Fetching the paper…

Reading the bibliography…

2019

Evaluating Sequence-to-Sequence Models for Handwritten Text Recognition

Michael, Johannes, Labahn, Roger, Grüning, Tobias et al.

Original
PDF
Post on X

Understand

Encoder-decoder models have become an effective approach for sequence learning tasks like machine translation, image captioning and speech recognition, but have yet to show competitive results for handwritten text recognition.

To this end, we propose an attention-based sequence-to-sequence model.
It combines a convolutional neural network as a generic feature extractor with a recurrent neural network to encode both the visual information, as well as the temporal context between characters in the input image, and uses a separate recurrent neural network to decode the actual character sequence.
We make experimental comparisons between various attention mechanisms and positional encodings, in order to find an appropriate alignment between the input and output sequence.

Evaluating Sequence-to-Sequence Models for Handwritten Text Recognition · Around

Built on

S. Hochreiter and J. Schmidhuber, “Long short-term memory,” Neural computation , vol. 9, pp. 1735–80, 12 1997
1997
Earlier work this paper cites.
U.-V. Marti and H. Bunke, “The iam-database: an english sentence database for offline handwriting recognition,” International Journal on Document Analysis and Recognition , vol. 5, no. 1, pp. 39–46, Nov 2002
2002
Earlier work this paper cites.
A. Graves and J. Schmidhuber, “Framewise phoneme classification with bidirectional lstm and other neural network architectures,” Neural networks , vol. 18, pp. 602–610, 07 2005
2005
Earlier work this paper cites.
A. Graves, S. Fernández, F. Gomez, and J. Schmidhuber, “Connectionist temporal classification: Labelling unsegmented sequence data with recurrent neural networks,” in ICML , 01 2006, pp. 369–376
2006
Earlier work this paper cites.
A. Graves, S. Fernández, and J. Schmidhuber, “Multi-dimensional recurrent neural networks,” CoRR , vol. abs/0705.2011, 2007
Original
2007
Earlier work this paper cites.
A. Graves, M. Liwicki, S. Fernández, R. Bertolami, H. Bunke, and J. Schmidhuber, “A novel connectionist system for unconstrained handwriting recognition,” IEEE Transactions on Pattern Analysis and Machine Intelligence , vol. 31, no. 5, pp. 855–868, 05 2009
2009
Earlier work this paper cites.
X. Glorot and Y. Bengio, “Understanding the difficulty of training deep feedforward neural networks,” in International Conference on Artificial Intelligence and Statistics , 05 2010, pp. 249–256
2010
Earlier work this paper cites.
V. Pham, C. Kermorvant, and J. Louradour, “Dropout improves recurrent neural networks for handwriting recognition,” CoRR , vol. abs/1312.4569, 2013
Original
2013
Earlier work this paper cites.
A. Graves, “Generating sequences with recurrent neural networks,” CoRR , vol. abs/1308.0850, 2013
Original
2013
Earlier work this paper cites.
A. L. Maas, A. Y. Hannun, and A. Y. Ng, “Rectifier nonlinearities improve neural network acoustic models,” in ICML , 2013
2013
Earlier work this paper cites.
J. A. Sánchez, V. Romero, A. H. Toselli, and E. Vidal, “Icfhr2014 competition on handwritten text recognition on transcriptorium datasets (htrts),” in International Conference on Frontiers in Handwriting Recognition , 09 2014, pp. 785–790
2014
Earlier work this paper cites.
I. Sutskever, O. Vinyals, and Q. V. Le, “Sequence to sequence learning with neural networks,” NIPS , 09 2014
2014
Earlier work this paper cites.
D. Bahdanau, K. Cho, and Y. Bengio, “Neural machine translation by jointly learning to align and translate,” CoRR , vol. abs/1409.0473, 2014
Original
2014
Earlier work this paper cites.
D. Kingma and J. Ba, “Adam: A method for stochastic optimization,” ICLR , 12 2014
2014
Earlier work this paper cites.

Similar

K. Cho, A. Courville, and Y. Bengio, “Describing multimedia content using attention-based encoder-decoder networks,” IEEE Transactions on Multimedia , vol. 17, pp. 1875–1886, 11 2015
2015
Cited alongside, same era.
K. Xu, J. Ba, R. Kiros, K. Cho, A. C. Courville, R. Salakhutdinov, R. S. Zemel, and Y. Bengio, “Show, attend and tell: Neural image caption generation with visual attention,” CoRR , vol. abs/1502.03044, 2015
Original
2015
Cited alongside, same era.
D. Bahdanau, J. Chorowski, D. Serdyuk, P. Brakel, and Y. Bengio, “End-to-end attention-based large vocabulary speech recognition,” CoRR , vol. abs/1508.04395, 2015
Original
2015
Cited alongside, same era.
C.-Y. Lee, S. Xie, P. W. Gallagher, Z. Zhang, and Z. Tu, “Deeply-supervised nets,” in Proceedings of AISTATS , 2015
2015
Cited alongside, same era.

Then

J. Puigcerver, “Are multidimensional recurrent layers really necessary for handwritten text recognition?” in 2017 14th IAPR International Conference on Document Analysis and Recognition , 2017, pp. 67–72
2017
Later among the works it cites.
T. Strauß, “Decoding the output of neural networks - a discriminative approach,” Ph.D. dissertation, University of Rostock, 2017
2017
Later among the works it cites.
J. Poulos and R. Valle, “Attention networks for image-to-text,” CoRR , vol. abs/1712.04046, 2017
Original
2017
Later among the works it cites.
C. Raffel, T. Luong, P. J. Liu, R. J. Weiss, and D. Eck, “Online and linear-time attention by enforcing monotonic alignments,” in ICML , 2017
2017
Later among the works it cites.
A. Vaswani, N. Shazeer, N. Parmar, J. Uszkoreit, L. Jones, A. N. Gomez, L. Kaiser, and I. Polosukhin, “Attention is all you need,” CoRR , vol. abs/1706.03762, 2017

Beyond the bibliography

alphaXiv searches the wider corpus for related work and actual follow-ups.

Open on alphaXiv

alphaXiv is searching for related work…

T. Luong, H. Pham, and C. D. Manning, “Effective approaches to attention-based neural machine translation,” in EMNLP , 2015, pp. 1412–1421

2015

Cited alongside, same era.

J. Chorowski, D. Bahdanau, D. Serdyuk, K. Cho, and Y. Bengio, “Attention-based models for speech recognition,” in NIPS , 2015, pp. 577–585

2015

Cited alongside, same era.

I. Pratikakis, K. Zagoris, J. Puigcerver, A. H. Toselli, and E. Vidal, “Icfhr2016 handwritten keyword spotting competition (h-kws 2016),” in ICFHR , 2016, pp. 613–618

2016

Cited alongside, same era.

P. Voigtlaender, P. Doetsch, and H. Ney, “Handwriting recognition with large multidimensional long short-term memory recurrent neural networks,” in ICFHR , 10 2016, pp. 228–233

2016

Cited alongside, same era.

T. Bluche, “Joint line segmentation and transcription for end-to-end handwritten paragraph recognition,” CoRR , vol. abs/1604.08352, 2016

2016

Cited alongside, same era.

P. Doetsch, A. Zeyer, and H. Ney, “Bidirectional decoder networks for attention-based end-to-end offline handwriting recognition,” in International Conference on Frontiers in Handwriting Recognition , 2016, pp. 361–366

2016

Cited alongside, same era.

B. Sankaran, H. Mi, Y. Al-Onaizan, and A. Ittycheriah, “Temporal attention model for neural machine translation,” CoRR , vol. abs/1608.02927, 2016

Original

2016

Cited alongside, same era.

S. Kim, T. Hori, and S. Watanabe, “Joint ctc-attention based end-to-end speech recognition using multi-task learning,” CoRR , vol. abs/1609.06773, 2016

2016

Cited alongside, same era.

2017

Later among the works it cites.

J. Gehring, M. Auli, D. Grangier, D. Yarats, and Y. N. Dauphin, “Convolutional sequence to sequence learning,” in ICML , 08 2017, pp. 1243–1252

2017

Later among the works it cites.

C. Wigington, S. Stewart, B. Davis, B. Barrett, B. Price, and S. Cohen, “Data augmentation for recognition of handwritten words and lines using a cnn-lstm network,” in ICDAR , 11 2017, pp. 639–645

2017

Later among the works it cites.

S. Shankar and S. Sarawagi, “Label organized memory augmented neural network,” CoRR , vol. abs/1707.01461, 2017

Original

2017

Later among the works it cites.

A. Sriram, H. Jun, S. Satheesh, and A. Coates, “Cold fusion: Training seq2seq models together with language models,” CoRR , vol. abs/1708.06426, 2017

2017

Later among the works it cites.

A. Chowdhury and L. Vig, “An efficient end-to-end neural model for handwritten text recognition,” CoRR , vol. abs/1807.07965, 2018

2018

Later among the works it cites.

J. Sueiras, V. Ruiz, A. Sanchez, and J. Vélez, “Offline continuous handwriting recognition using sequence to sequence neural networks,” Neurocomputing , vol. 289, 02 2018

2018

Later among the works it cites.

L. Kang, J. I. Toledo, P. Riba, M. Villegas, A. Fornés, and M. Rusinol, “Convolve, attend and spell: An attention-based sequence-to-sequence model for handwritten word recognition,” GCPR , 2018

2018

Later among the works it cites.

M. Yousef, K. F. Hussain, and U. S. Mohammed, “Accurate, data-efficient, unconstrained text recognition with convolutional neural networks,” CoRR , vol. abs/1812.11894, 2018

2018

Later among the works it cites.

C.-C. Chiu and C. Raffel, “Monotonic chunkwise attention,” in ICLR , 2018

2018

Later among the works it cites.