Zobrazeno 1 - 10
of 20
pro vyhledávání: '"Frigo, Oriel"'
In this paper we present a new approach for feature fusion between RGB and LWIR Thermal images for the task of semantic segmentation for driving perception. We propose DooDLeNet, a double DeepLab architecture with specialized encoder-decoders for the
Externí odkaz:
http://arxiv.org/abs/2204.10266
Graph Context Encoder: Graph Feature Inpainting for Graph Generation and Self-supervised Pretraining
We propose the Graph Context Encoder (GCE), a simple but efficient approach for graph representation learning based on graph feature masking and reconstruction. GCE models are trained to efficiently reconstruct input graphs similarly to a graph autoe
Externí odkaz:
http://arxiv.org/abs/2106.10124
Deep learning based molecular graph generation and optimization has recently been attracting attention due to its great potential for de novo drug design. On the one hand, recent models are able to efficiently learn a given graph distribution, and ma
Externí odkaz:
http://arxiv.org/abs/2106.13318
Despite quick progress in the last few years, recent studies have shown that modern graph neural networks can still fail at very simple tasks, like detecting small cycles. This hints at the fact that current networks fail to catch information about t
Externí odkaz:
http://arxiv.org/abs/2011.15069
Autoencoder reconstructions are widely used for the task of unsupervised anomaly localization. Indeed, an autoencoder trained on normal data is expected to only be able to reconstruct normal features of the data, allowing the segmentation of anomalou
Externí odkaz:
http://arxiv.org/abs/2002.03734
Deep learning based molecular graph generation and optimization has recently been attracting attention due to its great potential for de novo drug design. On the one hand, recent models are able to efficiently learn a given graph distribution, and ma
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::d410e6fb617fb8700d33eeae6a4c6617
http://arxiv.org/abs/2106.13318
http://arxiv.org/abs/2106.13318
Akademický článek
Tento výsledek nelze pro nepřihlášené uživatele zobrazit.
K zobrazení výsledku je třeba se přihlásit.
K zobrazení výsledku je třeba se přihlásit.
Autor:
Frigo, Oriel
Publikováno v:
Image Processing. Université Paris Descartes (Paris 5), 2016. English
Image Processing [eess.IV]. Université Paris Descartes (Paris 5), 2016. English
Image Processing [eess.IV]. Université Paris Descartes (Paris 5), 2016. English
The objective of this thesis is to provide new techniques for example-based video editing. We address three related problems: color transfer, tonal stabilization and style transfer. The first problem consists in transferring colors from anexample ima
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=dedup_wf_001::1cdb38c7ecb5f83e41df2e188c058003
https://theses.hal.science/tel-01477096
https://theses.hal.science/tel-01477096
Publikováno v:
GRETSI 2015
GRETSI 2015, Sep 2015, Lyon, France
GRETSI 2015, Sep 2015, Lyon, France
In this work, we present a fast and parametric method to achieve tonal stabilization in videos containing color fluctuations. Our main contribution is to compensate tonal instabilities with a color transformation guided by dominant motion estimated b
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=dedup_wf_001::134be71795634bfef19fc9983f783486
https://hal.archives-ouvertes.fr/hal-01256950
https://hal.archives-ouvertes.fr/hal-01256950
Akademický článek
Tento výsledek nelze pro nepřihlášené uživatele zobrazit.
K zobrazení výsledku je třeba se přihlásit.
K zobrazení výsledku je třeba se přihlásit.