TY  - CONF
AU  - Jose Carlos Rubio
AU  - Joan Serrat
AU  - Antonio Lopez
A2  - CVPR
PY  - 2012//
TI  - Unsupervised co-segmentation through region matching
BT  - 25th IEEE Conference on Computer Vision and Pattern Recognition
SP  - 749
EP  - 756
PB  - IEEE Xplore
N2  - Co-segmentation is defined as jointly partitioning multiple images depicting the same or similar object, into foreground and background. Our method consists of a multiple-scale multiple-image generative model, which jointly estimates the foreground and background appearance distributions from several images, in a non-supervised manner. In contrast to other co-segmentation methods, our approach does not require the images to have similar foregrounds and different backgrounds to function properly. Region matching is applied to exploit inter-image information by establishing correspondences between the common objects that appear in the scene. Moreover, computing many-to-many associations of regions allow further applications, like recognition of object parts across images. We report results on iCoseg, a challenging dataset that presents extreme variability in camera viewpoint, illumination and object deformations and poses. We also show that our method is robust against large intra-class variability in the MSRC database.
SN  - 1063-6919
SN  - 978-1-4673-1226-4
L1  - http://refbase.cvc.uab.es/files/rsl2012c.pdf
UR  - http://dx.doi.org/10.1109/CVPR.2012.6247745
N1  - ADAS
ID  - Jose Carlos Rubio2012
ER  -