Home

About

Advanced Search

Browse by Discipline

Scientific Societies

E-print Alerts

Add E-prints

E-print Network
FAQHELPSITE MAPCONTACT US


  Advanced Search  

 
To appear in Proceedings of IEEE International Conference on Computer Vision (ICCV), October 2007. ClassMap: Efficient Multiclass Recognition via Embeddings
 

Summary: To appear in Proceedings of IEEE International Conference on Computer Vision (ICCV), October 2007.
ClassMap: Efficient Multiclass Recognition via Embeddings
Vassilis Athitsos1
, Alexandra Stefan2
, Quan Yuan2
, and Stan Sclaroff2
1
Computer Science and Engineering Department, University of Texas at Arlington, USA
2
Computer Science Department, Boston University, USA
Abstract
In many computer vision applications, such as face
recognition and hand pose estimation, we need systems that
can recognize a very large number of classes. Large margin
classification methods, such as AdaBoost and SVMs, often
provide competitive accuracy rates, but at the cost of eval-
uating a large number of binary classifiers. We propose
an embedding-based method for efficient multiclass recog-
nition. In our method, patterns and classes are mapped to
vectors in such a way that patterns and their associated

  

Source: Athitsos, Vassilis - Department of Computer Science and Engineering, University of Texas at Arlington

 

Collections: Computer Technologies and Information Sciences