Sciweavers

150 search results - page 1 / 30
» Shape Discovery from Unlabeled Image Collections
Sort
View
CVPR
2009
IEEE
15 years 12 hour ago
Shape Discovery from Unlabeled Image Collections
Can we discover common object shapes within unlabeled multi-category collections of images? While often a critical cue at the category-level, contour matches can be difficult to...
Yong Jae Lee (University of Texas at Austin), Kris...
ECCV
2010
Springer
13 years 9 months ago
From a Set of Shapes to Object Discovery
Abstract. This paper presents an approach to object discovery in a given unlabeled image set, based on mining repetitive spatial configurations of image contours. Contours that si...
ICIP
2008
IEEE
14 years 6 months ago
Classification of unlabeled point sets using ANSIG
We address two-dimensional shape-based classification, considering shapes described by arbitrary sets of unlabeled points, or landmarks. This is relevant in practice because, in m...
José J. Rodrigues, João M. F. Xavier...
CVPR
2008
IEEE
14 years 7 months ago
Unsupervised discovery of visual object class hierarchies
Objects in the world can be arranged into a hierarchy based on their semantic meaning (e.g. organism ? animal ? feline ? cat). What about defining a hierarchy based on the visual ...
Josef Sivic, Bryan C. Russell, Andrew Zisserman, W...
ICPR
2008
IEEE
14 years 6 months ago
MDL patch correspondences on unlabeled images
Automatic construction of Shape and Appearance Models from examples via establishing correspondences across the training set has been successful in the last decades. One successfu...
Johan Karlsson, Kalle Åström