75 citations
- Institut national de recherche en sciences et technologies du numériqueFR29 papers
- Centre Inria de l'Université de LilleFR18 papers
- Centre National de la Recherche ScientifiqueFR15 papers
- Université de LilleFR12 papers
- École Polytechnique Fédérale de LausanneCH6 papers
- Centre de Recherche en Informatique, Signal et Automatique de LilleFR4 papers
- Laboratoire d'Informatique, Signaux et Systèmes de Sophia AntipolisFR3 papers
- Universidad de SevillaES3 papers
- Université Côte d'AzurFR3 papers
- Carnegie Mellon UniversityUS2 papers
- Dynamic Imaging (United Kingdom)GB2 papers
- École Centrale de LilleFR2 papers
79 papers
Analysis of Diffusion Models for Manifold Data
Anand Jerry George, Rodrigo Veiga, Nicolas Macris
We analyze the time reversed dynamics of generative diffusion models. If the exact empirical score function is used in a regime of large dimension and exponentially large number of…
Spin-orbital excitations encoding the magnetic phase transition in the van der Waals antiferromagnet FePS
Yuan Wei, Yi Tseng, Hebatalla Elnaggar +13
In the rich phases of van der Waals (vdW) materials featuring intertwined electronic order and collective phenomena, characterizing elementary dynamics that entail the low-energy H…
Graph Neural Networks for Electric and Hydraulic Data Fusion to Enhance Short-term Forecasting of Pumped-storage Hydroelectricity
Raffael Theiler, Olga Fink
Pumped-storage hydropower plants (PSH) actively participate in grid power-frequency control and therefore often operate under dynamic conditions, which results in rapidly varying s…
Automatic Annotation of Direct Speech in Written French Narratives
Noé Durandard, Viet-Anh Tran, Gaspard Michel +1
The automatic annotation of direct speech (AADS) in written text has been often used in computational narrative understanding. Methods based on either rules or deep neural networks…
Non-decreasing Payment Rules for Combinatorial Auctions
Vitor Bosshard, Ye Wang, Sven Seuken
Combinatorial auctions are used to allocate resources in domains where bidders have complex preferences over bundles of goods. However, the behavior of bidders under different paym…
2D versus 3D Convolutional Spiking Neural Networks Trained with Unsupervised STDP for Human Action Recognition
Mireille El-Assal, Pierre Tirilly, Ioan Marius Bilasco
Current advances in technology have highlighted the importance of video analysis in the domain of computer vision. However, video analysis has considerably high computational costs…