28 citations · 58 across the 5 of their papers we have counts for
10 papers
Including Keyword Position in Image-based Models for Act Segmentation of Historical Registers
Mélodie Boillet, Martin Maarand, Thierry Paquet +1
The segmentation of complex images into semantic regions has seen a growing interest these last years with the advent of Deep Learning. Until recently, most existing methods for Hi…
SPAN: a Simple Predict & Align Network for Handwritten Paragraph Recognition
Denis Coquenet, Clément Chatelain, Thierry Paquet
Unconstrained handwriting recognition is an essential task in document analysis. It is usually carried out in two steps. First, the document is segmented into text lines. Second, a…
Recurrence-free unconstrained handwritten text recognition using gated fully convolutional network
Denis Coquenet, Clément Chatelain, Thierry Paquet
Unconstrained handwritten text recognition is a major step in most document analysis tasks. This is generally processed by deep recurrent neural networks and more specifically with…
Have convolutions already made recurrence obsolete for unconstrained handwritten text recognition ?
Denis Coquenet, Yann Soullard, Clément Chatelain +1
Unconstrained handwritten text recognition remains an important challenge for deep neural networks. These last years, recurrent networks and more specifically Long Short-Term Memor…
Multiple Document Datasets Pre-training Improves Text Line Detection With Deep Neural Networks
Mélodie Boillet, Christopher Kermorvant, Thierry Paquet
In this paper, we introduce a fully convolutional network for the document layout analysis task. While state-of-the-art methods are using models pre-trained on natural scene images…
CTCModel: a Keras Model for Connectionist Temporal Classification
Yann Soullard, Cyprien Ruffino, Thierry Paquet
We report an extension of a Keras Model, called CTCModel, to perform the Connectionist Temporal Classification (CTC) in a transparent way. Combined with Recurrent Neural Networks,…