164 search results - page 20 / 33 » Flexible latent variable models for multi-task learning |
IWINAC
2005
Springer
15 years 4 months ago
2005
Springer
This paper presents a method for spatial navigation performed mainly on past experiences. The past experiences are remembered in their temporal context, i.e. as episodes of events....
120
click to vote
ICCV
2011
IEEE
13 years 11 months ago
2011
IEEE
In this paper we develop an algorithm for action recognition and localization in videos. The algorithm uses a figurecentric visual word representation. Different from previous ap...
130
click to vote
CVPR
2009
IEEE
16 years 6 months ago
2009
IEEE
We present a new method for classification with structured
latent variables. Our model is formulated using the
max-margin formalism in the discriminative learning literature.
We...
100
click to vote
ECCV
2006
Springer
16 years 1 months ago
2006
Springer
Abstract. In recent years there has been growing interest in recognition models using local image features for applications ranging from long range motion matching to object class ...
112
click to vote
ICCV
2007
IEEE
16 years 1 months ago
2007
IEEE
Many computer vision tasks may be expressed as the problem of learning a mapping between image space and a parameter space. For example, in human body pose estimation, recent rese...