Sciweavers

220 search results - page 16 / 44
» Incremental Multiple Kernel Learning for object recognition
Sort
View
CVPR
2012
IEEE
13 years 2 months ago
Pose pooling kernels for sub-category recognition
The ability to normalize pose based on super-category landmarks can significantly improve models of individual categories when training data are limited. Previous methods have co...
Ning Zhang, Ryan Farrell, Trevor Darrell
103
Voted
CEC
2009
IEEE
15 years 6 months ago
How robot morphology and training order affect the learning of multiple behaviors
— Automatically synthesizing behaviors for robots with articulated bodies poses a number of challenges beyond those encountered when generating behaviors for simpler agents. One ...
Joshua S. Auerbach, Josh C. Bongard
PR
2007
102views more  PR 2007»
14 years 11 months ago
A robust incremental learning framework for accurate skin region segmentation in color images
In this paper, we propose a robust incremental learning framework for accurate skin region segmentation in real-life images. The proposed framework is able to automatically learn ...
Bin Li, Xiangyang Xue, Jianping Fan
99
Voted
ICPR
2008
IEEE
15 years 6 months ago
Regularized discriminant analysis for transformation-invariant object recognition
We present a novel method for incorporating prior knowledge about invariances in object recognition for discriminant analysis. In contrast to conventional isotropic regularization...
Yung-Kyun Noh, Jihun Ham, Daniel D. Lee
ICCV
2007
IEEE
16 years 1 months ago
Active Learning with Gaussian Processes for Object Categorization
Discriminative methods for visual object category recognition are typically non-probabilistic, predicting class labels but not directly providing an estimate of uncertainty. Gauss...
Ashish Kapoor, Kristen Grauman, Raquel Urtasun, Tr...