180 citations
Counting papers with at most 25 authors, so collaboration author lists do not stand in for the people here.
- Université Paris-SaclayFR185 papers
- Centre National de la Recherche ScientifiqueFR119 papers
- Institut national de recherche en sciences et technologies du numériqueFR29 papers
- Laboratoire Interdisciplinaire de PhysiqueFR26 papers
- Sorbonne UniversitéFR20 papers
- Centre Inria de SaclayFR17 papers
- CentraleSupélecFR15 papers
- Local Initiatives Support CorporationUS15 papers
- Université Paris CitéFR15 papers
- Universidad Complutense de MadridES14 papers
- École Normale Supérieure - PSLFR11 papers
- Gleason (United States)US10 papers
33 papers · 1 filter
Cosmology with cosmic web environments I. Real-space power spectra
Tony Bonnaire, Nabila Aghanim, Joseph Kuruvilla +1
We undertake the first comprehensive and quantitative real-space analysis of the cosmological information content in the environments of the cosmic web (voids, filaments, walls, an…
Curriculum learning for data-driven modeling of dynamical systems
Alessandro Bucci, Onofrio Semeraro, Alexandre Allauzen +2
The reliable prediction of the temporal behavior of complex systems is key in numerous scientific fields. This strong interest is however hindered by modeling issues: often, the go…
New lower bounds for Schur and weak Schur numbers
Romain Ageron, Paul Casteras, Thibaut Pellerin +3
This article provides new lower bounds for both Schur and weak Schur numbers by exploiting a "template"-based approach. The concept of "template" is also generalized to weak Schur…
Does constituency analysis enhance domain-specific pre-trained BERT models for relation extraction?
Anfu Tang, Louise Deléger, Robert Bossy +2
Recently many studies have been conducted on the topic of relation extraction. The DrugProt track at BioCreative VII provides a manually-annotated corpus for the purpose of the dev…
Cluster-based hierarchical network model of the fluidic pinball -- Cartographing transient and post-transient, multi-frequency, multi-attractor behaviour
Nan Deng, Bernd R. Noack, Marek Morzyński +1
We propose a self-supervised cluster-based hierarchical reduced-order modelling methodology to model and analyse the complex dynamics arising from a sequence of bifurcations for a…
Self-Stabilization and Byzantine Tolerance for Maximal Independent Set
Johanne Cohen, Laurence Pilard, Jonas Sénizergues
We analyze the impact of transient and Byzantine faults on the construction of a maximal independent set in a general network. We adapt the self-stabilizing algorithm presented by…
Computational analysis of flow structures in turbulent ventricular blood flow associated with mitral valve intervention
Joel Kronborg, Frida Svelander, Samuel Eriksson-Lidbrink +4
Cardiac disease and clinical intervention may both lead to an increased risk for thrombosis events due to modified blood flow in the heart, and thereby a change in the mechanical s…
End-to-End Speech Emotion Recognition: Challenges of Real-Life Emergency Call Centers Data Recordings
Théo Deschamps-Berger, Lori Lamel, Laurence Devillers
Recognizing a speaker's emotion from their speech can be a key element in emergency call centers. End-to-end deep learning systems for speech emotion recognition now achieve equiva…
Interactive simulation for easy decision-making in fluid dynamics
Mengchen Wang, Nicolas Férey, Frédéric Magoulès +1
A conventional study of fluid simulation involves different stages including conception, simulation, visualization, and analysis tasks. It is, therefore, necessary to switch betwee…
Don't Judge Me by My Face : An Indirect Adversarial Approach to Remove Sensitive Information From Multimodal Neural Representation in Asynchronous Job Video Interviews
Léo Hemamou, Arthur Guillon, Jean-Claude Martin +1
se of machine learning for automatic analysis of job interview videos has recently seen increased interest. Despite claims of fair output regarding sensitive information such as ge…
Smart Crawling: A New Approach toward Focus Crawling from Twitter
Ahmad Khazaie, Nacéra Bennacer Seghouani, Francesca Bugiotti
Twitter is a social network that offers a rich and interesting source of information challenging to retrieve and analyze. Twitter data can be accessed using a REST API. The availab…
AutoDEUQ: Automated Deep Ensemble with Uncertainty Quantification
Romain Egele, Romit Maulik, Krishnan Raghavan +3
Deep neural networks are powerful predictors for a variety of tasks. However, they do not capture uncertainty directly. Using neural network ensembles to quantify uncertainty is co…
Unraveling the Hidden Environmental Impacts of AI Solutions for Environment
Anne-Laure Ligozat, Julien Lefèvre, Aurélie Bugeau +1
In the past ten years, artificial intelligence has encountered such dramatic progress that it is now seen as a tool of choice to solve environmental issues and in the first place g…
Codabench: Flexible, Easy-to-Use and Reproducible Benchmarking Platform
Zhen Xu, Sergio Escalera, Isabelle Guyon +5
Obtaining standardized crowdsourced benchmark of computational methods is a major issue in data science communities. Dedicated frameworks enabling fair benchmarking in a unified en…
Experimental Dispersion Relation of Surface Waves Along a Torus of Fluid
Filip Novkoski, Eric Falcon, Chi-Tuong Pham
We report the observation of gravity-capillary waves on a torus of fluid. By means of an original technique, a stable torus is achieved by depositing water on a superhydrophobic gr…
Perception! Immersion! Empowerment! Superpowers as Inspiration for Visualization
Wesley Willett, Bon Adriel Aseniero, Sheelagh Carpendale +4
We explore how the lens of fictional superpowers can help characterize how visualizations empower people and provide inspiration for new visualization systems. Researchers and prac…
Four-Valued Semantics for Deductive Databases
Dominique Laurent, Nicolas Spyratos
In this paper, we introduce a novel approach to deductive databases meant to take into account the needs of current applications in the area of data integration. To this end, we ex…
AutoML Meets Time Series Regression Design and Analysis of the AutoSeries Challenge
Zhen Xu, Wei-Wei Tu, Isabelle Guyon
Analyzing better time series with limited human effort is of interest to academia and industry. Driven by business scenarios, we organized the first Automated Time Series Regressio…
eXtended Reality for Autism Interventions: The importance of Mediation and Sensory-Based Approaches
Valentin Bauer, Tifanie Bouchara, Patrick Bourdot
eXtended Reality (XR) autism research, ranging from Augmented Reality to Virtual Reality, focuses on socio-emotional abilities and high-functioning autism. However common autism in…
Observation data compression for variational assimilation of dynamical systems
Sibo Cheng, Didier Lucor, Jean-Philippe Argaud
Accurate estimation of error covariances (both background and observation) is crucial for efficient observation compression approaches in data assimilation of large-scale dynamical…
Where are we in semantic concept extraction for Spoken Language Understanding?
Sahar Ghannay, Antoine Caubrière, Salima Mdhaffar +3
Spoken language understanding (SLU) topic has seen a lot of progress these last three years, with the emergence of end-to-end neural approaches. Spoken language understanding refer…
Document Domain Randomization for Deep Learning Document Layout Extraction
Meng Ling, Jian Chen, Torsten Möller +7
We present document domain randomization (DDR), the first successful transfer of convolutional neural networks (CNNs) trained only on graphically rendered pseudo-paper pages to rea…
Paradiseo: From a Modular Framework for Evolutionary Computation to the Automated Design of Metaheuristics ---22 Years of Paradiseo---
Johann Dreo, Arnaud Liefooghe, Sébastien Verel +5
The success of metaheuristic optimization methods has led to the development of a large variety of algorithm paradigms. However, no algorithm clearly dominates all its competitors…
Equilibrium and non-Equilibrium regimes in the learning of Restricted Boltzmann Machines
Aurélien Decelle, Cyril Furtlehner, Beatriz Seoane
Training Restricted Boltzmann Machines (RBMs) has been challenging for a long time due to the difficulty of computing precisely the log-likelihood gradient. Over the past decades,…