Zobrazeno 1 - 7
of 7
pro vyhledávání: '"Juan I. Forcen"'
Publikováno v:
Academica-e. Repositorio Institucional de la Universidad Pública de Navarra
Universitat Jaume I
Universitat Jaume I
Spatial pooling is an important step in computer vision systems like Convolutional Neural Networks or the Bag-of-Words method. The spatial pooling purpose is to combine neighbouring descriptors to obtain a single descriptor for a given region (local
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::923ac35c2e17411bcbb6e3e4598940f2
http://arxiv.org/abs/2007.01243
http://arxiv.org/abs/2007.01243
Autor:
Edurne Barrenechea, Miguel Pagola, Zdenko Takáč, Juan I. Forcen, Abdulrahman H. Altalhi, Humberto Bustince
Publikováno v:
Academica-e. Repositorio Institucional de la Universidad Pública de Navarra
instname
instname
In this work we study the relation between moderate deviation functions, restricted dissimilarity functions and restricted equivalence functions. We use moderate deviation functions in order to measure the similarity or dissimilarity between a given
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::96364321fa7336cb9ead982ff254edad
https://hdl.handle.net/2454/36157
https://hdl.handle.net/2454/36157
Publikováno v:
Pattern Recognition and Image Analysis ISBN: 9783030313319
IbPRIA (1)
IbPRIA (1)
Image retrieval can be tackled using deep features from pre trained Convolutional Neural Networks (CNN). The feature map from the last convolutional layer of a CNN encodes descriptive information from which a discriminative global descriptor can be o
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::7dd81fa895d02c1e55c0ba743dd90a00
https://doi.org/10.1007/978-3-030-31332-6_48
https://doi.org/10.1007/978-3-030-31332-6_48
Autor:
Humberto Bustince, Jose Manuel Soto-Hidalgo, Juan I. Forcen, Miguel Pagola, Jesús Chamorro-Martínez
Publikováno v:
FUZZ-IEEE
Color is a powerful feature for image analysis but it is usually not used in image classification schemes. We propose a method to combine fuzzy color information with the result obtained from a One-Versus-All classifier (OVA) trained with Bag-of-feat
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::1bc5c21eb0dd641eecc0a368659ca238
https://doi.org/10.1109/fuzz-ieee.2017.8015622
https://doi.org/10.1109/fuzz-ieee.2017.8015622
Publikováno v:
FUZZ-IEEE
Feature aggregation is a crucial step in many methods of image classification, like the Bag-of-Words (BoW) model or the Convolutional Neural Networks (CNN). In this aggregation step, usually known as spatial pooling, the descriptors of neighbouring e
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::6e2ea18c5abdb9822a0e64f84f920eef
https://doi.org/10.1109/fuzz-ieee.2017.8015606
https://doi.org/10.1109/fuzz-ieee.2017.8015606
Publikováno v:
Pattern Recognition and Image Analysis ISBN: 9783319588377
IbPRIA
IbPRIA
Bag-of-Words methods can be robust to image scaling, translation, and occlusion. An important step in this methodology, and other visual recognition systems like Convolutional Neural Networks, is spatial pooling, where the descriptors of neighbouring
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::51d74604eb41f9c7a1c36f52f1530b07
https://doi.org/10.1007/978-3-319-58838-4_48
https://doi.org/10.1007/978-3-319-58838-4_48
Publikováno v:
Applied Soft Computing. 84:105698
Image classification is a multi-class problem that is usually tackled with ensembles of binary classifiers. Furthermore, one of the most important challenges in this field is to find a set of highly discriminative image features for reaching a good p
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::dcf665ccf33b2191f308be528174772d
https://doi.org/10.1016/j.asoc.2019.105698
https://doi.org/10.1016/j.asoc.2019.105698