Zobrazeno 1 - 10
of 22
pro vyhledávání: '"Matheus Gutoski"'
Publikováno v:
IEEE Access, Vol 9, Pp 137029-137041 (2021)
Automatically understanding and describing the visual content of videos in natural language is a challenging task in computer vision. Existing approaches are often designed to describe single events in a closed-set setting. However, in real-world sce
Externí odkaz:
https://doaj.org/article/5b762188817647b281b645e62d871926
Publikováno v:
IEEE Access, Vol 8, Pp 86520-86535 (2020)
In One-Class Classification (OCC) problems, the classifier is trained with samples of a class considered normal, such that exceptional patterns can be identified as anomalies. Indeed, for real-world problems, the representation of the normal class in
Externí odkaz:
https://doaj.org/article/44edcd8134fe49619bbfa3e59b283c8d
Autor:
Leandro Takeshi Hattori, Matheus Gutoski, Heitor Silvério Lopes, Marcelo Romero, Manassés Ribeiro
Publikováno v:
Learning and Nonlinear Models. 18:56-65
Transfer learning is a paradigm that consists in training and testing classifiers with datasets drawn from distinct distributions. This technique allows to solve a particular problem using a model that was trained for another purpose. In the recent y
Publikováno v:
IEEE Access, Vol 9, Pp 137029-137041 (2021)
Automatically understanding and describing the visual content of videos in natural language is a challenging task in computer vision. Existing approaches are often designed to describe single events in a closed-set setting. However, in real-world sce
Publikováno v:
Neural Computing and Applications. 33:1207-1220
Human action recognition (HAR) is a topic widely studied in computer vision and pattern recognition. Despite the success of recent models for this issue, most of them approach HAR from the closed-set perspective. The closed-set recognition works unde
Publikováno v:
IEEE Access, Vol 8, Pp 86520-86535 (2020)
In One-Class Classification (OCC) problems, the classifier is trained with samples of a class considered normal, such that exceptional patterns can be identified as anomalies. Indeed, for real-world problems, the representation of the normal class in
Publikováno v:
Anais do 15. Congresso Brasileiro de Inteligência Computacional.
Typical semantic segmentation methods do not recognize unknown pixels during the test or deployment stage. This capability is critical for open-world environment applications where unseen objects appear all the time. Recently, to solve those limitati
Publikováno v:
Anais do 14. Congresso Brasileiro de Inteligência Computacional.
Autor:
André Eugênio Lazzaretti, Andrei de Souza Inácio, Matheus Gutoski, Anderson Brilhador, Leandro Takeshi Hattori, Heitor Silvério Lopes
Publikováno v:
LA-CCI
The Pixel-Level Classification of crops and weeds is an open problem in computer vision. The use of agrochemicals is necessary for effective weed control, but one of the great challenges of precision agriculture is to reduce their use while maintaini
Autor:
Brenda Cinthya Solari Berno, Matheus Gutoski, Andrei de Souza Inácio, Leandro Takeshi Hattori, Ademir Cristiano Gabardo, Heitor Silvério Lopes
Publikováno v:
LA-CCI
Co-purchase analysis is becoming an essential task for e-commerce businesses as it enables to predict new purchases and understand customer behavior. In this paper, we propose a novel framework to analyze books sales from co-purchase and visual data.