{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,6,27]],"date-time":"2025-06-27T04:14:11Z","timestamp":1750997651762,"version":"3.41.0"},"publisher-location":"Cham","reference-count":27,"publisher":"Springer International Publishing","isbn-type":[{"type":"print","value":"9783319700892"},{"type":"electronic","value":"9783319700908"}],"license":[{"start":{"date-parts":[[2017,1,1]],"date-time":"2017-01-01T00:00:00Z","timestamp":1483228800000},"content-version":"unspecified","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2017]]},"DOI":"10.1007\/978-3-319-70090-8_19","type":"book-chapter","created":{"date-parts":[[2017,10,27]],"date-time":"2017-10-27T04:33:39Z","timestamp":1509078819000},"page":"180-189","source":"Crossref","is-referenced-by-count":3,"title":["End-to-End Chinese Image Text Recognition with Attention Model"],"prefix":"10.1007","author":[{"given":"Fenfen","family":"Sheng","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Chuanlei","family":"Zhai","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhineng","family":"Chen","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Bo","family":"Xu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2017,10,28]]},"reference":[{"issue":"1","key":"19_CR1","doi-asserted-by":"crossref","first-page":"38","DOI":"10.1109\/34.824820","volume":"22","author":"G Nagy","year":"2000","unstructured":"Nagy, G.: Twenty years of document image analysis in PAMI. IEEE Trans. Pattern Anal. Mach. Intell. 22(1), 38\u201362 (2000)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"issue":"1","key":"19_CR2","doi-asserted-by":"crossref","first-page":"91","DOI":"10.1007\/s10032-013-0208-1","volume":"17","author":"L Xu","year":"2014","unstructured":"Xu, L., Yin, F., Wang, Q.F., Liu, C.L.: An over-segmentation method for single-touching Chinese handwriting with learning-based filtering. Int. J. Doc. Anal. Recogn. (IJDAR) 17(1), 91\u2013104 (2014)","journal-title":"Int. J. Doc. Anal. Recogn. (IJDAR)"},{"key":"19_CR3","doi-asserted-by":"crossref","unstructured":"Saidane, Z., Garcia, C., Dugelay, J.L.: The image text recognition graph (iTRG). In: IEEE International Conference on Multimedia and Expo, ICME 2009, pp. 266\u2013269. IEEE (2009)","DOI":"10.1109\/ICME.2009.5202486"},{"key":"19_CR4","doi-asserted-by":"crossref","unstructured":"Bai, J., Chen, Z., Feng, B., Xu, B.: Chinese image text recognition on grayscale pixels. In: 2014 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 1380\u20131384. IEEE (2014)","DOI":"10.1109\/ICASSP.2014.6853823"},{"key":"19_CR5","doi-asserted-by":"publisher","first-page":"755","DOI":"10.1007\/s00138-017-0837-3","volume-title":"Machine Vision and Applications","author":"Y Song","year":"2017","unstructured":"Song, Y., Chen, J., Xie, H., Chen, Z., Gao, X., Chen, X.: Robust and parallel Uyghur text localization in complex background images. Machine Vision and Applications, vol. 28, pp. 755\u2013769. Springer, Heidelberg (2017). doi: 10.1007\/s00138-017-0837-3"},{"issue":"13","key":"19_CR6","doi-asserted-by":"crossref","first-page":"15083","DOI":"10.1007\/s11042-017-4538-8","volume":"76","author":"S Fang","year":"2017","unstructured":"Fang, S., Xie, H., Chen, Z., Zhu, S., Gu, X., Gao, X.: Detecting Uyghur text in complex background images with convolutional neural network. Multimedia Tools Appl. 76(13), 15083\u201315103 (2017)","journal-title":"Multimedia Tools Appl."},{"key":"19_CR7","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"},{"key":"19_CR8","doi-asserted-by":"publisher","first-page":"525","DOI":"10.1007\/978-981-10-3005-5_43","volume-title":"Chinese Conference on Pattern Recognition","author":"C Zhai","year":"2016","unstructured":"Zhai, C., Chen, Z., Li, J., Xu, B.: Chinese image text recognition with BLSTM-CTC: a segmentation-free method. In: Tan, T., Li, X., Chen, X., Zhou, J., Yang, J., Cheng, H. (eds.) Chinese Conference on Pattern Recognition, pp. 525\u2013536. Springer, Singapore (2016). doi: 10.1007\/978-981-10-3005-5_43"},{"key":"19_CR9","unstructured":"Bahdanau, D., Cho, K., Bengio, Y.: Neural machine translation by jointly learning to align and translate. arXiv preprint arXiv:1409.0473 (2014)"},{"key":"19_CR10","doi-asserted-by":"crossref","unstructured":"Mishra, A., Alahari, K., Jawahar, C.: An MRF model for binarization of natural scene text. In: 2011 International Conference on Document Analysis and Recognition (ICDAR), pp. 11\u201316. IEEE (2011)","DOI":"10.1109\/ICDAR.2011.12"},{"key":"19_CR11","doi-asserted-by":"crossref","unstructured":"Bai, J., Feng, B., Xu, B.: Binarization of natural scene text based on L1-Norm PCA. In: 2013 IEEE International Conference on Multimedia and Expo Workshops (ICMEW), pp. 1\u20134. IEEE (2013)","DOI":"10.1109\/ICMEW.2013.6618244"},{"key":"19_CR12","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"209","DOI":"10.1007\/978-3-319-11179-7_27","volume-title":"Artificial Neural Networks and Machine Learning \u2013 ICANN 2014","author":"J Bai","year":"2014","unstructured":"Bai, J., Chen, Z., Feng, B., Xu, B.: Chinese image character recognition using DNN and machine simulated training samples. In: Wermter, S., Weber, C., Duch, W., Honkela, T., Koprinkova-Hristova, P., Magg, S., Palm, G., Villa, A.E.P. (eds.) ICANN 2014. LNCS, vol. 8681, pp. 209\u2013216. Springer, Cham (2014). doi: 10.1007\/978-3-319-11179-7_27"},{"key":"19_CR13","doi-asserted-by":"crossref","unstructured":"Bai, J., Chen, Z., Feng, B., Xu, B.: Image character recognition using deep convolutional neural network learned from different languages. In: 2014 IEEE International Conference on Image Processing (ICIP), pp. 2560\u20132564. IEEE (2014)","DOI":"10.1109\/ICIP.2014.7025518"},{"key":"19_CR14","doi-asserted-by":"crossref","unstructured":"Zhong, Z., Jin, L., Feng, Z.: Multi-font printed Chinese character recognition using multi-pooling convolutional neural network. In: 2015 13th International Conference on Document Analysis and Recognition (ICDAR), pp. 96\u2013100. IEEE (2015)","DOI":"10.1109\/ICDAR.2015.7333733"},{"key":"19_CR15","unstructured":"Ren, X., Chen, K., Sun, J.: A CNN based scene Chinese text recognition algorithm with synthetic data engine. arXiv preprint arXiv:1604.01891 (2016)"},{"key":"19_CR16","doi-asserted-by":"crossref","unstructured":"Messina, R., Louradour, J.: Segmentation-free handwritten Chinese text recognition with LSTM-RNN. In: 2015 13th International Conference on Document Analysis and Recognition (ICDAR), pp. 171\u2013175. IEEE (2015)","DOI":"10.1109\/ICDAR.2015.7333746"},{"issue":"11","key":"19_CR17","doi-asserted-by":"crossref","first-page":"1875","DOI":"10.1109\/TMM.2015.2477044","volume":"17","author":"K Cho","year":"2015","unstructured":"Cho, K., Courville, A., Bengio, Y.: Describing multimedia content using attention-based encoder-decoder networks. IEEE Trans. Multimedia 17(11), 1875\u20131886 (2015)","journal-title":"IEEE Trans. Multimedia"},{"key":"19_CR18","unstructured":"Xu, K., Ba, J., Kiros, R., Cho, K., Courville, A., Salakhudinov, R., Zemel, R., Bengio, Y.: Show, attend and tell: neural image caption generation with visual attention. In: International Conference on Machine Learning, pp. 2048\u20132057 (2015)"},{"key":"19_CR19","unstructured":"Chorowski, J.K., Bahdanau, D., Serdyuk, D., Cho, K., Bengio, Y.: Attention-based models for speech recognition. In: Advances in Neural Information Processing Systems, pp. 577\u2013585 (2015)"},{"key":"19_CR20","doi-asserted-by":"crossref","unstructured":"Bluche, T., Louradour, J., Messina, R.: Scan, attend and read: end-to-end handwritten paragraph recognition with MDLSTM attention. arXiv preprint arXiv:1604.03286 (2016)","DOI":"10.1109\/ICDAR.2017.174"},{"key":"19_CR21","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"},{"key":"19_CR22","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":"19_CR23","unstructured":"Ba, J., Mnih, V., Kavukcuoglu, K.: Multiple object recognition with visual attention. arXiv preprint arXiv:1412.7755 (2014)"},{"key":"19_CR24","unstructured":"Jaderberg, M., Simonyan, K., Zisserman, A., et al.: Spatial transformer networks. In: Advances in Neural Information Processing Systems, pp. 2017\u20132025 (2015)"},{"key":"19_CR25","unstructured":"Zeiler, M.D.: Adadelta: an adaptive learning rate method. arXiv preprint arXiv:1212.5701 (2012)"},{"key":"19_CR26","doi-asserted-by":"crossref","unstructured":"Cho, K., Van Merri\u00ebnboer, B., Bahdanau, D., Bengio, Y.: On the properties of neural machine translation: encoder-decoder approaches. arXiv preprint arXiv:1409.1259 (2014)","DOI":"10.3115\/v1\/W14-4012"},{"key":"19_CR27","doi-asserted-by":"crossref","unstructured":"Sennrich, R., Firat, O., Cho, K., Birch, A., Haddow, B., Hitschler, J., Junczys-Dowmunt, M., L\u00e4ubli, S., Barone, A.V.M., Mokry, J., et al.: Nematus: a toolkit for neural machine translation. arXiv preprint arXiv:1703.04357 (2017)","DOI":"10.18653\/v1\/E17-3017"}],"container-title":["Lecture Notes in Computer Science","Neural Information Processing"],"original-title":[],"link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-319-70090-8_19","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,26]],"date-time":"2025-06-26T19:25:00Z","timestamp":1750965900000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/978-3-319-70090-8_19"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2017]]},"ISBN":["9783319700892","9783319700908"],"references-count":27,"URL":"https:\/\/doi.org\/10.1007\/978-3-319-70090-8_19","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2017]]}}}