Sciweavers

349 search results - page 3 / 70
» A Discriminative Framework for Modelling Object Classes
Sort
View
ICCV
2005
IEEE
14 years 7 months ago
Efficient Learning of Relational Object Class Models
We present an efficient method for learning part-based object class models from unsegmented images represented as sets of salient features. A model includes parts' appearance...
Aharon Bar-Hillel, Tomer Hertz, Daphna Weinshall
ICASSP
2011
IEEE
12 years 9 months ago
Combining generic and class-specific codebooks for object categorization and detection
Combining advantages of shape and appearance features, we propose a novel model that integrates these two complementary features into a common framework for object categorization ...
Hong Pan, Yaping Zhu, Liang-Zheng Xia, Truong Q. N...
ICPR
2004
IEEE
14 years 6 months ago
Linear Discriminant Analysis and Discriminative Log-linear Modeling
We discuss the relationship between the discriminative training of Gaussian models and the maximum entropy framework for log-linear models. Observing that linear transforms leave ...
Daniel Keysers, Hermann Ney
ICIP
2002
IEEE
14 years 7 months ago
Modeling object classes in aerial images using hidden Markov models
A canonical model is proposed for object classes in aerial images. This model is motivated by the observation that geographic regions of interest are characterized by collections ...
Shawn Newsam, Sitaram Bhagavathy, B. S. Manjunath
PVLDB
2008
82views more  PVLDB 2008»
13 years 4 months ago
TraClass: trajectory classification using hierarchical region-based and trajectory-based clustering
Trajectory classification, i.e., model construction for predicting the class labels of moving objects based on their trajectories and other features, has many important, real-worl...
Jae-Gil Lee, Jiawei Han, Xiaolei Li, Hector Gonzal...