Scan, Attend and Read: End-to-End Handwritten Paragraph Recognition with MDLSTM Attention

  title={Scan, Attend and Read: End-to-End Handwritten Paragraph Recognition with MDLSTM Attention},
  author={Th{\'e}odore Bluche and J{\'e}r{\^o}me Louradour and Ronaldo O. Messina},
  journal={2017 14th IAPR International Conference on Document Analysis and Recognition (ICDAR)},
We present an attention-based model for end-to-end handwriting recognition. Our system does not require any segmentation of the input paragraph. The model is inspired by the differentiable attention models presented recently for speech recognition, image captioning or translation. The main difference is the implementation of covert and overt attention with a multi-dimensional LSTM network. Our principal contribution towards handwriting recognition lies in the automatic transcription without a… CONTINUE READING
Highly Cited
This paper has 31 citations. REVIEW CITATIONS
Recent Discussions
This paper has been referenced on Twitter 14 times over the past 90 days. VIEW TWEETS


Publications citing this paper.
Showing 1-10 of 20 extracted citations


Publications referenced by this paper.
Showing 1-10 of 31 references

Lecture 6.5-rmsprop: Divide the gradient by a running average of its recent magnitude

  • Tijmen Tieleman, Geoffrey Hinton
  • COURSERA: Neural Networks for Machine Learning,
  • 2012
Highly Influential
3 Excerpts

ICFHR 2014 HTRtS : Handwritten Text Recognition on tranScriptorium Datasets

  • Baoguang Shi, Xinggang Wang, Pengyuan Lv, Cong Yao
  • International Conference on Frontiers in…
  • 2016

Similar Papers

Loading similar papers…