7 citations
Counting papers with at most 25 authors, so collaboration author lists do not stand in for the people here.
- Laure Berti-Équille3 profiles8 · h 24
- Grigor Bezirganyan3 · h 3
- Jérémie Guiochet2 profiles3 · h 22
- Joris Guérin3 · h 2
- Kevin Delmas3 · h 5
- K. Veeramachaneni3 · h 38
- Sana Sellami3 · h 3
- Sarah Alnegheimish3 · h 9
- Sébastien Fournier3 · h 4
- Raul Sena Ferreira2 · h 5
- Abdelmadjid Chergui1 · h 1
- Alfredo Cuesta-Infante1 · h 14
- Institut de Recherche pour le DéveloppementFR12 papers
- UMR Espace-Dev11 papers
- Aix-Marseille UniversitéFR3 papers
- Laboratoire d'Analyse et d'Architecture des SystèmesFR3 papers
- Office National d'Études et de Recherches AérospatialesFR3 papers
- Université Fédérale de Toulouse Midi-PyrénéesFR3 papers
- Centre National de la Recherche ScientifiqueFR2 papers
- IAC (United States)US2 papers
- Université de MontpellierFR2 papers
- Université Toulouse III - Paul SabatierFR2 papers
- American UniversityUS1 paper
- Bioversity InternationalCO1 paper
13 papers
MixMAS: A Framework for Sampling-Based Mixer Architecture Search for Multimodal Fusion and Learning
Abdelmadjid Chergui, Grigor Bezirganyan, Sana Sellami +2
Choosing a suitable deep learning architecture for multimodal data fusion is a challenging task, as it requires the effective integration and processing of diverse data types, each…
Hierarchical Classification for Automated Image Annotation of Coral Reef Benthic Structures
Célia Blondin, Joris Guérin, Kelly Inagaki +2
Automated benthic image annotation is crucial to efficiently monitor and protect coral reefs against climate change. Current machine learning approaches fail to capture the hierarc…
Safety Monitoring of Machine Learning Perception Functions: a Survey
Raul Sena Ferreira, Joris Guérin, Kevin Delmas +2
Machine Learning (ML) models, such as deep neural networks, are widely applied in autonomous systems to perform complex perception tasks. New dependability challenges arise when ML…
Multimodal Learning with Uncertainty Quantification based on Discounted Belief Fusion
Grigor Bezirganyan, Sana Sellami, Laure Berti-Équille +1
Multimodal AI models are increasingly used in fields like healthcare, finance, and autonomous driving, where information is drawn from multiple sources or modalities such as images…
LUMA: A Benchmark Dataset for Learning from Uncertain and Multimodal Data
Grigor Bezirganyan, Sana Sellami, Laure Berti-Équille +1
Multimodal Deep Learning enhances decision-making by integrating diverse information sources, such as texts, images, audio, and videos. To develop trustworthy multimodal approaches…
Can we Defend Against the Unknown? An Empirical Study About Threshold Selection for Neural Network Monitoring
Khoi Tran Dang, Kevin Delmas, Jérémie Guiochet +1
With the increasing use of neural networks in critical systems, runtime monitoring becomes essential to reject unsafe predictions during inference. Various techniques have emerged…
Large language models can be zero-shot anomaly detectors for time series?
Sarah Alnegheimish, Linh Nguyen, Laure Berti-Equille +1
Recent studies have shown the ability of large language models to perform a variety of tasks, including time series forecasting. The flexible nature of these models allows them to…
Sen2Chain: An Open-Source Toolbox for Processing Sentinel-2 Satellite Images and Producing Time-Series of Spectral Indices
Christophe Revillion, Pascal Mouquet, Jeremy Commins +10
The increasing availability of free high-resolution earth observation data covering any point on the globe every few days led to the emergence of new remote sensing tools that can…
Single Word Change is All You Need: Using LLMs to Create Synthetic Training Examples for Text Classifiers
Lei Xu, Sarah Alnegheimish, Laure Berti-Equille +2
In text classification, creating an adversarial example means subtly perturbing a few words in a sentence without changing its meaning, causing it to be misclassified by a classifi…
OrionBench: Benchmarking Time Series Generative Models in the Service of the End-User
Sarah Alnegheimish, Laure Berti-Equille, Kalyan Veeramachaneni
Time series anomaly detection is a vital task in many domains, including patient monitoring in healthcare, forecasting in finance, and predictive maintenance in energy industries.…
The State of Food Systems Worldwide: Counting Down to 2030
Kate Schneider, Jessica Fanzo, Lawrence Haddad +54
Transforming food systems is essential to bring about a healthier, equitable, sustainable, and resilient future, including achieving global development and sustainability goals. To…
Out-Of-Distribution Detection Is Not All You Need
Joris Guérin, Kevin Delmas, Raul Sena Ferreira +1
The usage of deep neural networks in safety-critical systems is limited by our ability to guarantee their correct behavior. Runtime monitors are components aiming to identify unsaf…
Discovering Multi-Table Functional Dependencies Without Full Join Computation
Ugo Comignani, Laure Berti-Équille, Noël Novelli
In this paper, we study the problem of discovering join FDs, i.e., functional dependencies (FDs) that hold on multiple joined tables. We leverage logical inference, selective minin…