Zobrazeno 1 - 10
of 65
pro vyhledávání: '"Juan José Pantrigo"'
Autor:
Alfredo Cuesta-Infante, Antonio S. Montemayor, Kenia Picos, Ulises Orozco-Rosas, Juan José Pantrigo
Publikováno v:
IEEE Access. 10:84648-84663
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::357abc4c4ffba81f3f3089fd0f20afda
https://doi.org/10.1109/access.2022.3197628
https://doi.org/10.1109/access.2022.3197628
Publikováno v:
Neurocomputing. 379:64-73
Deep Bayesian Networks are a hot topic in Deep Learning because this approach makes it possible to minimize both the epistemic and the homoscedastic uncertainty at the same time self balancing multiple and complementary losses for a given task, simpl
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::6b954bba2e9af0e3f409729bda474944
https://doi.org/10.1016/j.neucom.2019.09.101
https://doi.org/10.1016/j.neucom.2019.09.101
Publikováno v:
Bio-inspired Systems and Applications: from Robotics to Ambient Intelligence ISBN: 9783031065262
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::e758d4c007200c1dabfcbf67e55d4f47
https://doi.org/10.1007/978-3-031-06527-9_23
https://doi.org/10.1007/978-3-031-06527-9_23
Publikováno v:
Bio-inspired Systems and Applications: from Robotics to Ambient Intelligence ISBN: 9783031065262
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::412cc0d02f9d639712f326de7c2b0dae
https://doi.org/10.1007/978-3-031-06527-9_58
https://doi.org/10.1007/978-3-031-06527-9_58
Publikováno v:
Expert Systems with Applications. 212:118580
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::ea047e30555362b7863c9648336c423b
https://doi.org/10.1016/j.eswa.2022.118580
https://doi.org/10.1016/j.eswa.2022.118580
Publikováno v:
Neurocomputing. 323:335-343
In this paper we present a deep learning based method to estimate the human pose in 3D when multiple 2D views are available. Our system is composed of a cascade of specialized systems. Firstly, 2D poses are obtained using a deep neural network for th
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::034cfe1814c9522eb363aaf6b0637a3c
https://doi.org/10.1016/j.neucom.2018.10.009
https://doi.org/10.1016/j.neucom.2018.10.009
Publikováno v:
Advances in Artificial Intelligence ISBN: 9783030857127
CAEPIA
CAEPIA
Human activity recognition is a challenging problem, where deep learning methods are showing to be very efficient. In this paper we propose the use of capsule networks. This type of networks have proved to generalize better to novel viewpoints than c
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::59536d761e731757bfde7f48e78909f7
https://doi.org/10.1007/978-3-030-85713-4_8
https://doi.org/10.1007/978-3-030-85713-4_8
Publikováno v:
Pattern Recognition. 76:80-94
Combination of a Convolutional Neural Network (CNN) and a Long Short-Term Memory (LSTM) recurrent network for skeleton-based human activity and hand gesture recognition.Two-stage training strategy which firstly focuses on the CNN training and, second
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::2786e421b2d2e5947596f34273022631
https://doi.org/10.1016/j.patcog.2017.10.033
https://doi.org/10.1016/j.patcog.2017.10.033
Autor:
Gema Anguita, Jose Luis Moreno, Alfredo Cuesta-Infante, Luciano Palombarani, Iván Ramírez, Valvanera Alonso, Juan José Pantrigo, Antonio S. Montemayor
Publikováno v:
Neural Computing and Applications. 32:13203-13211
In this paper, we propose a twofold methodology for visual detection and recognition of different types of city dumpsters, with minimal human labeling of the image data set. Firstly, we carry out transfer learning by using Google Inception-v3 convolu
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::ac4bac59f4c269d50ececd244d4999bc
https://doi.org/10.1007/s00521-018-3390-8
https://doi.org/10.1007/s00521-018-3390-8
Publikováno v:
Neural Computing and Applications. 32:13175-13181
We present a detection method that is able to detect a learned target and is valid for both static and moving cameras. As an application, we detect pedestrians, but could be anything if there is a large set of images of it. The data set is fed into a
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::e5a14e77cb77e09d1e947840679d85da
https://doi.org/10.1007/s00521-017-3197-z
https://doi.org/10.1007/s00521-017-3197-z