Výsledky vyhledávání - "Guillermo Ortiz-Jimenez"

Optimism in the Face of Adversity: Understanding and Improving Deep Learning through Adversarial Robustness

Autor: Apostolos Modas, Pascal Frossard, Guillermo Ortiz-Jimenez, Seyed-Mohsen Moosavi-Dezfooli

Driven by massive amounts of data and important advances in computational resources, new deep learning systems have achieved outstanding results in a large spectrum of applications. Nevertheless, our current theoretical understanding on the mathemati

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_dedup___::d7c29e892ff397982cf8195876902903
http://arxiv.org/abs/2010.09624

Zobrazit plný text záznamu

Forward-Backward Splitting for Optimal Transport Based Problems

Autor: Guillermo Ortiz-Jimenez, Hermina Petric Maretic, Mireille El Gheche, Pascal Frossard, Effrosyni Simou

Publikováno v: ICASSP

Optimal transport aims to estimate a transportation plan that minimizes a displacement cost. This is realized by optimizing the scalar product between the sought plan and the given cost, over the space of doubly stochastic matrices. When the entropy

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_dedup___::b6c351b612b6b88c17abffc2ea49d94e
https://doi.org/10.1109/icassp40776.2020.9053335

Zobrazit plný text záznamu

On the choice of graph neural network architectures

Autor: Pascal Frossard, Clement Vignac, Guillermo Ortiz-Jimenez

Publikováno v: ICASSP

Seminal works on graph neural networks have primarily targeted semi-supervised node classification problems with few observed labels and high-dimensional signals. With the development of graph networks, this setup has become a de facto benchmark for

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_dedup___::318e56950702de8aee290864c580c250
http://arxiv.org/abs/1911.05384

Zobrazit plný text záznamu

Simulation framework for a 3-D high-resolution imaging radar at 300 GHz with a scattering model based on rendering techniques

Autor: Rafael Pagés, Federico Garcia-Rial, Luis Ubeda-Medina, Guillermo Ortiz-Jimenez, Jesus Grajal, Narciso Garcia

Publikováno v: IEEE Transactions on teraHertz Science and Technology, ISSN 2156-342X, 2017, Vol. 7, No. 4
Archivo Digital UPM
Universidad Politécnica de Madrid

We present a simulation framework for a 3-D high-resolution imaging radar at 300 GHz with mechanical scanning. This tool allows us to reproduce the imaging capabilities of the radar in different setups and with different targets. The simulations are

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_dedup___::1c7ed3d54536202618771ea11e82d213
https://oa.upm.es/50818/

Zobrazit plný text záznamu

Sparse Sampling for Inverse Problems With Tensors

Autor: Guillermo Ortiz-Jimenez, Sundeep Prabhakar Chepuri, Geert Leus, Mario Coutino

Publikováno v: IEEE Transactions on Signal Processing, 67(12)

We consider the problem of designing sparse sampling strategies for multidomain signals, which can be represented using tensors that admit a known multilinear decomposition. We leverage the multidomain structure of tensor signals and propose to acqui

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_dedup___::0595057073ee592f3902b38eded84940
https://infoscience.epfl.ch/record/266851

Zobrazit plný text záznamu

Vyhledávací nástroje:

Upřesnit hledání