Zobrazeno 1 - 7
of 7
pro vyhledávání: '"Maxim Peterson"'
Publikováno v:
Pattern Recognition Letters. 80:24-29
A meta-model approach for autoencoders is presented.New modification of autoencoder's learning algorithm is proposed.Developed meta-model provides faster training in terms of consumed training samples. The problem of training autoencoders (with logis
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::ffc46adefb8d673aac0424e1463c60b9
https://doi.org/10.1016/j.patrec.2016.05.018
https://doi.org/10.1016/j.patrec.2016.05.018
Autor:
Nikolai Skorobogatko, Alexey Potapov, Oleg Scherbakov, Innokentii Zhdanov, Sergey Rodionov, Maxim Peterson
Publikováno v:
Artificial General Intelligence ISBN: 9783319976754
AGI
AGI
What frameworks and architectures are necessary to create a vision system for AGI? In this paper, we propose a formal model that states the task of perception within AGI. We show the role of discriminative and generative models in achieving efficient
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::22ac3ac8aaac65faa81a9ab9c1acab4a
https://doi.org/10.1007/978-3-319-97676-1_18
https://doi.org/10.1007/978-3-319-97676-1_18
Publikováno v:
IFIP Advances in Information and Communication Technology ISBN: 9783319920061
Person re-identification (Re-ID) is the task of matching humans across cameras with non-overlapping views that has important applications in visual surveillance. Like other computer vision tasks, this task has gained much with the utilization of deep
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::d8a661515c3d4d2b6b97ea8cb0c4ef7a
https://doi.org/10.1007/978-3-319-92007-8_7
https://doi.org/10.1007/978-3-319-92007-8_7
Autor:
A. V. Yashchenko, Sergey Rodionov, Maxim Peterson, O. V. Shcherbakov, Innokentii Zhdanov, Alexey Potapov
Publikováno v:
Journal of Optical Technology. 86:769
Generative neural network models for visual concept learning and the problem of approximating image distribution density are studied. A criterion for an image to belong to a simulated class is introduced based on an estimate of the probability in the
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::724c64177f94d9161d682feffa8c2707
https://doi.org/10.1364/jot.86.000769
https://doi.org/10.1364/jot.86.000769
Publikováno v:
Progress in Pattern Recognition, Image Analysis, Computer Vision, and Applications ISBN: 9783319125671
AIAI
AIAI
Deep learning is promising approach to extract useful nonlinear representations of data. However, it is usually applied with large training sets, which are not always available in practical tasks. In this paper, we consider stacked autoencoders with
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::44cf1b16a1c089bfd60d63c5fe3357a0
https://doi.org/10.1007/978-3-662-44654-6_25
https://doi.org/10.1007/978-3-662-44654-6_25
Publikováno v:
AIP Conference Proceedings.
The paper describes an approach to integrating the structural methods in correlation algorithms for dense depth map construction from a stereo pair. The main idea is to modify the matrix of correlation energy according to the result of structural ana
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::bad437e901862d711a8880150c31e748
https://doi.org/10.1063/1.4809688
https://doi.org/10.1063/1.4809688
Publikováno v:
Journal of Physics: Conference Series. 536:012013
We consider image features on the base of histograms of oriented gradients (HOG) with addition of contour curvature histogram (HOG-CH), and also compare it with results of known scale-invariant feature transform (SIFT) approach in application to retr
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::01ba8f6be5b5d7b0822a79583f369055
https://doi.org/10.1088/1742-6596/536/1/012013
https://doi.org/10.1088/1742-6596/536/1/012013