Sciweavers

60 search results - page 3 / 12
» On Ullman's theorem in computer vision
Sort
View
ICPR
2006
IEEE
14 years 8 months ago
3D Object Digitization: Topology Preserving Reconstruction
In this paper we derive a sampling theorem, which is the first one to guarantee topology preservation during digitization of 3D objects. This new theorem is applicable to several ...
Longin Jan Latecki, Peer Stelldinger
CVPR
2005
IEEE
14 years 9 months ago
Cross-Generalization: Learning Novel Classes from a Single Example by Feature Replacement
We develop an object classification method that can learn a novel class from a single training example. In this method, experience with already learned classes is used to facilita...
Evgeniy Bart, Shimon Ullman
CVPR
2005
IEEE
14 years 9 months ago
Identifying Semantically Equivalent Object Fragments
We describe a novel technique for identifying semantically equivalent parts in images belonging to the same object class, (e.g. eyes, license plates, aircraft wings etc.). The vis...
Boris Epshtein, Shimon Ullman
ICCV
2005
IEEE
14 years 9 months ago
Feature Hierarchies for Object Classification
The paper describes a method for automatically extracting informative feature hierarchies for object classification, and shows the advantage of the features constructed hierarchic...
Boris Epshtein, Shimon Ullman
ICCV
2003
IEEE
14 years 9 months ago
Object Recognition with Informative Features and Linear Classification
In this paper we show that efficient object recognition can be obtained by combining informative features with linear classification. The results demonstrate the superiority of in...
Michel Vidal-Naquet, Shimon Ullman