Zobrazeno 1 - 10
of 43
pro vyhledávání: '"Roberto Hirata Junior"'
Autor:
Erik Miguel de Elias, Vinicius Sanches Carriel, Guilherme Werneck De Oliveira, Aldri Luiz Dos Santos, Michele Nogueira, Roberto Hirata Junior, Daniel Macedo Batista
Publikováno v:
2022 IEEE Latin-American Conference on Communications (LATINCOM).
Publikováno v:
2019 XV Workshop de Visão Computacional (WVC).
Acquiring an OMR (Optical Mark Recognition) reading equipment can be impracticable to some companies or individuals due to its costs. Computational software solutions can be more attractive, but they require specific page format or page layout, such
Publikováno v:
Journal of Mathematical Imaging and Vision. 16:199-222
The design of an aperture operator is based on adequately constraining the spatial domain and the graylevel range in order to diminish the space of operators and, consequently, the estimation error. The design of a resolution constrained operator is
Publikováno v:
SIBGRAPI
In the reversible conversion of color images to gray ones, colors are mapped to textures and from the textures the receiver can recover the colors, i.e. one may print a color image with a black and white printer and, at a later time, recover colors.
Autor:
Rodrigo Carvalho Borges
Publikováno v:
Biblioteca Digital de Teses e Dissertações da USP
Universidade de São Paulo (USP)
instacron:USP
Universidade de São Paulo (USP)
instacron:USP
Music streaming platforms have become popular in the last decades due to the increasing number of tracks available online. The track catalogues offered by these platforms are usually too big to be searched manually, and automatic recommendation algor
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::7e53984a13644a9444ca7e19ce93ad15
Autor:
Sarah Pires Pérez
Publikováno v:
Biblioteca Digital de Teses e Dissertações da USP
Universidade de São Paulo (USP)
instacron:USP
Universidade de São Paulo (USP)
instacron:USP
Art is the means by which humanity has always expressed itself, as art oers a record of humanitys feelings, its ways of life and its conception of the world. Although we are fortunate to have a vast store of cultural wealth from past generations, the
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::a9b58978731d4e75d70a47ec5aa46ff2
Autor:
Antonio Augusto Abello
Publikováno v:
Biblioteca Digital de Teses e Dissertações da USP
Universidade de São Paulo (USP)
instacron:USP
Universidade de São Paulo (USP)
instacron:USP
Convolutional Neural Networks (CNNs) recently became the state-of-the-art for various Computer Vision tasks. However, for reasons not completely understood, they are very sensitive to low resolution images. This can be troublesome as real life applic
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::bb473fcb2f35dcd97959472bd3f215fa
Autor:
Eric K. Tokuda
Publikováno v:
Biblioteca Digital de Teses e Dissertações da USP
Universidade de São Paulo (USP)
instacron:USP
Universidade de São Paulo (USP)
instacron:USP
Nowadays, images are generated on a large scale and in a decentralized way. Such modality of data carries valuable information but extracting this information is not always trivial. In this thesis, we tackle computer vision challenges when using grou
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::b481da3d2065a6eaed4dd1483fd74421
https://doi.org/10.11606/t.45.2019.tde-20012021-191240
https://doi.org/10.11606/t.45.2019.tde-20012021-191240
Publikováno v:
Biblioteca Digital de Teses e Dissertações da USP
Universidade de São Paulo (USP)
instacron:USP
Universidade de São Paulo (USP)
instacron:USP
Machine learning classifiers construct decision boundaries that partition data space into a set of regions to which labels are assigned. Understanding these decision boundaries can notably help the actual practical usage of such classifiers (by answe
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::dd34289e6257a2bbf55c33f48f6e5c3b
https://doi.org/10.11606/t.45.2020.tde-27112020-071803
https://doi.org/10.11606/t.45.2020.tde-27112020-071803
Autor:
Felipe de Souza Salvatore
Publikováno v:
Biblioteca Digital de Teses e Dissertações da USP
Universidade de São Paulo (USP)
instacron:USP
Universidade de São Paulo (USP)
instacron:USP
Natural language inference (NLI) is the task of determining the entailment relationship between a pair of sentences. We are interested in the problem of verifying whether the deep learning models current used in NLI satisfy some logical properties. I
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::922acea6bd1b84ca796456c49f8d344f