Thomas Deselaers — accepted AI-conference papers

2022

Data Incubation - Synthesizing Missing Data for Handwriting Recognition

Jen-Hao Rick Chang, Martin Bresler, Youssouf Chherawala, Adrien Delaye, Thomas Deselaers, Ryan S. Dixon +1

ICASSP 2022accepted

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 recognizer from a modest amount of training samples. By training our controllable handwriting synthesizer on the same data, we…

Cited by 0 Source ↗Scholar ↗

2020

CoSE: Compositional Stroke Embeddings

Emre Aksan, Thomas Deselaers, Andrea Tagliasacchi, Otmar Hilliges

NeurIPS 2020poster

We present a generative model for stroke-based drawing tasks which is able to model complex free-form structures. While previous approaches rely on sequence-based models for drawings of basic objects or handwritten text, we propose a model that treats drawings as a collection of strokes that can be…

Cited by 39 Source ↗PDF ↗code ↗Scholar ↗

2020

Indylstms: Independently Recurrent LSTMS

Pedro Gonnet, Thomas Deselaers

ICASSP 2020accepted

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, but as a diagonal matrix, i.e. the output and state of each LSTM cell depends on the inputs and its own output/state, as…

Cited by 0 Source ↗Scholar ↗