Zobrazeno 1 - 10
of 217
pro vyhledávání: '"Apprentissage non supervisé"'
Autor:
Guillon, Louise
Publikováno v:
Medical Imaging. Université Paris-Saclay, 2023. English. ⟨NNT : 2023UPAST058⟩
One of the visual characteristics of the brain is its folded appearance. It is composed of convolutions called gyri, which are delimited by furrows called sulci. Like fingerprints, the patterns of cortical folding, i.e. the arrangement, characteristi
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=od______3515::40d0febaa9d7304b61034d71ba7c35bf
https://theses.hal.science/tel-04100135/file/120972_GUILLON_2023_archivage.pdf
https://theses.hal.science/tel-04100135/file/120972_GUILLON_2023_archivage.pdf
Autor:
Mudumba, Sai Rajeswar
Les formes, les surfaces, les événements et les objets (vivants et non vivants) constituent le monde. L'intelligence des agents naturels, tels que les humains, va au-delà de la simple reconnaissance de formes. Nous excellons à construire des repr
Externí odkaz:
http://hdl.handle.net/1866/27485
Autor:
Chen, Hao
Publikováno v:
Machine Learning [cs.LG]. Université Côte d'Azur, 2022. English. ⟨NNT : 2022COAZ4014⟩
As a core component of intelligent video surveillance systems, person re-identification (ReID) targets at retrieving a person of interest across non-overlapping cameras. Despite significant improvements in supervised ReID, cumbersome annotation proce
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=dedup_wf_001::0af7caca20949a161afd113e09f93426
https://theses.hal.science/tel-03783651
https://theses.hal.science/tel-03783651
Autor:
Vo, Huy V.
Publikováno v:
Artificial Intelligence [cs.AI]. Ecole normale supérieure-ENS PARIS, 2022. English. ⟨NNT : ⟩
Object detectors are important components of intelligent systems such as autonomous vehicles or robots. They are typically obtained with fully-supervised training, which requires large manually annotated datasets whose construction is time-consuming
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=dedup_wf_001::ee289958c174b074858fb50da92dadbc
https://hal.science/tel-03919952
https://hal.science/tel-03919952
Autor:
Chabert-Liddell, Saint-Clair
This thesis deals with the development of statistical methods for the analysis of collections of interaction networks through three original contributions. Interaction networks are a natural way to represent in graph form the exchanges or relationshi
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=dedup_wf_001::7dd40fa606e8e3eba6eb30710e7c0ad5
https://hal.archives-ouvertes.fr/tel-03629379
https://hal.archives-ouvertes.fr/tel-03629379
Autor:
Antonazzo, Filippo
Publikováno v:
Data Structures and Algorithms [cs.DS]. Université de Lille, 2022. English. ⟨NNT : 2022ULILB015⟩
Statistics [math.ST]. Université de Lille, 2022. English. ⟨NNT : ⟩
Statistics [math.ST]. Université de Lille, 2022. English. ⟨NNT : ⟩
Clustering reveals all its interest when the data set size considerably increases, since there is the opportunity to discover tiny but possibly high value clusters, which can not be detected with moderate sample sizes. However, the clustering of such
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=dedup_wf_001::3fe75bf7693d2ff1066ed2d94bec5b7a
https://theses.hal.science/tel-03846222
https://theses.hal.science/tel-03846222
Autor:
Caron, Mathilde
Publikováno v:
Artificial Intelligence [cs.AI]. Université Grenoble Alpes [2020-..], 2021. English. ⟨NNT : 2021GRALM066⟩
Humans and many animals can see the world and understand it effortlessly which gives some hope that visual perception could be realized by computers and Artificial Intelligence. More importantly, living beings acquire such an understanding of the vis
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=od_______165::083546f6988bd0ce9c906a9a06bc115b
https://theses.hal.science/tel-03675254/document
https://theses.hal.science/tel-03675254/document
Autor:
Sun, Qiaoqiao
Publikováno v:
Signal and Image processing. Ecole Centrale Marseille, 2021. English. ⟨NNT : 2021ECDM0008⟩
This thesis is devoted to analyzing and processing hyperspectral images mainly with deep learning methods. To fully exploit the spectral-spatial information of hyperspectral data, convolutional neural network with parameter tuning is proposed for hyp
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=od______3430::bd0273c2ce9dbc0f3c31e53a9660c5c9
https://theses.hal.science/tel-03643897
https://theses.hal.science/tel-03643897
Autor:
Schreuder, Nicolas
Publikováno v:
Statistics [math.ST]. Institut Polytechnique de Paris, 2021. English. ⟨NNT : 2021IPPAG004⟩
Machine learning algorithms are celebrated for their impressive performance on many tasksthat we thought were dedicated to human minds, from handwritten digits recognition (LeCunet al. 1990) to cancer prognosis (Kourou et al. 2015). Nevertheless, as
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=dedup_wf_001::15c59fae23f52279076d7c3a2eca7e72
https://tel.archives-ouvertes.fr/tel-03435618
https://tel.archives-ouvertes.fr/tel-03435618
Autor:
Meunier, Etienne, Bouthemy, Patrick
Publikováno v:
ORASIS 2021-18ème édition des journées francophones des jeunes chercheurs en vision par ordinateur
ORASIS 2021-18ème édition des journées francophones des jeunes chercheurs en vision par ordinateur, Centre National de la Recherche Scientifique [CNRS], Sep 2021, Saint Ferréol, France. pp.1-8
ORASIS 2021-18ème édition des journées francophones des jeunes chercheurs en vision par ordinateur, Centre National de la Recherche Scientifique [CNRS], Sep 2021, Saint Ferréol, France. pp.1-8
International audience; Cet article s’intéresse à la localisation des mouvements saillants dans les images successives d’une séquence vidéo. Un mouvement saillant est un mouvement se démarquant de son contexte environnant. Notre méthode s
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=dedup_wf_001::372461f83fcdfebf6a68bb77f9240ac4
https://hal.archives-ouvertes.fr/hal-03339650/file/Orasis_2021_Meunier.pdf
https://hal.archives-ouvertes.fr/hal-03339650/file/Orasis_2021_Meunier.pdf