443 citations
- Centre National de la Recherche ScientifiqueFR470 papers
- École PolytechniqueFR434 papers
- Université Paris-SaclayFR210 papers
- Commissariat à l'Énergie Atomique et aux Énergies AlternativesFR177 papers
- Centre de Physique ThéoriqueFR131 papers
- Télécom SudParisFR124 papers
- Institut National de Physique Nucléaire et de Physique des ParticulesFR123 papers
- Laboratoire Leprince-RinguetFR123 papers
- Massachusetts Institute of TechnologyUS120 papers
- Télécom ParisFR115 papers
- Tsinghua UniversityCN109 papers
- Peking UniversityCN108 papers
75 papers · 1 filter
Weakly Supervised Change Detection Using Guided Anisotropic Difusion
Rodrigo Caye Daudt, Bertrand Le Saux, Alexandre Boulch +1
Large scale datasets created from crowdsourced labels or openly available data have become crucial to provide training data for large scale learning algorithms. While these dataset…
An Experimental Study of the Impact of Pre-training on the Pruning of a Convolutional Neural Network
Nathan Hubens, Matei Mancas, Bernard Gosselin +2
In recent years, deep neural networks have known a wide success in various application domains. However, they require important computational and memory resources, which severely h…
Galactic Star Formation with NIKA2 (GASTON): Evidence of mass accretion onto dense clumps
A. J. Rigby, R. Adam, P. Ade +49
High-mass stars () play a crucial role in the evolution of galaxies, and so it is imperative that we understand how they are formed. We have used the New…
Morphisms and minimisation of weighted automata
Sylvain Lombardy, Jacques Sakarovitch
This paper studies the algorithms for the minimisation of weighted automata. It starts with the definition of morphisms-which generalises and unifies the notion of bisimulation to…
Refined Commonsense Knowledge from Large-Scale Web Contents
Tuan-Phong Nguyen, Simon Razniewski, Julien Romero +1
Commonsense knowledge (CSK) about concepts and their properties is helpful for AI applications. Prior works, such as ConceptNet, have compiled large CSK collections. However, they…
Probing the role of magnetic fields in star-forming filaments: NIKA2-Pol commissioning results toward OMC-1
H. Ajeddig, R. Adam, P. Ade +43
Dust polarization observations are a powerful, practical tool to probe the geometry (and to some extent, the strength) of magnetic fields in star-forming regions. In particular, Pl…