Zobrazeno 1 - 10
of 169
pro vyhledávání: '"Bombrun, Lionel"'
Publikováno v:
IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), IEEE/CVF, Jun 2024, Seattle, United States
The deployment of safe and trustworthy machine learning systems, and particularly complex black box neural networks, in real-world applications requires reliable and certified guarantees on their performance. The conformal prediction framework offers
Externí odkaz:
http://arxiv.org/abs/2406.08884
Publikováno v:
2023 IEEE/CVF International Conference on Computer Vision Workshops (ICCVW), IEEE/CVF, Oct 2023, Paris, France
As deep learning predictive models become an integral part of a large spectrum of precision agricultural systems, a barrier to the adoption of such automated solutions is the lack of user trust in these highly complex, opaque and uncertain models. In
Externí odkaz:
http://arxiv.org/abs/2308.15094
Autor:
Ribeiro, Vinícius Silva Osterne, Bombrun, Lionel, Nobre, Juvêncio Santos, Cavalcante, Charles Casimiro, Berthoumieu, Yannick
Publikováno v:
In Signal Processing July 2024 220
Akademický článek
Tento výsledek nelze pro nepřihlášené uživatele zobrazit.
K zobrazení výsledku je třeba se přihlásit.
K zobrazení výsledku je třeba se přihlásit.
The present paper shows that warped Riemannian metrics, a class of Riemannian metrics which play a prominent role in Riemannian geometry, are also of fundamental importance in information geometry. Precisely, the paper features a new theorem, which s
Externí odkaz:
http://arxiv.org/abs/1707.07163
A novel efficient method for content-based image retrieval (CBIR) is developed in this paper using both texture and color features. Our motivation is to represent and characterize an input image by a set of local descriptors extracted at characterist
Externí odkaz:
http://arxiv.org/abs/1611.02102
Akademický článek
Tento výsledek nelze pro nepřihlášené uživatele zobrazit.
K zobrazení výsledku je třeba se přihlásit.
K zobrazení výsledku je třeba se přihlásit.
The Riemannian geometry of covariance matrices has been essential to several successful applications, in computer vision, biomedical signal and image processing, and radar data processing. For these applications, an important ongoing challenge is to
Externí odkaz:
http://arxiv.org/abs/1607.06929
Data which lie in the space $\mathcal{P}_{m\,}$, of $m \times m$ symmetric positive definite matrices, (sometimes called tensor data), play a fundamental role in applications including medical imaging, computer vision, and radar signal processing. An
Externí odkaz:
http://arxiv.org/abs/1507.01760
Autor:
Bombrun, Lionel
Le travail de recherche présenté dans ce mémoire de thèse est dédié au développement des méthodes en télédétection radar polarimétrique et interférométrique. L'interférométrie radar à synthèse d'ouverture renseigne sur la topographi
Externí odkaz:
http://tel.archives-ouvertes.fr/tel-00930170
http://tel.archives-ouvertes.fr/docs/00/93/01/70/PDF/2008_Lionel_Bombrun_Th.pdf
http://tel.archives-ouvertes.fr/docs/00/93/01/70/PDF/2008_Lionel_Bombrun_Th.pdf