no code implementations • 13 Oct 2021 • Jen-Hao Rick Chang, Martin Bresler, Youssouf Chherawala, Adrien Delaye, Thomas Deselaers, Ryan Dixon, Oncel Tuzel
We use the framework to optimize data synthesis and demonstrate significant improvement on handwriting recognition over a model trained on real data only.
1 code implementation • NeurIPS 2020 • Emre Aksan, Thomas Deselaers, Andrea Tagliasacchi, Otmar Hilliges
We demonstrate qualitatively and quantitatively that our proposed approach is able to model the appearance of individual strokes, as well as the compositional structure of larger diagram drawings.
2 code implementations • 20 Feb 2020 • Philippe Gervais, Thomas Deselaers, Emre Aksan, Otmar Hilliges
We are releasing a dataset of diagram drawings with dynamic drawing information.
no code implementations • ICLR 2019 • Victor Carbune, Thierry Coppey, Alexander Daryin, Thomas Deselaers, Nikhil Sarda, Jay Yagnik
We leverage the existing concept of variables and create a new type, a predicted variable.
no code implementations • 19 Apr 2019 • R. Reeve Ingle, Yasuhisa Fujii, Thomas Deselaers, Jonathan Baccash, Ashok C. Popat
These constitute a solution to bring HTR capability into a large scale OCR system.
no code implementations • 19 Mar 2019 • Pedro Gonnet, Thomas Deselaers
The number of parameters per IndyLSTM layer, and thus the number of FLOPS per evaluation, is linear in the number of nodes in the layer, as opposed to quadratic for regular LSTM layers, resulting in potentially both smaller and faster models.
no code implementations • 22 Feb 2019 • Victor Carbune, Pedro Gonnet, Thomas Deselaers, Henry A. Rowley, Alexander Daryin, Marcos Calvo, Li-Lun Wang, Daniel Keysers, Sandro Feuz, Philippe Gervais
We describe an online handwriting system that is able to support 102 languages using a deep neural network architecture.
no code implementations • ICLR 2019 • Victor Carbune, Thierry Coppey, Alexander Daryin, Thomas Deselaers, Nikhil Sarda, Jay Yagnik
As opposed to previous work applying ML to algorithmic problems, our proposed approach does not require to drop existing implementations but seamlessly integrates into the standard software development workflow and gives full control to the software developer over how ML methods are applied.