Naslov
Weakly Supervised Object Localization, Fisher Vectors, Sparse Classification Models.

Autori
Krapac, Josip ; Šegvić, Siniša

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

Izvornik
Proceedings of the 10th International Conference on Computer Vision Theory and Applications / Jose Braz, Sebastiano Battiato and Francisco Imai - Berlin : SCITEPRESS, 2015, 1-10

ISBN
978-989-758-089-5

Skup
International Conference on Computer Vision Theory and Applications

Mjesto i datum
Berlin, Njemačka, 11.03.2015. - 14.03.2015

Vrsta sudjelovanja
Predavanje

Vrsta recenzije
Međunarodna recenzija

Ključne riječi
Weakly Supervised Object Localization; Fisher Vectors; Sparse Classification Models.

Sažetak
We propose a novel method for learning object localization models in a weakly supervised manner, by employing images annotated with object class labels but not with object locations. Given an image, the learned model predicts both the presence of the object class in the image and the bounding box that determines the object location. The main ingredients of our method are a large Fisher vector representation and a sparse classification model enabling efficient evaluation of patch scores. The method is able to reliably detect very small objects with some intra-class variation in reasonable time. Experimental validation has been performed on a public dataset and we report localization performance comparable to strongly supervised approaches.

Izvorni jezik
Engleski

Znanstvena područja
Računarstvo

POVEZANOST RADA