R
Rafael Molina
Researcher at University of Granada
Publications - 398
Citations - 11970
Rafael Molina is an academic researcher from University of Granada. The author has contributed to research in topics: Image restoration & Iterative reconstruction. The author has an hindex of 52, co-authored 381 publications receiving 10765 citations. Previous affiliations of Rafael Molina include Intel & Northwestern University.
Papers
More filters
Book ChapterDOI
Combining Attention-based Multiple Instance Learning and Gaussian Processes for CT Hemorrhage Detection
TL;DR: In this article, an attention-based multiple instance learning (Att-MIL) approach is proposed to diagnose intracranial hemorrhage (ICH) using a combination of an Att-CNN and a variational Gaussian Process for Multiple Instance Learning (VGPMIL) model.
Proceedings ArticleDOI
Local Bayesian image restoration using variational methods and Gamma-Normal distributions
TL;DR: A new Bayesian methodology for the restoration of blurred and noisy images using a spatially varying image prior utilizing a Gamma-Normal hyperprior distribution on the local precision parameters.
Proceedings ArticleDOI
Variational Bayesian inference image restoration using a product of total variation-like image priors
TL;DR: Numerical experiments are shown which demonstrate that image restoration based on this prior compares favorably with previous state-of-the-art restoration algorithms.
Capacidad de inducción metabólica de las verduras más consumidas habitualmente
Juan María Llobet,A. Ballesta,S. Mas,M. J. Lafuente,T. W. Kensler,Nuria Laso,A. Lafuente,Rafael Molina +7 more
TL;DR: In this paper, an estudio descriptivo in vitro de la capacidad de induccion metabolica de 15 verduras (15 verduran seleccionadas) that se consumen habitualmente.
Proceedings ArticleDOI
Learning filters in Gaussian process classification problems
TL;DR: This work utilizes Bayesian modeling and inference to jointly learn a classifier and estimate an optimal filterbank, and shows that the proposed method compares favorably with other classification/filtering approaches, without the need of parameter tuning.