%0 Conference Proceedings %T Convolve, Attend and Spell: An Attention-based Sequence-to-Sequence Model for Handwritten Word Recognition %A Lei Kang %A Juan Ignacio Toledo %A Pau Riba %A Mauricio Villegas %A Alicia Fornes %A Marçal Rusiñol %B 40th German Conference on Pattern Recognition %D 2018 %F Lei Kang2018 %O DAG; 600.097; 603.057; 302.065; 601.302; 600.084; 600.121; 600.129 %O exported from refbase (http://refbase.cvc.uab.es/show.php?record=3167), last updated on Fri, 26 Feb 2021 14:07:30 +0100 %X 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. %U https://doi.org/10.1007/978-3-030-12939-2_32 %U http://refbase.cvc.uab.es/files/KTR2018.pdf %P 459-472