[1] Sueiras J, Ruiz V, Sanchez A et al. Offline continuous handwriting recognition using sequence to sequence neural networks[J]. Neurocomputing, 289, 119-128(2018).
[2] Doetsch P, Kozielski M, Ney H et al. Fast and robust training of recurrent neural networks for offline handwriting recognition[C]. //2014 14th International Conference on Frontiers in Handwriting Recognition, September 1-4, 2014, Hersonissos, Greece., 279-284(2014).
[3] Kozielski M, Doetsch P, Ney H et al. Improvements in RWTH’s system for off-line handwriting recognition[C]. //2013 12nd International Conference on Document Analysis and Recognition, August 25-28, 2013, Washington, DC, USA., 935-939(2013).
[6] Bluche T, Louradour J, Messina R et al. Scan,attend and read: end-to-end handwritten paragraph recognition with MDLSTM attention[C]. //2017 14th IAPR International Conference on Document Analysis and Recognition (ICDAR), November 9-15, 2017, Kyoto, Japan, 1050-1055(2017).
[7] Bluche T, Ney H, Kermorvant C et al. Feature extraction with convolutional neural networks for handwritten word recognition[C]. //2013 12nd International Conference on Document Analysis and Recognition, August 25-28, 2013, Washington, DC, USA., 285-289(2013).
[9] Voigtlaender P, Doetsch P, Ney H et al. Handwriting recognition with large multidime nsional long short-term memory recurrent neural networks[C]. //2016 15th International Conference on Frontiers in Handwriting Recognition (ICFHR), October 23-26, 2016, Shenzhen, China., 228-233(2016).
[10] Bluche T, Ney H, Kermorvant C et al. Tandem HMM with convolutional neural network for handwritten word recognition[C]. //2013 IEEE International Conference on Acoustics, Speech and Signal Processing, May 26-31, 2013, Vancouver, BC, Canada., 2390-2394(2013).
[12] Vaswani A, Shazeer N, Parmar N et al. Attention is all you need[C]. //NIPS’17: Procee dings of the 31st International Conference on Neural Information Processing Systems, December 4-9, 2017, Long Beach, CA, USA, 6000-6010(2017).
[14] Kang L, Toledo J I, Riba P et al. Convolve, attend and spell: an attention-based sequence-to-sequence model for handwritten word recognition[M]. //Brox T, Bruhn A, Fritz M, et al. Lecture notes in computer science, 11269, 459-472(2019).
[15] Fang D B, Feng G, Cao H Y et al. Handwritten formula symbol recognition based on multi-feature convolutional neural network[J]. Laser & Optoelectronics Progress, 56, 072001(2019).
[19] Mor N, Wolf L. Confidence prediction for lexicon-free OCR[C]. //2018 IEEE Winter Conference on Applications of Computer Vision (WACV), March 12-15, 2018, Lake Tahoe, NV, USA., 218-225(2018).
[20] Krishnan P, Dutta K, Jawahar C V et al. Word spotting and recognition using deep embedding[C]. //2018 13rd IAPR International Workshop on Document Analysis Systems (DAS), April 24-27, 2018, Vienna, Austria., 1-6(2018).
[22] Wigington C, Stewart S, Davis B et al. Data augmentation for recognition of hand written words and lines using a CNN-LSTM network[C]. //2017 14th IAPR International Conference on Document Analysis and Recognition (ICDAR), November 9-15, 2017, Kyoto, Japan., 639-645(2017).