). Robust scene text recognition with automatic rectification. In: IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp 4168\u20134176.","DOI":"10.1109\/CVPR.2016.452"},{"issue":"11","key":"1411_CR53","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. (2017). An end-to-end trainable neural network for image-based sequence recognition and its application to scene text recognition. IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI), 39(11), 2298\u20132304.","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI)"},{"key":"1411_CR54","doi-asserted-by":"publisher","first-page":"2035","DOI":"10.1109\/TPAMI.2018.2848939","volume":"41","author":"B Shi","year":"2018","unstructured":"Shi, B., Yang, M., Wang, X., Lyu, P., Yao, C., & Bai, X. (2018). ASTER: An attentional scene text recognizer with flexible rectification. IEEE Transactions on Pattern Analysis and Machine Intelligence, 41, 2035.","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"key":"1411_CR55","unstructured":"Su, B., Lu, S. (2014). Accurate scene text recognition based on recurrent neural network. In: Asian Conference on Computer Vision (ACCV), pp 35\u201348."},{"key":"1411_CR56","first-page":"3104","volume":"2","author":"I Sutskever","year":"2014","unstructured":"Sutskever, I., Vinyals, O., & Le, Q. V. (2014). Sequence to sequence learning with neural networks. Neural Information Processing Systems (NeurIPS), 2, 3104\u20133112.","journal-title":"Neural Information Processing Systems (NeurIPS)"},{"key":"1411_CR57","unstructured":"Wang, K., Babenko, B., Belongie, S. (2011). End-to-end scene text recognition. In: IEEE International Conference on Computer Vision (ICCV), pp 1457\u20131464."},{"key":"1411_CR58","unstructured":"Wang, T., Wu, DJ., Coates, A., Ng, AY. (2012). End-to-end text recognition with convolutional neural networks. In: IEEE International Conference on Pattern Recognition (ICPR), pp 3304\u20133308."},{"key":"1411_CR59","doi-asserted-by":"crossref","unstructured":"Wu, L., Zhang, C., Liu, J., Han, J., Liu, J., Ding, E., Bai, X. (2019). Editing text in the wild. In: ACM International Conference on Multimedia (ACM MM), pp 1500\u20131508.","DOI":"10.1145\/3343031.3350929"},{"key":"1411_CR60","doi-asserted-by":"crossref","unstructured":"Yang, M., Guan, Y., Liao, M., He, X., Bian, K., Bai, S., Yao, C., Bai, X. (2019a). Symmetry-constrained rectification network for scene text recognition. In: IEEE International Conference on Computer Vision (ICCV), pp 9147\u20139156.","DOI":"10.1109\/ICCV.2019.00924"},{"key":"1411_CR61","doi-asserted-by":"crossref","unstructured":"Yang, S., Wang, Z., Wang, Z., Xu, N., Liu, J., Guo, Z. (2019b). Controllable artistic text style transfer via shape-matching GAN. In: IEEE International Conference on Computer Vision (ICCV).","DOI":"10.1109\/ICCV.2019.00454"},{"key":"1411_CR62","doi-asserted-by":"crossref","unstructured":"Yang, X., He, D., Zhou, Z., Kifer, D., Giles, CL. (2017). Learning to read irregular text with attention mechanisms. In: International Joint Conferences on Artificial Intelligence (IJCAI), pp 3280\u20133286.","DOI":"10.24963\/ijcai.2017\/458"},{"key":"1411_CR63","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: IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp 4042\u20134049.","DOI":"10.1109\/CVPR.2014.515"},{"issue":"7","key":"1411_CR64","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. (2015). Text detection and recognition in imagery: A survey. IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI), 37(7), 1480\u20131500 .","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI)"},{"key":"1411_CR65","doi-asserted-by":"crossref","unstructured":"Zhan, F., Lu, S. (2019). ESIR: End-to-end scene text recognition via iterative image rectification. In: IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp 2059\u20132068.","DOI":"10.1109\/CVPR.2019.00216"},{"key":"1411_CR66","doi-asserted-by":"crossref","unstructured":"Zhang, Y., Nie, S., Liu, W., Xu, X., Zhang, D., Shen, HT. (2019). Sequence-to-sequence domain adaptation network for robust text image recognition. In: IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp 2740\u20132749.","DOI":"10.1109\/CVPR.2019.00285"},{"key":"1411_CR67","doi-asserted-by":"crossref","unstructured":"Zhu, JY., Park, T., Isola, P., Efros, AA. (2017). Unpaired Image-to-Image Translation Using Cycle-Consistent Adversarial Networks. In: IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp 2242\u20132251.","DOI":"10.1109\/ICCV.2017.244"},{"issue":"1","key":"1411_CR68","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. (2016). Scene text detection and recognition: Recent advances and future trends. Frontiers of Computer Science, 10(1), 19\u201336.","journal-title":"Frontiers of Computer Science"}],"container-title":["International Journal of Computer Vision"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s11263-020-01411-1.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/article\/10.1007\/s11263-020-01411-1\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s11263-020-01411-1.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,12,10]],"date-time":"2022-12-10T15:31:52Z","timestamp":1670686312000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/s11263-020-01411-1"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,1,5]]},"references-count":68,"journal-issue":{"issue":"4","published-print":{"date-parts":[[2021,4]]}},"alternative-id":["1411"],"URL":"https:\/\/doi.org\/10.1007\/s11263-020-01411-1","relation":{},"ISSN":["0920-5691","1573-1405"],"issn-type":[{"value":"0920-5691","type":"print"},{"value":"1573-1405","type":"electronic"}],"subject":[],"published":{"date-parts":[[2021,1,5]]},"assertion":[{"value":"19 December 2019","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"28 November 2020","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"5 January 2021","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}}]}}