Learning representations using neural networks and optimal transport

Autor: Harchaoui, Warith

Publikováno v: Neural and Evolutionary Computing [cs.NE]. Université de Paris, 2020. English. ⟨NNT : 2020UNIP7215⟩
Neural and Evolutionary Computing [cs.NE]. Université de Paris, 2020. English

The last decade has seen neural networks become a reference tool in statistical learning. Indeed, this technology has established itself as an essential tool for data types as varied as images, text, sound, etc. in large scales settings. The success

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=dedup_wf_001::dc8b0cd0954938953354f291b829ae8f
https://tel.archives-ouvertes.fr/tel-03370529/document

Analyse Automatique des Macro et Micro Expressions Faciales : Détection et Reconnaissance par Machine Learning

Autor: Al Chanti, Dawood

Publikováno v: Signal and Image processing. Université Grenoble Alpes, 2019. English. ⟨NNT : 2019GREAT058⟩
Image Processing [eess.IV]. UGA (Université Grenoble Alpes), 2019. English

Facial expression analysis is an important problem in many biometric tasks, such as face recognition, face animation, affective computing and human computer interface. In this thesis, we aim at analyzing facial expressions using images and video sequ

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=dedup_wf_001::6b519cd0d513b982ac2c7cc95d9926a7
https://tel.archives-ouvertes.fr/tel-02525707/document

Patch-based Bayesian approaches for image restoration

Autor: Dai, Dai Viet

Publikováno v: Medical Imaging. Universite Paris 13; Sorbonne Paris Cité, 2018. English

In this thesis, we investigate the patch-based image denoising and super-resolution under the Bayesian Maximum A Posteriori framework, with the help of a set of high quality images which are known as standard images. Our contributions are to address

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=dedup_wf_001::6380094db09862cb46e6faab2d3b72b9
https://hal.archives-ouvertes.fr/tel-01825225

Modèles de covariance pour l'analyse et la classification de signaux électroencéphalogrammes

Autor: Spinnato, Juliette

Cette thèse s’inscrit dans le contexte de l’analyse et de la classification de signaux électroencéphalogrammes (EEG) par des méthodes d’analyse discriminante. Ces signaux multi-capteurs qui sont, par nature, très fortement corrélés spati

Externí odkaz: http://www.theses.fr/2015AIXM4727/document

Classification automatique à base de modèle et choix de modèles pour les données discrétisées

Autor: Wu, Jingwen

Publikováno v: Other. Supélec, 2014. English. ⟨NNT : 2014SUPL0005⟩

This thesis studies the Gaussian mixture model-based clustering approaches and the criteria of model selection for binned data clustering. Fourteen binned-EM algorithms and fourteen bin-EM-CEM algorithms are developed for fourteen parsimonious Gaussi

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=od______2592::958dcc607eb8a232a06bf2c97a8817f6
https://theses.hal.science/tel-01142358