160 citations
- Franck Mamalet2 profiles8 · h 20
- Thibaut Boissin6 · h 9
- Thomas Fel6 · h 15
- Sébastien Gerchinovitz5 · h 15
- Adrien Gauffriau4 · h 5
- Claire Pagetti4 · h 25
- François Malgouyres4 · h 3
- L'eo And'eol2 profiles4 · h 5
- Mélanie Ducoffe2 profiles4 · h 11
- Corentin Friedrich3 · h 4
- David Bertoin2 profiles3 · h 5
- E. Achour3 · h 6
- Institut de Mathématiques de ToulouseFR15 papers
- Université Toulouse III - Paul SabatierFR12 papers
- Institut National des Sciences Appliquées de ToulouseFR9 papers
- Société Nationale des Chemins de Fer Français (France)FR9 papers
- Institut de Recherche en Informatique de ToulouseFR8 papers
- Université Fédérale de Toulouse Midi-PyrénéesFR6 papers
- Airbus (France)FR5 papers
- Brown UniversityUS5 papers
- Institut Polytechnique de BordeauxFR5 papers
- Université Toulouse-I-CapitoleFR5 papers
- Université Toulouse - Jean JaurèsFR5 papers
- Institut Supérieur de l'Aéronautique et de l'Espace (ISAE-SUPAERO)FR4 papers
9 papers · 1 filter
Graph-Based Convexification of Nested Signal Temporal Logic Constraints for Trajectory Optimization
Thomas Claudet, Davide Martire, Damiana Losa +2
Optimizing high-level mission planning constraints is traditionally solved in exponential time and requires to split the problem into several ones, making the connections between t…
Read, look and detect: Bounding box annotation from image-caption pairs
Eduardo Hugo Sanchez
Various methods have been proposed to detect objects while reducing the cost of data annotation. For instance, weakly supervised object detection (WSOD) methods rely only on image-…
Adversarial alignment: Breaking the trade-off between the strength of an attack and its relevance to human perception
Drew Linsley, Pinyuan Feng, Thibaut Boissin +4
Deep neural networks (DNNs) are known to have a fundamental sensitivity to adversarial attacks, perturbations of the input that are imperceptible to humans yet powerful enough to c…
Multilevel Surrogate-based Control Variates
Mohamed Reda El Amri, Paul Mycek, Sophie Ricci +1
Monte Carlo (MC) sampling is a popular method for estimating the statistics (e.g. expectation and variance) of a random variable. Its slow convergence has led to the emergence of a…
COCKATIEL: COntinuous Concept ranKed ATtribution with Interpretable ELements for explaining neural net classifiers on NLP tasks
Fanny Jourdan, Agustin Picard, Thomas Fel +3
Transformer architectures are complex and their use in NLP, while it has engendered many successes, makes their interpretability or explainability challenging. Recent debates have…
LARD -- Landing Approach Runway Detection -- Dataset for Vision Based Landing
Mélanie Ducoffe, Maxime Carrere, Léo Féliers +4
As the interest in autonomous systems continues to grow, one of the major challenges is collecting sufficient and representative real-world data. Despite the strong practical and c…