Consulter le flux RSS

Publications

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

Affichage des publications 681 à 690 sur 1123 au total

Machine Learning

Self-supervision versus synthetic datasets: which is the lesser evil in the context of video denoising?

Supervised training has led to state-of-the-art results in image and video denoising. However, its application to real data is limited since it requires large datasets of noisy-clean pairs that are difficult to obtain. For this reason, networks are…

Valéry Dewil, Arnaud Barral, Gabriele Facciolo, Pablo Arias

The 1st Workshop on Vision Datasets Understanding (CVPR 2022) -

Mathematics

Monotone discretization of the Monge–Ampère equation of optimal transport

We design a monotone finite difference discretization of the second boundary value problem for the Monge–Ampère equation, whose main application is optimal transport. We prove the existence of solutions to a class of monotone numerical schemes for…

Guillaume Bonnet, Jean-Marie Mirebeau

ESAIM: Mathematical Modelling and Numerical Analysis -

Machine Learning

Efficient Graph Convolution for Joint Node Representation Learning and Clustering

Attributed graphs are used to model a wide variety of real-world networks. Recent graph convolutional network-based representation learning methods have set state-of-the-art results on the clustering of attributed graphs. However, these approaches…

Chakib Fettal, Lazhar Labiod, Mohamed Nadif

WSDM '22: The Fifteenth ACM International Conference on Web Search and Data Mining -

Artificial Intelligence

An assessment of Multi Object Tracking on low framerate conditions

La performance des méthodes de l'état de l'art en suivi multi-objets est généralement montrée sur des vidéos à fréquence image élevée, où les objets bougent très peu d'une image à l'autre. Il y a cependant des intérêts à travailler dans le cas plus…

Anis Yassine Ben Mabrouk, Gabriele Facciolo, Rafael Grompone von Gioi, Axel Davy

Life Sciences

Receptor Tyrosine Kinase KIT: A New Look for an Old Receptor

RTK KIT regulates a variety of crucial cellular processes via its cytoplasmic (CD) domain composed of the tyrosine kinase domain crowned by highly flexible domains-juxtamembrane region, kinase insert domain and C-tail, key recruitment regions for…

Julie Ledoux, Luba Tchertanov

IWBBIO-2022 International Work-Conference on Bioinformatics and Biomedical Engineering -

Life Sciences

Human Vitamin K Epoxide Reductase as a Target of its Redox Protein

Human Vitamin K epoxide reductase (hVKORC1) is a key enzyme to reduce vitamin K. Such function requires activation of the enzyme by a redox partner delivering reducing equivalents through thioldisulphide exchange reactions. The activation process…

Julie Ledoux, Maxim Stolyarchuck, Luba Tchertanov

Ignacio Rojas, Olga Valenzuela, Fernando Rojas, Luis Javier Herrera, Francisco Ortuño -

Mathematics

Decision-making tools for healthcare structures in times of pandemic

The COVID-19 sanitary crisis has shed an unprecedented light on the role of modellers, mathematicians, computer scientists and data scientists in the monitoring and in the understanding of the dynamics of an epidemic. The general audience became…

Thierry Garaix, Stéphane Gaubert, Julie Josse, Nicolas Vayatis, Amandine Véber

Anaesthesia Critical Care & Pain Medicine -

Statistics Theory

Weighting Schemes for One-Shot Federated Learning

This paper focuses on one-shot aggregation of statistical estimations made across disjoint data sources for federated learning, in the context of empirical risk minimization. We exploit the role of each local sample size for this problem to develop…

Marie Garin, Theodoros Evgeniou, Nicolas Vayatis