141 search results - page 28 / 29 » LOCUS: Learning Object Classes with Unsupervised Segmentatio... |
120
click to vote
ICCV
2009
IEEE
16 years 6 months ago
2009
IEEE
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 ...
160
Voted
TSMC
2010
14 years 8 months ago
2010
We study the problem of projecting high-dimensional tensor data on an unspecified Riemannian manifold onto some lower dimensional subspace1 without much distorting the pairwise geo...
172
Voted
VLSISP
2010
15 years 4 days ago
2010
Abstract In case of insufficient data samples in highdimensional classification problems, sparse scatters of samples tend to have many ‘holes’—regions that have few or no nea...
181
Voted
SIAMIS
2010
14 years 8 months ago
2010
Markov random field (MRF) models, including conditional random field models, are popular in computer vision. However, in order to be computationally tractable, they are limited to ...
137
click to vote
CVPR
2011
IEEE
14 years 5 months ago
2011
IEEE
Spatially-discrete Markov random fields (MRFs) and spatially-continuous variational approaches are ubiquitous in low-level vision, including image restoration, segmentation, opti...