Diffusion scientifique
Dernières publications
Bringing NeRFs to the Latent Space: Inverse Graphics Autoencoder
Communication lors d'une conférence
Antoine Schnepf, Karim Kassab, Jean-Yves Franceschi, Laurent Caraffa, Flavian Vasile, Jeremie Mary, Andrew I. Comport, Valérie Gouet-Brunet
While pre-trained image autoencoders are increasingly utilized in computer vision, the application of inverse graphics in 2D latent spaces…
FALCON: A multi-label graph-based dataset for fallacy classification in the COVID-19 infodemic
Communication lors d'une conférence
Mariana Chaves, Elena Cabrio, Serena Villata
Fallacies are arguments that seem valid but contain logical flaws. During the COVID-19 pandemic, they played a role in spreading…
Hybrid Visual SLAM for Multi-session Precise Localization: Application to a Coastal Cliff in Normandy
Communication lors d'une conférence
Diego Navarro, Ezio Malis, Raphael Antoine, Philippe Martinet
In the context of smart structure maintenance, the positioning of data measurements (e.d. radar, thermal camera, etc..) is crucial. Most…
Towards a fully automated underwater census for fish assemblages in the Mediterranean Sea
Article dans une revue
Kilian Bürgi, Charles Bouveyron, Diane Lingrand, Benoit Derijard, Frédéric Precioso, Cécile Sabourault
Assessing underwater biodiversity is labour-intensive and costly, but is crucial for measuring the extent of the decline in local fish…
Mind the map! Accounting for existing maps when estimating online HDMaps from sensors.
Communication lors d'une conférence
Rémy Sun, Li Yang, Diane Lingrand, Frédéric Precioso
While HDMaps are a crucial component of autonomous driving, they are expensive to acquire and maintain. Estimating these maps from sensors…
Attribute Inference Attacks for Federated Regression Tasks
Communication lors d'une conférence
Francesco Diana, Othmane Marfoq, Chuan Xu, Giovanni Neglia, Frédéric Giroire, Eoin Thomas
Federated Learning (FL) enables multiple clients, such as mobile phones and IoT devices, to collaboratively train a global machine…