Naslov
Patch-level Spatial Layout for Classification and Weakly Supervised Localization

Autori
Zadrija, Valentina ; Krapac, Josip ; Verbeek, Jakob ; Šegvić, Siniša

Vrsta, podvrsta i kategorija rada
Radovi u zbornicima skupova, cjeloviti rad (in extenso), znanstveni

Izvornik
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, 2016, 492-503

ISBN
978-3-319-24946-9

Skup
German Conference on Pattern Recognition

Mjesto i datum
Aachen, Njemačka, 07.10.2015. - 10.10.2015

Vrsta sudjelovanja
Poster

Vrsta recenzije
Međunarodna recenzija

Ključne riječi
object localization; weak supervision; Fisher vectors.

Sažetak
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.

Izvorni jezik
Engleski

Znanstvena područja
Računarstvo

POVEZANOST RADA