63 search results - page 3 / 13 » Combining Generative Models and Fisher Kernels for Object Re... |
CVPR
2007
IEEE
14 years 7 months ago
2007
IEEE
We present a hierarchical generative model for object recognition that is constructed by weakly-supervised learning. A key component is a novel, adaptive patch feature whose width...
ICCV
2007
IEEE
13 years 12 months ago
2007
IEEE
Kernel classifiers based on Support Vector Machines (SVM) have recently achieved state-of-the art results on several popular datasets like Caltech or Pascal. This was possible by...
IROS
2008
IEEE
13 years 12 months ago
2008
IEEE
— This paper presents a method to recognize and generate sequential motions for object manipulation such as placing one object on another or rotating it. Motions are learned usin...
CVPR
2005
IEEE
14 years 7 months ago
2005
IEEE
Objects can exhibit different dynamics at different scales, and this is often exploited by visual tracking algorithms. A local dynamic model is typically used to extract image fea...
ECCV
2010
Springer
13 years 5 months ago
2010
Springer
Abstract. We propose a new generative model, and a new image similarity kernel based on a linked hierarchy of probabilistic segmentations. The model is used to efficiently segment ...