Spatio-Temporal Neural Network for Fitting and Forecasting COVID-19

no code implementations • 22 Mar 2021 • Yi-Shuai Niu, Wentao Ding, Junpeng Hu, Wenxu Xu, Stephane Canu

We established a Spatio-Temporal Neural Network, namely STNN, to forecast the spread of the coronavirus COVID-19 outbreak worldwide in 2020.

Unsupervised Domain Adaptation for Person Re-Identification through Source-Guided Pseudo-Labeling

no code implementations • 20 Sep 2020 • Fabian Dubourvieux, Romaric Audigier, Angelique Loesch, Samia Ainouz, Stephane Canu

A challenge for re-ID is the performance preservation when a model is used on data of interest (target data) which belong to a different domain from the training data domain (source data).

Metric Learning Person Re-Identification +2

L 1-norm double backpropagation adversarial defense

no code implementations • 5 Mar 2019 • Ismaïla Seck, Gaëlle Loosli, Stephane Canu

Adversarial examples are a challenging open problem for deep neural networks.

Adversarial Defense

Non-convex Regularizations for Feature Selection in Ranking With Sparse SVM

no code implementations • 2 Jul 2015 • Léa Laporte, Rémi Flamary, Stephane Canu, Sébastien Déjean, Josiane Mothe

Feature selection in learning to rank has recently emerged as a crucial issue.

feature selection Learning-To-Rank