%0 Conference Proceedings
%T Unsupervised co-segmentation through region matching
%A Jose Carlos Rubio
%A Joan Serrat
%A Antonio Lopez
%B 25th IEEE Conference on Computer Vision and Pattern Recognition
%D 2012
%I IEEE Xplore
%@ 1063-6919
%@ 978-1-4673-1226-4
%F Jose Carlos Rubio2012
%O ADAS
%O exported from refbase (http://refbase.cvc.uab.es/show.php?record=2033), last updated on Mon, 14 Oct 2013 14:26:24 +0200
%X 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.
%U http://refbase.cvc.uab.es/files/rsl2012c.pdf
%U http://dx.doi.org/10.1109/CVPR.2012.6247745
%P 749-756