TY  - CONF
AU  - Lei Kang
AU  - Juan Ignacio Toledo
AU  - Pau Riba
AU  - Mauricio Villegas
AU  - Alicia Fornes
AU  - Marçal Rusiñol
A2  - GCPR
PY  - 2018//
TI  - Convolve, Attend and Spell: An Attention-based Sequence-to-Sequence Model for Handwritten Word Recognition
BT  - 40th German Conference on Pattern Recognition
SP  - 459
EP  - 472
N2  - This paper proposes Convolve, Attend and Spell, an attention based sequence-to-sequence model for handwritten word recognition. The proposed architecture has three main parts: an encoder, consisting of a CNN and a bi-directional GRU, an attention mechanism devoted to focus on the pertinent features and a decoder formed by a one-directional GRU, able to spell the corresponding word, character by character. Compared with the recent state-of-the-art, our model achieves competitive results on the IAM dataset without needing any pre-processing step, predefined lexicon nor language model. Code and additional results are available in https://github.com/omni-us/research-seq2seq-HTR.
UR  - https://doi.org/10.1007/978-3-030-12939-2_32
L1  - http://refbase.cvc.uab.es/files/KTR2018.pdf
N1  - DAG; 600.097; 603.057; 302.065; 601.302; 600.084; 600.121; 600.129
ID  - Lei Kang2018
ER  -