@InProceedings{GattoFukuJśniSant:2021:AdSuLe,
author = "Gatto, Bernardo B. and Fukui, Kazuhiro and J{\'u}nior, Waldir S.
S. and Santos, Eulanda M. dos",
affiliation = "{Federal University of Amazonas} and {University of Tsukuba} and
{Federal University of Amazonas} and {Federal University of
Amazonas}",
title = "Advances in subspace learning and its applications",
booktitle = "Proceedings...",
year = "2021",
editor = "Paiva, Afonso and Menotti, David and Baranoski, Gladimir V. G. and
Proen{\c{c}}a, Hugo Pedro and Junior, Antonio Lopes Apolinario
and Papa, Jo{\~a}o Paulo and Pagliosa, Paulo and dos Santos,
Thiago Oliveira and e S{\'a}, Asla Medeiros and da Silveira,
Thiago Lopes Trugillo and Brazil, Emilio Vital and Ponti, Moacir
A. and Fernandes, Leandro A. F. and Avila, Sandra",
organization = "Conference on Graphics, Patterns and Images, 34. (SIBGRAPI)",
publisher = "Sociedade Brasileira de Computa{\c{c}}{\~a}o",
address = "Porto Alegre",
keywords = "Subspace representation, shallow networks, manifold learning,
tensor analysis.",
abstract = "Pattern-set matching refers to a class of problems where learning
takes place through sets rather than elements. Much used in
computer vision, this approach presents robustness to variations
such as illumination, intrinsic parameters of the signal capture
devices, and pose of the analyzed object. Inspired by applications
of subspace analysis, three new collections of methods are
presented in this thesis\$^{1}\$ summary: (1) New
representations for two-dimensional sets; (2) Shallow networks for
image classification; and (3) Tensor data representation by
subspaces. New representations are proposed to preserve the
spatial structure and maintain a fast processing time. We also
introduce a technique to keep temporal structure, even using the
principal component analysis, which classically does not model
sequences. In shallow networks, we present two convolutional
neural networks that do not require backpropagation, employing
only subspaces for their convolution filters. These networks
present advantages when the training time and hardware resources
are scarce. Finally, to handle tensor data, such as videos, we
propose methods that employ subspaces for representation in a
compact and discriminative way. Our proposed work has been applied
in problems other than computer vision, such as representation and
classification of bioacoustics and text patterns.",
conference-location = "Gramado, RS, Brazil (virtual)",
conference-year = "18-22 Oct. 2021",
language = "en",
ibi = "8JMKD3MGPEW34M/45DFJGB",
url = "http://urlib.net/ibi/8JMKD3MGPEW34M/45DFJGB",
targetfile = "sibgrapi_camera_ready.pdf",
urlaccessdate = "2024, May 07"
}