Publications

Statistics

Can Push-forward Generative Models Fit Multimodal Distributions?

Many generative models synthesize data by transforming a standard Gaussian random variable using a deterministic neural network. Among these models are the Variational Autoencoders and the Generative Adversarial Networks. In this work, we call them …

Antoine Salmona, Valentin de Bortoli, Julie Delon, Agnès Desolneux

NeurIPS 2022 - 2022

Technology for Human Learning

Vers un modèle général de recommandation de trajectoires d’apprentissage

L’apprentissage adaptatif est un domaine de l’e-learning qui consiste à étudier et concevoir des dispositifs informatiques capables de délivrer des expériences d’apprentissage personnalisées. Dans la pratique, ces systèmes reposent souvent sur une…

Jean Vassoyan

Neuvièmes Rencontres Jeunes Chercheur·e·s en EIAH, RJC-EIAH - 2022

Image Processing

Improving the Pair Selection and the Model Fusion Steps of Satellite Multi-View Stereo Pipelines

Multi-view stereo reconstruction of scenes from satellite images is traditionally performed with a pair-wise stereovision approach: (1) multiple views are grouped into pairs, (2) each pair is processed by two-view stereo methods producing an…

Alvaro Gómez, Gregory Randall, Gabriele Facciolo, Rafael Grompone von Gioi

Image Processing

Improving Pixel-Level Contrastive Learning by Leveraging Exogenous Depth Information

Ahmed Ben Saad, Kristina Prokopetc, Josselin Kherroubi, Axel Davy, Adrien Courtois, Gabriele Facciolo

Image Processing

AUTOMATIC METHANE PLUME QUANTIFICATION USING SENTINEL-2 TIME SERIES

Methane emissions monitoring is essential to control methane pollution. In this paper, we propose an automatic practical methodology using time series to estimate the quantity of methane in a given plume using a multispectral satellite like Sentinel…

T. Ehret, A. de Truchis, M. Mazzolini, J.-M. Morel, Gabriele Facciolo

2022 IEEE International Geoscience and Remote Sensing Symposium (IGARSS 2022) - 2022

Image Processing

Self-Supervised Push-Frame Super-Resolution With Detail-Preserving Control And Outlier Detection

Self-supervised training enables the application of deeplearning based methods for multi-image super-resolution of satellite imagery. In this work we propose two improvements on the self-supervised Deep-Shift-and-Add (DSA) method introduced by…

Ngoc Long Nguyen, Jeremy Anger, Axel Davy, Pablo Arias, Gabriele Facciolo

2022 IEEE International Geoscience and Remote Sensing Symposium (IGARSS 2022) - 2022

Psychology

Pratiques cliniques contemporaines et télépsychologie.

Lise Haddouk

Manuel des dispositifs et pratiques cliniques aux limites. - 2022

Psychology

Télépsychologie : état des lieux et enjeux

Cet état des lieux sur la télépsychologie en France et au niveau international a pour objectif de nourrir les réflexions et les pratiques des professionnels et des chercheurs. En effet, les récentes et rapides évolutions de ces modes d'intervention,…

Lise Haddouk, Benoit Schneider

Psychiatrics and mental health

Accueillir à distance en télépsychologie

Lise Haddouk

Santé Mentale - 2022

Psychiatrics and mental health

Online consultations in mental healthcare: Modelling determinants of use and experience based on an international survey study at the onset of the pandemic

Tom van Daele, Kim Mathiasen, Per Carlbring, Sylvie Bernaerts, Agostino Brugnera, Angelo Compare, Aranzazu Duque, Jonas Eimontas, David Gosar, Lise Haddouk, Maria Karekla, Pia Larsen, Gianluca Lo Coco, Tine Nordgreen, João Salgado, Andreas Schwerdtfeger, Eva van Assche, Sam Willems, Nele A.J. de Witte

Internet Interventions - 2022