Sciweavers

431 search results - page 76 / 87
» Representation Changes for Efficient Learning in Structural ...
Sort
View
JMLR
2008
168views more  JMLR 2008»
15 years 4 months ago
Max-margin Classification of Data with Absent Features
We consider the problem of learning classifiers in structured domains, where some objects have a subset of features that are inherently absent due to complex relationships between...
Gal Chechik, Geremy Heitz, Gal Elidan, Pieter Abbe...
ICCV
2009
IEEE
16 years 9 months ago
Decomposing a Scene into Geometric and Semantically Consistent Regions
High-level, or holistic, scene understanding involves reasoning about objects, regions, and the 3D relationships between them. This requires a representation above the level of ...
Stephen Gould, Richard Fulton, Daphne Koller
JMLR
2010
137views more  JMLR 2010»
14 years 11 months ago
Importance Sampling for Continuous Time Bayesian Networks
A continuous time Bayesian network (CTBN) uses a structured representation to describe a dynamic system with a finite number of states which evolves in continuous time. Exact infe...
Yu Fan, Jing Xu, Christian R. Shelton
CVPR
2009
IEEE
16 years 11 months ago
Epitomized Priors for Multi-labeling Problems
Image parsing remains difficult due to the need to combine local and contextual information when labeling a scene. We approach this problem by using the epitome as a prior over ...
Jonathan Warrell, Simon J. D. Prince, Alastair P. ...
IEEEICCI
2007
IEEE
15 years 10 months ago
An Image Association Model of the Brodmann Areas
The ability to associate images is the basis for learning relationships involving vision, hearing, tactile sensation, and kinetic motion. A new architecture is described that has ...
Douglas S. Greer