Search Results for author: Marie Beurton-Aimar

Found 4 papers, 2 papers with code

Multitask Multi-database Emotion Recognition

1 code implementation8 Jul 2021 Manh Tu Vu, Marie Beurton-Aimar

We also exploit the sharing videos between the two tasks of the AffWild2 database that is used in the competition, to further improve the performance of the network.

Arousal Estimation Emotion Recognition

Using Graph Neural Networks to Reconstruct Ancient Documents

no code implementations13 Nov 2020 Cecilia Ostertag, Marie Beurton-Aimar

In this work we present a solution based on a Graph Neural Network, using pairwise patch information to assign labels to edges representing the spatial relationships between pairs.

Graph Neural Network

Predicting Brain Degeneration with a Multimodal Siamese Neural Network

no code implementations2 Nov 2020 Cecilia Ostertag, Marie Beurton-Aimar, Muriel Visani, Thierry Urruty, Karell Bertet

We also show the superiority of the multimodal architecture, for up to 37. 5\% of missing values in test set subjects' clinical measurements, compared to a model using only the clinical modality.

3DSiameseNet to Analyze Brain MRI

1 code implementation3 Sep 2019 Cecilia Ostertag, Marie Beurton-Aimar, Thierry Urruty

Prediction of the cognitive evolution of a person susceptible to develop a neurodegenerative disorder is crucial to provide an appropriate treatment as soon as possible.

Cannot find the paper you are looking for? You can Submit a new open access paper.