Sciweavers

38 search results - page 2 / 8
» Fast kernel learning for spatial pyramid matching
Sort
View
AAAI
2008
13 years 7 months ago
Dimension Amnesic Pyramid Match Kernel
With the success of local features in object recognition, feature-set representations are widely used in computer vision and related domains. Pyramid match kernel (PMK) is an effi...
Yi Liu, Xulei Wang, Hongbin Zha
CVPR
2012
IEEE
11 years 7 months ago
SURFing the point clouds: Selective 3D spatial pyramids for category-level object recognition
This paper proposes a novel approach to recognize object categories in point clouds. By quantizing 3D SURF local descriptors, computed on partial 3D shapes extracted from the poin...
Carolina Redondo-Cabrera, Roberto Javier Ló...
CVPR
2008
IEEE
14 years 6 months ago
Relaxed matching kernels for robust image comparison
The popular bag-of-features representation for object recognition collects signatures of local image patches and discards spatial information. Some have recently attempted to at l...
Andrea Vedaldi, Stefano Soatto
CVPR
2012
IEEE
11 years 7 months ago
Beyond spatial pyramids: Receptive field learning for pooled image features
In this paper we examine the effect of receptive field designs on classification accuracy in the commonly adopted pipeline of image classification. While existing algorithms us...
Yangqing Jia, Chang Huang, Trevor Darrell
CVPR
2009
IEEE
14 years 12 months ago
Let the Kernel Figure it Out; Principled Learning of Pre-processing for Kernel Classifiers
Most modern computer vision systems for high-level tasks, such as image classification, object recognition and segmentation, are based on learning algorithms that are able to se...
Peter V. Gehler, Sebastian Nowozin