Zobrazeno 1 - 3
of 3
pro vyhledávání: '"Salah Rifai"'
Publikováno v:
Advances in Intelligent Systems and Computing ISBN: 9783319126098
ICPRAM (Selected Papers)
ICPRAM (Selected Papers)
Classifying scenes (e.g. into “street”, “home” or “leisure”) is an important but complicated task nowadays, because images come with variability, ambiguity, and a wide range of illumination or scale conditions. Standard approaches build a
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::9a5799bf1093c039158dc57492d0a482
https://doi.org/10.1007/978-3-319-12610-4_13
https://doi.org/10.1007/978-3-319-12610-4_13
Publikováno v:
Computer Vision – ECCV 2012 ISBN: 9783642337826
ECCV (6)
ECCV (6)
We propose a semi-supervised approach to solve the task of emotion recognition in 2D face images using recent ideas in deep learning for handling the factors of variation present in data. An emotion classification algorithm should be both robust to (
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::1cec599bec7be1fbcbac2169c1995069
https://doi.org/10.1007/978-3-642-33783-3_58
https://doi.org/10.1007/978-3-642-33783-3_58
Autor:
Pascal Vincent, Xavier Muller, Salah Rifai, Grégoire Mesnil, Yann N. Dauphin, Yoshua Bengio, Xavier Glorot
Publikováno v:
Machine Learning and Knowledge Discovery in Databases ISBN: 9783642237829
ECML/PKDD (2)
ECML/PKDD (2)
We propose a novel regularizer when training an autoencoder for unsupervised feature extraction. We explicitly encourage the latent representation to contract the input space by regularizing the norm of the Jacobian (analytically) and the Hessian (st
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::22c1a294a3cabe87c999c4c901f67dcc
https://doi.org/10.1007/978-3-642-23783-6_41
https://doi.org/10.1007/978-3-642-23783-6_41