Weakly Supervised Object Localization with Large Fisher Vectors (CROSBI ID 623597)
Prilog sa skupa u zborniku | izvorni znanstveni rad | međunarodna recenzija
Podaci o odgovornosti
Krapac, Josip ; Šegvić, Siniša
engleski
Weakly Supervised Object Localization with Large Fisher Vectors
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.
Weakly Supervised Object Localization; Fisher Vectors; Sparse Classification Models.
nije evidentirano
nije evidentirano
nije evidentirano
nije evidentirano
nije evidentirano
nije evidentirano
Podaci o prilogu
1-10.
2015.
objavljeno
Podaci o matičnoj publikaciji
Proceedings of the 10th International Conference on Computer Vision Theory and Applications
Jose Braz, Sebastiano Battiato and Francisco Imai
Berlin: Jose Braz, Sebastiano Battiato and Francisco Imai
978-989-758-089-5
Podaci o skupu
10th International Conference on Computer Vision Theory and Applications
predavanje
11.03.2015-14.03.2015
Berlin, Njemačka