Consulter le flux RSS

Publications

Cette page présente les publications du Centre Borelli déposées sur le serveur HAL.

Affichage des publications 251 à 260 sur 1555 au total

Machine Learning

SKADA-Bench: Benchmarking Unsupervised Domain Adaptation Methods with Realistic Validation On Diverse Modalities

Unsupervised Domain Adaptation (DA) consists of adapting a model trained on a labeled source domain to perform well on an unlabeled target domain with some data distribution shift. While many methods have been proposed in the literature, fair and…

Yanis Lalou, Theo Gnassounou, Antoine Collas, Antoine de Mathelin, Oleksii Kachaiev, Ambroise Odonnat, Thomas Moreau, Alexandre Gramfort, Rémi Flamary

Transactions on Machine Learning Research -

Machine Learning

Signed Graph Autoencoder for Explainable and Polarization-Aware Network Embeddings

Autoencoders based on Graph Neural Networks (GNNs) have garnered significant attention in recent years for their ability to extract informative latent representations, characterizing the structure of complex topologies, such as graphs. Despite the…

Nikolaos Nakis, Chrysoula Kosma, Giannis Nikolentzos, Michalis Chatzianastasis, Iakovos Evdaimon, Michalis Vazirgiannis

AISTATS 2025 -28th International Conference on Artificial Intelligence and Statistics -

Life Sciences

In its very early phases, COVID-19 shifts the associations between alcohol consumption and psychological symptoms in young adults

Background. The COVID-19 pandemic has impacted various aspects of daily life, leading to increased psychological symptoms and changes in alcohol use, yet little is known about their specific interactions, particularly early stages during the…

Karina Janson, Arun L.W. Bokde, Sylvane Desrivières, Hugh Garavan, Penny Gowland, Antoine Grigis, Andreas Heinz, Jean-Luc Martinot, Marie-Laure Paillère Martinot, Eric Artiges, Dimitri Papadopoulos Orfanos, Tomáš Paus, Luise Poustka, Michael N Smolka, Nathalie E Holz, Nilakshi Vaidya, Henrik Walter, Robert Whelan, Gunter Schumann, Herta Flor, Olaf Reis, Emanuel Schwarz, Tobias Banaschewski, Frauke Nees

European Psychiatry -

Humanities and Social Sciences

Multi-segmental control of style

By analyzing body movements and muscle activity across ground level, height exposure, and return-to-ground conditions, this study identified significant, individualized changes in motor control and EMG activity that define perceptualmotor styles…

Danping Wang, Yunchao Peng, Donovan Morel, Ioannis Bargiotas, Nicolas Vayatis, Lise Haddouk, Pierre‐paul Vidal

Annual Review of Cybertherapy and Telemedicine -

Computer Science

A Comparative Analysis of OCR Models on Diverse Datasets: Insights from Memes and Hiertext Dataset

Optical Character Recognition (OCR) plays a critical role in various text extraction applications, yet its performance varies significantly across languages, visual appearances, and document types. This study benchmarks several state-of-the-art OCR…

Iknoor Singh, Miguel Colom, Kalina Bontcheva

2025 IEEE/CVF Winter Conference on Applications of Computer Vision (WACV 2025) -

Santé publique et épidémiologie

Coronary Heart Disease Attributable to Psychosocial Stressors at Work

BACKGROUND: Psychosocial stressors at work, including job strain and effort-reward imbalance (ERI), have been associated with an increased risk of coronary heart disease (CHD). However, the proportion of CHD events attributable to these exposures…

Mathilde Lavigne-Robichaud, Xavier Trudel, Denis Talbot, Alain Milot, Ana Paula Bruno Pena-Gralle, Miceline Mésidor, Mahée Gilbert-Ouimet, Isabelle Niedhammer, Hélène Sultan-Taïeb, Clermont E Dionne, Michel Vézina, Line Guénette, Sophie Lauzier, Elizabeth Maunsell, Caroline Biron, Neil Pearce, Benoît Mâsse, Gilles R Dagenais, Chantal Brisson

JACC. Advances -

Machine Learning

Graph Neural Networks for Electricity Load Forecasting

Forecasting electricity demand is increasingly challenging as energy systems become more decentralized and intertwined with renewable sources. Graph Neural Networks (GNNs) have recently emerged as a powerful paradigm to model spatial dependencies in…

Eloi Campagne, Yvenn Amara-Ouali, Yannig Goude, Itai Zehavi, Argyris Kalogeratos