259 citations · 978 across the 60 of their papers we have counts for
3 papers · 1 filter
Sequentially Generated Instance-Dependent Image Representations for Classification
Gabriel Dulac-Arnold, Ludovic Denoyer, Nicolas Thome +2
In this paper, we investigate a new framework for image classification that adaptively generates spatial representations. Our strategy is based on a sequential process that learns…
Learning Information Spread in Content Networks
Cédric Lagnier, Simon Bourigault, Sylvain Lamprier +2
We introduce a model for predicting the diffusion of content information on social media. When propagation is usually modeled on discrete graph structures, we introduce here a cont…
Learning States Representations in POMDP
Gabriella Contardo, Ludovic Denoyer, Thierry Artieres +1
We propose to deal with sequential processes where only partial observations are available by learning a latent representation space on which policies may be accurately learned.