Matthieu Ospici
Matthieu Ospici
Bull / Atos
Verified email at
Cited by
Cited by
Density functional theory calculation on many-cores hybrid central processing unit-graphic processing unit architectures
L Genovese, M Ospici, T Deutsch, JF Méhaut, A Neelov, S Goedecker
The Journal of chemical physics 131 (3), 2009
Daubechies wavelets for high performance electronic structure calculations: The BigDFT project
L Genovese, B Videau, M Ospici, T Deutsch, S Goedecker, JF Méhaut
Comptes Rendus Mécanique 339 (2-3), 149-164, 2011
Are adversarial robustness and common perturbation robustness independant attributes?
A Laugros, A Caplier, M Ospici
Proceedings of the IEEE/CVF International Conference on Computer Vision …, 2019
Addressing neural network robustness with mixup and targeted labeling adversarial training
A Laugros, A Caplier, M Ospici
Computer Vision–ECCV 2020 Workshops: Glasgow, UK, August 23–28, 2020 …, 2020
Online unsupervised domain adaptation for person re-identification
H Rami, M Ospici, S Lathuilière
Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern …, 2022
SGPU 2: a runtime system for using of large applications on clusters of hybrid nodes
M Ospici, D Komatitsch, JF Méhaut, T Deutsch
Second Workshop on Hybrid Multi-core Computing, held in conjunction with …, 2011
T. Deutsc h, JF Mehaut, A. Neelov, SJ Goedecker
L Genovese, M Ospici
Chem. Phys, 34103, 2009
Using synthetic corruptions to measure robustness to natural distribution shifts
A Laugros, A Caplier, M Ospici
arXiv preprint arXiv:2107.12052, 2021
Prediction of fish location by combining fisheries data and sea bottom temperature forecasting
M Ospici, K Sys, S Guegan-Marat
International Conference on Image Analysis and Processing, 437-448, 2022
Using the overlapping score to improve corruption benchmarks
A Laugros, A Caplier, M Ospici
2021 IEEE International Conference on Image Processing (ICIP), 959-963, 2021
Exploitation et partage de GPU dans des grappes de calcul hybrides
M Ospici, L Genovese, T Deutsch
Rencontres francophones du Parallélisme (RenPar’19), 2009
Person re-identification across different datasets with multi-task learning
M Ospici, A Cecchi
arXiv preprint arXiv:1807.09666, 2018
Modèles de programmation et d'exécution pour les architectures parallèles et hybrides. Applications à des codes de simulation pour la physique.
M Ospici
Université de Grenoble, 2013
Wavelet-based density functional theory calculation on massively parallel hybrid architectures
L Genovese, M Ospici, B Videau, T Deutsch, JF Mehaut
GPU Computing Gems Emerald Edition, 133-151, 2011
Method for calibrating an object re-identification solution implementing an array of a plurality of cameras
M Ospici
US Patent App. 17/961,510, 2023
Method for training an image analysis neural network, and object re-identification method implementing such a neural network
M Ospici
US Patent App. 17/901,135, 2023
Floor Plan Reconstruction from Sparse Views: Combining Graph Neural Network with Constrained Diffusion
A Gueze, M Ospici, D Rohmer, MP Cani
Proceedings of the IEEE/CVF International Conference on Computer Vision …, 2023
Automatic extraction of attributes of an object within a set of digital images
A Cecchi, M Ospici, P Paleo
US Patent 11,256,945, 2022
Increasing the Coverage and Balance of Robustness Benchmarks by Using Non-Overlapping Corruptions
A LAUGROS, A Caplier, M Ospici
The system can't perform the operation now. Try again later.
Articles 1–19