Laboratoire Jean Kuntzmann

Learning realistic human actions from movies

International audience

Action recognition by dense trajectories

Feature trajectories have shown to be efficient for rep-resenting videos. Typically, they are extracted using the KLT tracker or matching SIFT descriptors between frames. Howeve...

Evaluation of CMIP6 DECK Experiments With CNRM‐CM6‐1

Abstract This paper describes the main characteristics of CNRM‐CM6‐1, the fully coupled atmosphere‐ocean general circulation model of sixth generation jointly developed by Centr...

End-to-End Incremental Learning

Combining efficient object localization and image classification

International audience

Solving Variational Inequalities with Stochastic Mirror-Prox Algorithm

In this paper we consider iterative methods for stochastic variational inequalities (s.v.i.) with monotone operators. Our basic assumption is that the operator possesses both sm...