Zobrazeno 1 - 10 of 19 pro vyhledávání: '"Berthelier, Anthony"'
1
Report
Learning Sparse Filters in Deep Convolutional Neural Networks with a l1/l2 Pseudo-Norm
Autor: Berthelier, Anthony, Yan, Yongzhe, Chateau, Thierry, Blanc, Christophe, Duffner, Stefan, Garcia, Christophe
While deep neural networks (DNNs) have proven to be efficient for numerous tasks, they come at a high memory and computation cost, thus making them impractical on resource-limited devices. However, these networks are known to contain a large number o
Externí odkaz: http://arxiv.org/abs/2007.10022
Zobrazit plný text záznamu
2
Report
Facial Landmark Correlation Analysis
Autor: Yan, Yongzhe, Duffner, Stefan, Phutane, Priyanka, Berthelier, Anthony, Blanc, Christophe, Garcia, Christophe, Chateau, Thierry
We present a facial landmark position correlation analysis as well as its applications. Although numerous facial landmark detection methods have been presented in the literature, few of them explicitly take into account the inherent relationship amon
Externí odkaz: http://arxiv.org/abs/1911.10576
Zobrazit plný text záznamu
3
Report
2D Wasserstein Loss for Robust Facial Landmark Detection
Autor: Yan, Yongzhe, Duffner, Stefan, Phutane, Priyanka, Berthelier, Anthony, Blanc, Christophe, Garcia, Christophe, Chateau, Thierry
The recent performance of facial landmark detection has been significantly improved by using deep Convolutional Neural Networks (CNNs), especially the Heatmap Regression Models (HRMs). Although their performance on common benchmark datasets has reach
Externí odkaz: http://arxiv.org/abs/1911.10572
Zobrazit plný text záznamu
7
Etudes techniques de compression de réseaux de neurones pour sa mise en place dans une architecture embarquée de type Smartphone
Autor: Berthelier, Anthony
Publikováno v: Electronique. Université Clermont Auvergne, 2021. Français. ⟨NNT : 2021UCFAC086⟩
Over the past years, deep neural networks have proved to be an essential element for developing intelligent solutions. They have achieved remarkable performances at a cost of a large size with deeper layers and millions of parameters. Therefore utili
Externí odkaz: https://explore.openaire.eu/search/publication?articleId=dedup_wf_001::cfff63234ca6a984e46a002ddf9d544a
https://theses.hal.science/tel-03663958
Zobrazit plný text záznamu
9
Akademický článek
Tento výsledek nelze pro nepřihlášené uživatele zobrazit.
K zobrazení výsledku je třeba se přihlásit.
10
Human Hair Segmentation In The Wild Using Deep Shape Prior
Autor: Yan, Yongzhe, Berthelier, Anthony, Duffner, Stefan, Naturel, Xavier, Garcia, Christophe, Chateau, Thierry
Publikováno v: Conference on Computer Vision and Pattern Recognition Workshop (CVPR Workshop)
Conference on Computer Vision and Pattern Recognition Workshop (CVPR Workshop), Jun 2019, Long Beach, United States
International audience; Virtual human hair dying is becoming a popular Augmented Reality (AR) application in recent years. Human hair contains diverse color and texture information which can be significantly varied from case to case depending on diff
Externí odkaz: https://explore.openaire.eu/search/publication?articleId=dedup_wf_001::475a6bd5fc4a333a38eb67b243dc0984
https://hal.archives-ouvertes.fr/hal-02891974/file/23_CVPRW_hair_segmentation.pdf
Zobrazit plný text záznamu

Vyhledávací nástroje:

Upřesnit hledání

Omezení vyhledávání
Plný text Recenzováno Digitální knihovna AV ČR
Zdroje