Sciweavers

978 search results - page 38 / 196
» Adapting Visual Category Models to New Domains
Sort
View
CVPR
2006
IEEE
15 years 3 months ago
Discriminative Object Class Models of Appearance and Shape by Correlatons
This paper presents a new model of object classes which incorporates appearance and shape information jointly. Modeling objects appearance by distributions of visual words has rec...
Silvio Savarese, John M. Winn, Antonio Criminisi
GRAPHITE
2003
ACM
15 years 3 months ago
Interactive visual method for motion and model reuse
We consider a repository of animation models and motions that can be reused to generate new animation sequences. For instance, a user can retrieve an animation of a dog kicking it...
Akanksha Huang, Zhiyong Huang, B. Prabhakaran, Con...
ATAL
2005
Springer
15 years 3 months ago
Discovering strategic multi-agent behavior in a robotic soccer domain
2. THE MASM ALGORITHM An input to the MASM algorithm is a time-annotated multi-agent action sequence. The action sequence is then transformed into an action graph. An action graph ...
Andraz Bezek
NIPS
2008
14 years 11 months ago
Unsupervised Learning of Visual Sense Models for Polysemous Words
Polysemy is a problem for methods that exploit image search engines to build object category models. Existing unsupervised approaches do not take word sense into consideration. We...
Kate Saenko, Trevor Darrell
KBSE
2010
IEEE
14 years 7 months ago
VikiBuilder: end-user specification and generation of visual wikis
With the need to make sense out of large and constantly growing information spaces, tools to support information management are becoming increasingly valuable. In prior work we pr...
Christian Hirsch, John G. Hosking, John C. Grundy