Records |
Author |
Patricia L. Suarez; Angel D. Sappa; Boris X. Vintimilla |
Title |
Infrared Image Colorization based on a Triplet DCGAN Architecture. |
Type |
Conference Article |
Year |
2017 |
Publication |
13th IEEE Workshop on Perception Beyond the Visible Spectrum – In conjunction with CVPR 2017. (This paper has been selected as “Best Paper Award” ) |
Abbreviated Journal |
|
Volume |
2017-July |
Issue |
|
Pages |
212-217 |
Keywords |
|
Abstract |
|
Address |
|
Corporate Author |
|
Thesis |
|
Publisher |
|
Place of Publication |
|
Editor |
|
Language |
|
Summary Language |
|
Original Title |
|
Series Editor |
|
Series Title |
|
Abbreviated Series Title |
|
Series Volume |
|
Series Issue |
|
Edition |
|
ISSN |
|
ISBN |
|
Medium |
|
Area |
|
Expedition |
|
Conference |
|
Notes |
|
Approved |
no |
Call Number |
cidis @ cidis @ |
Serial |
62 |
Permanent link to this record |
|
|
|
Author |
Patricia L. Suarez; Angel D. Sappa; Boris X. Vintimilla |
Title |
Image patch similarity through a meta-learning metric based approach |
Type |
Conference Article |
Year |
2019 |
Publication |
15th International Conference on Signal Image Technology & Internet based Systems (SITIS 2019); Sorrento, Italia |
Abbreviated Journal |
|
Volume |
|
Issue |
|
Pages |
511-517 |
Keywords |
|
Abstract |
Comparing images regions are one of the core methods used on computer vision for tasks like image classification, scene understanding, object detection and recognition. Hence, this paper proposes a novel approach to determine similarity of image regions (patches), in order to obtain the best representation of image patches. This problem has been studied by many researchers presenting different approaches, however, the ability to find the better criteria to measure the similarity on image regions are still a challenge. The present work tackles this problem using a few-shot metric based meta-learning framework able to compare image regions and determining a similarity measure to decide if there is similarity between the compared patches. Our model is training end-to-end from scratch. Experimental results
have shown that the proposed approach effectively estimates the similarity of the patches and, comparing it with the state of the art approaches, shows better results. |
Address |
|
Corporate Author |
|
Thesis |
|
Publisher |
|
Place of Publication |
|
Editor |
|
Language |
|
Summary Language |
|
Original Title |
|
Series Editor |
|
Series Title |
|
Abbreviated Series Title |
|
Series Volume |
|
Series Issue |
|
Edition |
|
ISSN |
|
ISBN |
|
Medium |
|
Area |
|
Expedition |
|
Conference |
|
Notes |
|
Approved |
no |
Call Number |
gtsi @ user @ |
Serial |
115 |
Permanent link to this record |
|
|
|
Author |
Patricia L. Suarez, Dario Carpio, Angel Sappa |
Title |
Boosting Guided Super-Resolution Performance with Synthesized Images |
Type |
Conference Article |
Year |
2023 |
Publication |
17th International Conference On Signal Image Technology & Internet Based Systems |
Abbreviated Journal |
|
Volume |
|
Issue |
|
Pages |
|
Keywords |
|
Abstract |
|
Address |
|
Corporate Author |
|
Thesis |
|
Publisher |
|
Place of Publication |
|
Editor |
|
Language |
|
Summary Language |
|
Original Title |
|
Series Editor |
|
Series Title |
|
Abbreviated Series Title |
|
Series Volume |
|
Series Issue |
|
Edition |
|
ISSN |
|
ISBN |
|
Medium |
|
Area |
|
Expedition |
|
Conference |
|
Notes |
|
Approved |
no |
Call Number |
cidis @ cidis @ |
Serial |
225 |
Permanent link to this record |
|
|
|
Author |
Patricia L. Suarez, Dario Carpio, Angel Sappa |
Title |
Depth Map Estimation from a Single 2D Image |
Type |
Conference Article |
Year |
2023 |
Publication |
17th International Conference On Signal Image Technology & Internet Based Systems |
Abbreviated Journal |
|
Volume |
|
Issue |
|
Pages |
|
Keywords |
|
Abstract |
|
Address |
|
Corporate Author |
|
Thesis |
|
Publisher |
|
Place of Publication |
|
Editor |
|
Language |
|
Summary Language |
|
Original Title |
|
Series Editor |
|
Series Title |
|
Abbreviated Series Title |
|
Series Volume |
|
Series Issue |
|
Edition |
|
ISSN |
|
ISBN |
|
Medium |
|
Area |
|
Expedition |
|
Conference |
|
Notes |
|
Approved |
no |
Call Number |
cidis @ cidis @ |
Serial |
226 |
Permanent link to this record |
|
|
|
Author |
Patricia L. Suarez, Dario Carpio, Angel D. Sappa and Henry O. Velesaca |
Title |
Transformer based Image Dehazing. |
Type |
Conference Article |
Year |
2022 |
Publication |
16TH International Conference On Signal Image Technology & Internet Based Systems SITIS 2022. |
Abbreviated Journal |
|
Volume |
|
Issue |
|
Pages |
148-154 |
Keywords |
|
Abstract |
|
Address |
|
Corporate Author |
|
Thesis |
|
Publisher |
|
Place of Publication |
|
Editor |
|
Language |
|
Summary Language |
|
Original Title |
|
Series Editor |
|
Series Title |
|
Abbreviated Series Title |
|
Series Volume |
|
Series Issue |
|
Edition |
|
ISSN |
|
ISBN |
|
Medium |
|
Area |
|
Expedition |
|
Conference |
|
Notes |
|
Approved |
no |
Call Number |
cidis @ cidis @ |
Serial |
195 |
Permanent link to this record |
|
|
|
Author |
Patricia L. Suárez, Dario Carpio, and Angel Sappa |
Title |
Non-Homogeneous Haze Removal through a Multiple Attention Module Architecture. |
Type |
Conference Article |
Year |
2021 |
Publication |
16 International Symposium on Visual Computing. Octubre 4-6, 2021. Lecture Notes in Computer Science |
Abbreviated Journal |
|
Volume |
13018 |
Issue |
|
Pages |
178-190 |
Keywords |
|
Abstract |
|
Address |
|
Corporate Author |
|
Thesis |
|
Publisher |
|
Place of Publication |
|
Editor |
|
Language |
|
Summary Language |
|
Original Title |
|
Series Editor |
|
Series Title |
|
Abbreviated Series Title |
|
Series Volume |
|
Series Issue |
|
Edition |
|
ISSN |
|
ISBN |
|
Medium |
|
Area |
|
Expedition |
|
Conference |
|
Notes |
|
Approved |
no |
Call Number |
cidis @ cidis @ |
Serial |
162 |
Permanent link to this record |
|
|
|
Author |
Patricia L. Suárez, Angel D. Sappa, Boris X. Vintimilla |
Title |
Cycle generative adversarial network: towards a low-cost vegetation index estimation |
Type |
Conference Article |
Year |
2021 |
Publication |
IEEE International Conference on Image Processing (ICIP 2021) |
Abbreviated Journal |
|
Volume |
2021-September |
Issue |
|
Pages |
2783-2787 |
Keywords |
CyclicGAN, NDVI, near infrared spectra, instance normalization. |
Abstract |
This paper presents a novel unsupervised approach to estimate the Normalized Difference Vegetation Index (NDVI).The NDVI is obtained as the ratio between information from the visible and near infrared spectral bands; in the current work, the NDVI is estimated just from an image of the visible spectrum through a Cyclic Generative Adversarial Network (CyclicGAN). This unsupervised architecture learns to estimate the NDVI index by means of an image translation between the red channel of a given RGB image and the NDVI unpaired index’s image. The translation is obtained by means of a ResNET architecture and a multiple loss function. Experimental results obtained with this unsupervised scheme show the validity of the implemented model. Additionally, comparisons with the state of the art approaches are provided showing improvements with the proposed approach. |
Address |
|
Corporate Author |
|
Thesis |
|
Publisher |
|
Place of Publication |
|
Editor |
|
Language |
|
Summary Language |
|
Original Title |
|
Series Editor |
|
Series Title |
|
Abbreviated Series Title |
|
Series Volume |
|
Series Issue |
|
Edition |
|
ISSN |
|
ISBN |
|
Medium |
|
Area |
|
Expedition |
|
Conference |
|
Notes |
|
Approved |
no |
Call Number |
cidis @ cidis @ |
Serial |
164 |
Permanent link to this record |
|
|
|
Author |
Patricia L. Suárez, Angel D. Sappa and Boris X. Vintimilla |
Title |
Deep learning-based vegetation index estimation |
Type |
Book Chapter |
Year |
2021 |
Publication |
Generative Adversarial Networks for Image-to-Image Translation Book. |
Abbreviated Journal |
|
Volume |
Chapter 9 |
Issue |
Issue 2 |
Pages |
205-232 |
Keywords |
|
Abstract |
|
Address |
|
Corporate Author |
|
Thesis |
|
Publisher |
|
Place of Publication |
|
Editor |
|
Language |
|
Summary Language |
|
Original Title |
|
Series Editor |
|
Series Title |
|
Abbreviated Series Title |
|
Series Volume |
|
Series Issue |
|
Edition |
|
ISSN |
|
ISBN |
|
Medium |
|
Area |
|
Expedition |
|
Conference |
|
Notes |
|
Approved |
no |
Call Number |
cidis @ cidis @ |
Serial |
137 |
Permanent link to this record |
|
|
|
Author |
Pabelco Zambrano, Fernanda Calderon, Héctor Villegas, Jonathan Paillacho, Doménica Pazmiño, Miguel Realpe |
Title |
UAV Remote Sensing applications and current trends in crop monitoring and diagnostics: A Systematic Literature Review |
Type |
Conference Article |
Year |
2023 |
Publication |
IEEE 13th International Conference on Pattern Recognition Systems (ICPRS) 2023, julio 4-7 |
Abbreviated Journal |
|
Volume |
|
Issue |
|
Pages |
|
Keywords |
|
Abstract |
|
Address |
|
Corporate Author |
|
Thesis |
|
Publisher |
|
Place of Publication |
|
Editor |
|
Language |
|
Summary Language |
|
Original Title |
|
Series Editor |
|
Series Title |
|
Abbreviated Series Title |
|
Series Volume |
|
Series Issue |
|
Edition |
|
ISSN |
|
ISBN |
979-835033337-4 |
Medium |
|
Area |
|
Expedition |
|
Conference |
|
Notes |
|
Approved |
no |
Call Number |
cidis @ cidis @ |
Serial |
214 |
Permanent link to this record |
|
|
|
Author |
Ortiz J.; Londono J.; Novillo F.; Ampuno A.; Chávez M. |
Title |
Determinación de Invariantes en Grandes Centros de Datos basados en Topología Fat-Tree |
Type |
Journal Article |
Year |
2015 |
Publication |
Revista Politécnica |
Abbreviated Journal |
|
Volume |
Vol. 35 |
Issue |
|
Pages |
pp. 91-96 |
Keywords |
Invariantes de red, topologías, Fat-tree, simulación, emulación |
Abstract |
Durante los últimos años ha existido un fuerte incremento en el acceso a internet, causando que los centros de datos ( DC) deban adaptar dinámicamente su infraestructura de red de cara a enfrentar posibles problemas de congestión, la cual no siempre se da de forma oportuna. Ante esto, nuevas topologías de red se han propuesto en los últimos años, como una forma de brindar mejores condiciones para el manejo de tráfico interno, sin embargo es común que para el estudio de estas mejoras, se necesite recrear el comportamiento de un verdadero DC en modelos de simulación/emulación. Por lo tanto se vuelve esencial validar dichos modelos, de cara a obtener resultados coherentes con la realidad. Esta validación es posible por medio de la identificación de ciertas propiedades que se deducen a partir de las variables y los parámetros que describen la red, y que se mantienen en las topologías de los DC para diversos escenarios y/o configuraciones. Estas propiedades, conocidas como invariantes, son una expresión del funcionamiento de la red en ambientes reales, como por ejemplo la ruta más larga entre dos nodos o el número de enlaces mínimo que deben fallar antes de una pérdida de conectividad en alguno de los nodos de la red. En el presente trabajo se realiza la identificación, formulación y comprobación de dos invariantes para la topología Fat-Tree, utilizando como software emulador a mininet. Las conclusiones muestran resultados concordantes entre lo analítico y lo práctico. |
Address |
|
Corporate Author |
|
Thesis |
|
Publisher |
Escuela Politécnica Nacional |
Place of Publication |
|
Editor |
|
Language |
Español |
Summary Language |
Español |
Original Title |
|
Series Editor |
|
Series Title |
|
Abbreviated Series Title |
|
Series Volume |
|
Series Issue |
|
Edition |
|
ISSN |
|
ISBN |
|
Medium |
|
Area |
|
Expedition |
|
Conference |
|
Notes |
|
Approved |
no |
Call Number |
cidis @ cidis @ |
Serial |
32 |
Permanent link to this record |