Publications

Computer Science

Convolutional Sparse Coding for Time Series Via a l0 Penalty: An Efficient Algorithm With Statistical Guarantees

Identifying characteristic patterns in time series, such as heartbeats or brain responses to a stimulus, is critical to understanding the physical or physiological phenomena monitored with sensors. Convolutional sparse coding (CSC) methods, which…

Charles Truong, Thomas Moreau

Statistical Analysis and Data Mining - 2024

Mathematics

Free Boundary Problems in Fluid Dynamics

Albert Ai, Thomas Alazard, Mihaela Ifrim, Daniel Tataru

Atmospheric and Oceanic Physics

Beyond the Sea Surface : Exploring Ocean Wave Measurements From Multiple Perspectives

This thesis explores ocean wave measurements from multiple perspectives, extending the analysis beyond their visual manifestation on the sea surface. Existing limitations in measurement technologies hinder a full understanding of aspects such as…

Daniel Santiago Pelaez Zapata

Image Processing

Detecting Forged Sentinel-2 Images Through Parallax-Based Cloud Analysis

The availability and significance of satellite imagery in our world is continuously growing. Satellite images now play a crucial role in various applications such as weather forecasting, greenhouse gas monitor- ing, agricultural crop health…

Matthieu Serfaty, Quentin Bammey, Tina Nikoukhah, Rafael Grompone von Gioi, Carlo de Franchis

European Conference on Computer Vision (ECCV) 2024 - Advances in Image Manipulation workshop - 2024

Mathematics

Graph-Convolutional Networks: Named Entity Recognition and Large Language Model Embedding in Document Clustering

Recent advances in machine learning, particularly Large Language Models (LLMs) such as BERT and GPT, provide rich contextual embeddings that improve text representation. However, current document clustering approaches often ignore the deeper…

Imed Keraghel, Mohamed Nadif

Computer Science

Clustering de documents avec des plongements LLMs : évaluation de la réduction de dimension

Le clustering de documents est crucial pour la gestion et l'analyse d'importants volumes de données textuelles. Les progrès récents dans les grands modèles de langage (LLMs), comme GPT, ont transformé la manière dont les textes peuvent être analysés…

Imed Keraghel, Stanislas Morbieu, Mohamed Nadif

Les 29èmes Rencontres de la Société Francophone de Classification (SFC) - 2024

Computer Science

Étude sur la classification d'entités nommées

La reconnaissance et la classification d'entités nommées au sein de documents est un processus permettant d'extraire des informations pertinentes pour une tâche donnée. Cependant, les méthodes disponibles pour effectuer ce processus varient selon…

Imed Keraghel, S Morbieu, M Nadif

Les 28èmes rencontres de la Société Francophone de Classification (SFC) - 2024

Life Sciences

Automatic gait events detection with inertial measurement units: healthy subjects and moderate to severe impaired patients

Abstract Background Recently, the use of inertial measurement units (IMUs) in quantitative gait analysis has been widely developed in clinical practice. Numerous methods have been developed for the automatic detection of gait events (GEs). While…

Cyril Voisard, Nicolas de L’escalopier, Damien Ricard, Laurent Oudre

Journal of NeuroEngineering and Rehabilitation - 2024

Machine Learning

Learning to Mitigate Externalities: the Coase Theorem with Hindsight Rationality

In economic theory, the concept of externality refers to any indirect effect resulting from an interaction between players that affects the social welfare. Most of the models within which externality has been studied assume that agents have perfect…

Antoine Scheid, Aymeric Capitaine, Etienne Boursier, Eric Moulines, Michael I Jordan, Alain Durmus

NeurIPS 2024 - The Thirty-Eighth Annual Conference on Neural Information Processing Systems - 2024

Computer Science

A blockchain-based unified PID with applications in healthcare

This work proposes DOIschain, a decentralized blockchain-based architecture to generate and store persistent, immutable, and perennial identifiers for digital objects (IDO) for the final products of computational scientific research. A supra…

Jose Armando Hernandez Gonzalez, Miguel Colom

The Sixth International Conference on Blockchain Computing and Applications (BCCA 2024) - 2024