1 code implementation • 14 Sep 2023 • Mathieu Seraphim, Alexis Lechervy, Florian Yger, Luc Brun, Olivier Etard
In recent years, Transformer-based auto-attention mechanisms have been successfully applied to the analysis of a variety of context-reliant data types, from texts to images and beyond, including data from non-Euclidean geometries.
Ranked #1 on Sleep Stage Detection on MASS SS3 (Macro-averaged Accuracy metric)
no code implementations • 24 Jul 2023 • Stevan Stanovic, Benoit Gaüzère, Luc Brun
Convolutional Neural Networks (CNNs) have enabled major advances in image classification through convolution and pooling.
no code implementations • 2 Aug 2022 • Stevan Stanovic, Benoit Gaüzère, Luc Brun
Consequently, our method does not discard any vertex information nor artificially increase the density of the graph.
no code implementations • 29 Nov 2021 • Luc Brun, Benoit Gaüzère, Sébastien Bougleux, Florian Yger
Conversely, the remaining elements of V2 correspond to the image of the epsilon pseudo element of V1.
no code implementations • 5 Jul 2019 • Nicolas Boria, David B. Blumenthal, Sébastien Bougleux, Luc Brun
Among different classes of heuristic algorithms that were proposed to compute approximate solutions, local search based algorithms provide the tightest upper bounds for GED.
no code implementations • 26 Jun 2019 • Nicolas Boria, S'ebastien Bougleux, Benoit Gaüzère, Luc Brun
Computing a graph prototype may constitute a core element for clustering or classification tasks.
no code implementations • 20 May 2019 • Xuan Nguyen, Luc Brun, Olivier Lezoray, Sébastien Bougleux
In this paper, we propose a new hand gesture recognition method based on skeletal data by learning SPD matrices with neural networks.
no code implementations • CVPR 2019 • Xuan Son Nguyen, Luc Brun, Olivier Lézoray, Sébastien Bougleux
A new type of layer is proposed for the third stage, based on a variant of stochastic gradient descent on Stiefel manifolds.