Zobrazeno 1 - 6
of 6
pro vyhledávání: '"B. G. Vijay Kumar"'
Publikováno v:
Lecture Notes in Computer Science ISBN: 9783031200588
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::49b69037d25c093f4319fd6283289e11
https://doi.org/10.1007/978-3-031-20059-5_42
https://doi.org/10.1007/978-3-031-20059-5_42
Publikováno v:
Computer Vision – ECCV 2018 ISBN: 9783030012304
ECCV (6)
ECCV (6)
In generalized zero shot learning (GZSL), the set of classes are split into seen and unseen classes, where training relies on the semantic features of the seen and unseen classes and the visual representations of only the seen classes, while testing
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::74ce4c7a46fa8417c89213c3436c1da3
https://doi.org/10.1007/978-3-030-01231-1_2
https://doi.org/10.1007/978-3-030-01231-1_2
Publikováno v:
Image and Vision Computing. 30:279-291
In this paper we introduce a supervised, maximum margin framework for linear and non-linear Non-negative Matrix Factorization. By contrast to existing methods in which the matrix factorization phase (i.e. the feature extraction phase) and the classif
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::f2df4f6bf3ff1c18755c2b7269ae09ec
https://doi.org/10.1016/j.imavis.2012.02.010
https://doi.org/10.1016/j.imavis.2012.02.010
Autor:
B. G. Vijay Kumar, Ioannis Patras
Publikováno v:
FG
Most of the existing methods that adopt the Implicit Shape Model (ISM) for action localization learn the dictionary (codebook) in an unsupervised manner. In contrast to this, we present a supervised approach to learn a dictionary for action localizat
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::be2ea89c15481d5d391c372f7a3d4543
https://doi.org/10.1109/fg.2013.6553745
https://doi.org/10.1109/fg.2013.6553745
Autor:
Ioannis Patras, B. G. Vijay Kumar
Publikováno v:
CVPR Workshops
In this work we present a discriminative codebook weighting approach for action detection. We learn global and local weights for the codewords by considering the spatio-temporal Hough voting space of the training sequences. In contrast to the Implici
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::a8068da5c55b37ae17806b8cfc2c8a02
https://doi.org/10.1109/cvprw.2012.6239257
https://doi.org/10.1109/cvprw.2012.6239257
Publikováno v:
BMVC
In this paper, we propose a maximum-margin framework for classification using Non-negative Matrix Factorization. In contrast to previous approaches where the classification and matrix factorization are separated, we incorporate the maximum margin con
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::c4e0118fdd4fa7d36b0f87d64cc9d938
https://doi.org/10.5244/c.25.129
https://doi.org/10.5244/c.25.129