868 search results - page 19 / 174 » Learning Object Representations Using Sequential Patterns |
131
Voted
VISAPP
2007
15 years 4 months ago
2007
We introduce one module in a cognitive system that learns the shape of objects by active exploration. More specifically, we propose a feature tracking scheme that makes use of the...
105
Voted
AAAI
2004
15 years 5 months ago
2004
Using language technology for text analysis and light-weight ontologies as a content-mediating level, we acquire indexing patterns from vast amounts of indexing data for Englishla...
115
Voted
ICASSP
2008
IEEE
15 years 10 months ago
2008
IEEE
The conventional method of generating a basis that is optimally adapted (in MSE) for representation of an ensemble of signals is Principal Component Analysis (PCA). A more ambitio...
131
Voted
CVPR
2001
IEEE
16 years 5 months ago
2001
IEEE
In this paper, we propose a novel method, called local nonnegative matrix factorization (LNMF), for learning spatially localized, parts-based subspace representation of visual pat...
87
Voted
ICPR
2008
IEEE
16 years 4 months ago
2008
IEEE
We propose a new loss function for discriminative learning of Markov random fields, which is an intermediate loss function between the sequential loss and the pointwise loss. We s...