Sciweavers

343 search results - page 11 / 69
» Mercer Kernels for Object Recognition with Local Features
Sort
View
CVPR
2004
IEEE
15 years 7 months ago
Scale-Invariant Shape Features for Recognition of Object Categories
We introduce a new class of distinguished regions based on detecting the most salient convex local arrangements of contours in the image. The regions are used in a similar way to ...
Frédéric Jurie, Cordelia Schmid
ICCV
2011
IEEE
14 years 3 months ago
Ask the locals: multi-way local pooling for image recognition
Invariant representations in object recognition systems are generally obtained by pooling feature vectors over spatially local neighborhoods. But pooling is not local in the featu...
Y-Lan Boureau, Nicolas Le Roux, francis bach, Jean...
ICPR
2010
IEEE
15 years 1 months ago
Improving Classification Accuracy by Comparing Local Features through Canonical Correlations
Classifying images using features extracted from densely sampled local patches has enjoyed significant success in many detection and recognition tasks. It is also well known that ...
Mert Dikmen, Thomas S. Huang
ACCV
2007
Springer
15 years 10 months ago
The Kernel Orthogonal Mutual Subspace Method and Its Application to 3D Object Recognition
This paper proposes the kernel orthogonal mutual subspace method (KOMSM) for 3D object recognition. KOMSM is a kernel-based method for classifying sets of patterns such as video fr...
Kazuhiro Fukui, Osamu Yamaguchi
MCS
2010
Springer
15 years 10 months ago
Combining Multiple Kernels by Augmenting the Kernel Matrix
Abstract. In this paper we present a novel approach to combining multiple kernels where the kernels are computed from different information channels. In contrast to traditional me...
Fei Yan, Krystian Mikolajczyk, Josef Kittler, Muha...