Sciweavers

1437 search results - page 146 / 288
» Recognition Using Region Correspondences
Sort
View
ESANN
2008
15 years 6 months ago
Robust object segmentation by adaptive metrics in Generalized LVQ
We investigate the effect of several adaptive metrics in the context of figure-ground segregation, using Generalized LVQ to train a classifier for image regions. Extending the Euc...
Alexander Denecke, Heiko Wersing, Jochen J. Steil,...
ICPR
2008
IEEE
15 years 11 months ago
Recognizing picture-taking environment from satellite images: A feasibility study
Semantic event recognition based only on vision cues has had limited success on unconstrained still pictures. Metadata related to picture taking provides contextual cues independe...
Jiebo Luo, Wei Hao, Dale McIntyre, Dhiraj Joshi, J...
IJCAI
2007
15 years 6 months ago
Parametric Kernels for Sequence Data Analysis
A key challenge in applying kernel-based methods for discriminative learning is to identify a suitable kernel given a problem domain. Many methods instead transform the input data...
Young-In Shin, Donald S. Fussell
ICCV
2005
IEEE
16 years 7 months ago
A Generative/Discriminative Learning Algorithm for Image Classification
We have developed a two-phase generative / discriminative learning procedure for the recognition of classes of objects and concepts in outdoor scenes. Our method uses both multipl...
Yi Li, Linda G. Shapiro, Jeff A. Bilmes
166
Voted
PAMI
2008
161views more  PAMI 2008»
15 years 5 months ago
TRUST-TECH-Based Expectation Maximization for Learning Finite Mixture Models
The Expectation Maximization (EM) algorithm is widely used for learning finite mixture models despite its greedy nature. Most popular model-based clustering techniques might yield...
Chandan K. Reddy, Hsiao-Dong Chiang, Bala Rajaratn...