50 search results - page 5 / 10 » Deep Learning with Kernel Regularization for Visual Recognit... |
ICCV
2009
IEEE
14 years 11 months ago
2009
IEEE
Common visual codebook generation methods used in
a Bag of Visual words model, e.g. k-means or Gaussian
Mixture Model, use the Euclidean distance to cluster features
into visual...
ICPR
2008
IEEE
14 years 23 days ago
2008
IEEE
Graph based semi-supervised learning methods (SSL) implicitly assume that the intrinsic geometry of the data points can be fully specified by an Euclidean distance based local ne...
AAAI
2008
13 years 8 months ago
2008
An important feature of many problem domains in machine learning is their geometry. For example, adjacency relationships, symmetries, and Cartesian coordinates are essential to an...
CVPR
2011
IEEE
13 years 1 months ago
2011
IEEE
In real-world applications, “what you saw” during training is often not “what you get” during deployment: the distribution and even the type and dimensionality of features...
CVPR
2010
IEEE
13 years 4 months ago
2010
IEEE
We address the problem of computing joint sparse representation of visual signal across multiple kernel-based representations. Such a problem arises naturally in supervised visual...