Patch-level Spatial Layout for Classification and Weakly Supervised Localization (CROSBI ID 633861)
Prilog sa skupa u zborniku | izvorni znanstveni rad | međunarodna recenzija
Podaci o odgovornosti
Zadrija, Valentina ; Krapac, Josip ; Verbeek, Jakob ; Šegvić, Siniša
engleski
Patch-level Spatial Layout for Classification and Weakly Supervised Localization
We propose a discriminative patch-level model which combines appearance and spatial layout cues. We start from a block-sparse model of patch appearance based on the normalized Fisher vector representation. The appearance model is responsible for i) selecting a discriminative subset of visual words, and ii) identifying distinctive patches assigned to the selected subset. These patches are further filtered by a sparse spatial model operating on a novel representation of pairwise patch layout. We have evaluated the proposed pipeline in image classification and weakly supervised localization experiments on a public traffic sign dataset. The results show significant advantage of the combined model over state of the art appearance models.
object localization; weak supervision; Fisher vectors.
nije evidentirano
nije evidentirano
nije evidentirano
nije evidentirano
nije evidentirano
nije evidentirano
Podaci o prilogu
492-503.
2016.
objavljeno
Podaci o matičnoj publikaciji
Pattern Recognition ; 37th German Conference, GCPR 2015 Aachen, Germany, October 7–10, 2015 Proceedings. Lecture Notes in Computer Science vol. 9358, ISSN 0302-974.
Gall, Juergen ; Gehler, Peter ; Leibe, Bastian
Cham: Springer
978-3-319-24946-9
Podaci o skupu
Nepoznat skup
poster
29.02.1904-29.02.2096