349 search results - page 23 / 70 » A Discriminative Framework for Modelling Object Classes |
153
Voted
CVPR
2009
IEEE
16 years 11 months ago
2009
IEEE
In this paper we present a method for learning classspecific
features for recognition. Recently a greedy layerwise
procedure was proposed to initialize weights of deep
belief ne...
177
click to vote
IWCM
2004
Springer
15 years 9 months ago
2004
Springer
We present a probabilistic framework for component-based automatic detection and tracking of objects in video. We represent objects as spatio-temporal two-layer graphical models, w...
154
click to vote
CVPR
2007
IEEE
16 years 6 months ago
2007
IEEE
Today's category-level object recognition systems largely focus on fronto-parallel views of objects with characteristic texture patterns. To overcome these limitations, we pr...
133
click to vote
CVPR
1999
IEEE
15 years 8 months ago
1999
IEEE
We introduce an approach to feature-based object recognition, using maximum a posteriori (MAP) estimation under a Markov random field (MRF) model. This approach provides an effici...
211
click to vote
VLDB
2007
ACM
16 years 4 months ago
2007
ACM
An optimization query asks for one or more data objects that maximize or minimize some function over the data set. We propose a general class of queries, model-based optimization ...