activity
20182021
most citedThe DIDI dataset: Digital Ink Diagram data

9 citations · 9 across the 2 of their papers we have counts for

collaborators

7 papers

cs.CV2021

Data Incubation -- Synthesizing Missing Data for Handwriting Recognition

Jen-Hao Rick Chang, Martin Bresler, Youssouf Chherawala +4

In this paper, we demonstrate how a generative model can be used to build a better recognizer through the control of content and style. We are building an online handwriting recogn…

cs.LG2020

CoSE: Compositional Stroke Embeddings

Emre Aksan, Thomas Deselaers, Andrea Tagliasacchi +1

We present a generative model for complex free-form structures such as stroke-based drawing tasks. While previous approaches rely on sequence-based models for drawings of basic obj…

cs.HC20209 cited

The DIDI dataset: Digital Ink Diagram data

Philippe Gervais, Thomas Deselaers, Emre Aksan +1

We are releasing a dataset of diagram drawings with dynamic drawing information. The dataset aims to foster research in interactive graphical symbolic understanding. The dataset wa…

cs.CV2019

A Scalable Handwritten Text Recognition System

R. Reeve Ingle, Yasuhisa Fujii, Thomas Deselaers +2

Many studies on (Offline) Handwritten Text Recognition (HTR) systems have focused on building state-of-the-art models for line recognition on small corpora. However, adding HTR cap…

cs.LG2019

IndyLSTMs: Independently Recurrent LSTMs

Pedro Gonnet, Thomas Deselaers

We introduce Independently Recurrent Long Short-term Memory cells: IndyLSTMs. These differ from regular LSTM cells in that the recurrent weights are not modeled as a full matrix, b…

cs.CL2019

Fast Multi-language LSTM-based Online Handwriting Recognition

Victor Carbune, Pedro Gonnet, Thomas Deselaers +7

We describe an online handwriting system that is able to support 102 languages using a deep neural network architecture. This new system has completely replaced our previous Segmen…