Zobrazeno 1 - 10
of 28
pro vyhledávání: '"Salvador España-Boquera"'
Autor:
Francisco J Zamora-Martínez, Salvador España-Boquera, Maria Jose Castro-Bleda, Adrian Palacios-Corella
Publikováno v:
PLoS ONE, Vol 13, Iss 7, p e0200884 (2018)
This paper presents a new method to reduce the computational cost when using Neural Networks as Language Models, during recognition, in some particular scenarios. It is based on a Neural Network that considers input contexts of different length in or
Externí odkaz:
https://doaj.org/article/000f48235b364425bd8d49ffac18c9bb
Publikováno v:
Revista de Geografía Agrícola. :61-79
El aguacate es un superalimento de moda, muy rentable. México es el primer productor mundial y Michoacán el primero nacional. El objetivo fue cartografiar el cultivo del aguacate en Michoacán con imágenes Sentinel-2 e identificar las principales
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::b4995c5bba4b4078508ee71238059b01
https://doi.org/10.5154/r.rga.2022.69.03
https://doi.org/10.5154/r.rga.2022.69.03
Publikováno v:
Language Resources and Evaluation. 56:1009-1022
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::15467c991afb75a1ff574f4ca21f0f41
https://doi.org/10.1007/s10579-022-09587-3
https://doi.org/10.1007/s10579-022-09587-3
The NoisyOffice Database: A Corpus To Train Supervised Machine Learning Filters For Image Processing
Autor:
Salvador España-Boquera, Maria Jose Castro-Bleda, Joan Pastor-Pellicer, Francisco Zamora-Martínez
Publikováno v:
RiuNet. Repositorio Institucional de la Universitat Politécnica de Valéncia
instname
instname
[EN] This paper presents the `NoisyOffice¿ database. It consists of images of printed text documents with noise mainly caused by uncleanliness from a generic office, such as coffee stains and footprints on documents or folded and wrinkled sheets wit
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::55d6501f287fed7ccdc12ed661e177e7
Autor:
Benedicto Crespo-Facorro, José Miguel Carot, Iluminada Corripio, Maria Jose Castro-Bleda, Luis Martí-Bonmatí, Jose Manuel Rubio, Gracián García-Martí, Salvador España-Boquera, Julio Sanjuán, Pau Soldevila-Matías
BACKGROUND: Recently there has been an increasing interest in the use of machine learning techniques to neuroimaging data, in order to discriminate patients with schizophrenia from healthy control. However, until now, these tools have not been useful
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::66ebc189bdfa5ce603392348752e4874
https://europepmc.org/articles/PMC6455209/
https://europepmc.org/articles/PMC6455209/
Autor:
Maria Jose Castro-Bleda, Francisco Zamora-Martínez, Salvador España-Boquera, Joan Pastor-Pellicer
Publikováno v:
RiuNet. Repositorio Institucional de la Universitat Politécnica de Valéncia
instname
instname
[EN] Recent improvements in deep learning techniques show that deep models can extract more meaningful data directly from raw signals than conventional parametrization techniques, making it possible to avoid specific feature extraction in the area of
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::12688e0e688a1bf3343adb70594b3baa
http://hdl.handle.net/10251/138465
http://hdl.handle.net/10251/138465
Autor:
Maria Jose Castro-Bleda, Salvador España-Boquera, Adrian Palacios-Corella, Francisco Zamora-Martínez
Publikováno v:
PLoS ONE, Vol 13, Iss 7, p e0200884 (2018)
PLoS ONE
RiuNet. Repositorio Institucional de la Universitat Politécnica de Valéncia
instname
PLoS ONE
RiuNet. Repositorio Institucional de la Universitat Politécnica de Valéncia
instname
[EN] This paper presents a new method to reduce the computational cost when using Neural Networks as Language Models, during recognition, in some particular scenarios. It is based on a Neural Network that considers input contexts of different length
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::7409bccfeaf6cd2ac1e25041c85d1c5d
http://europepmc.org/articles/PMC6062053?pdf=render
http://europepmc.org/articles/PMC6062053?pdf=render
Autor:
Josep Silva, Salvador España-Boquera, Alvaro Hermida-Perez, David Guerrero-Lopez, José Vicente Benlloch-Dualde
Publikováno v:
ITHET
Computer programming courses require a lot of practice. Nevertheless, the difficulties found when trying to install the computer programming environment used in the university courses prevent many students from practicing at home. Hence, they can onl
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::a9543e3b962c4dc63130f59aa261d93c
https://doi.org/10.1109/ithet.2017.8067822
https://doi.org/10.1109/ithet.2017.8067822
Autor:
Salvador España Boquera
Publikováno v:
RiuNet. Repositorio Institucional de la Universitat Politécnica de Valéncia
instname
instname
[EN] This work is focused on problems (like automatic speech recognition (ASR) and handwritten text recognition (HTR)) that: 1) can be represented (at least approximately) in terms of one-dimensional sequences, and 2) solving these problems entails b
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::74950d219df7cfa100e7719d2e7ecf8b
A combined Convolutional Neural Network and Dynamic Programming approach for text line normalization
Autor:
Salvador España-Boquera, Francisco Zamora-Martínez, Maria Jose Castro-Bleda, Joan Pastor-Pellicer
Publikováno v:
ICDAR
This work proposes a new normalization algorithm for handwritten text lines based on the use of Convolutional Neural Networks trained to classify pixels of the scanned text line as belonging to the main body area. The reference lines of the text line
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::77c492d078fd1abbdd84410260134af1
https://doi.org/10.1109/icdar.2015.7333780
https://doi.org/10.1109/icdar.2015.7333780