1345 search results - page 149 / 269 » Efficient Learning of Relational Object Class Models |
141
click to vote
CASES
2006
ACM
15 years 7 months ago
2006
ACM
Customizing architectures for particular applications is a promising approach to yield highly energy-efficient designs for embedded systems. This work explores the benefits of arc...
134
Voted
PAMI
2006
15 years 3 months ago
2006
Multiple-instance problems arise from the situations where training class labels are attached to sets of samples (named bags), instead of individual samples within each bag (called...
171
Voted
KDD
2012
ACM
13 years 5 months ago
2012
ACM
Real-world, multiple-typed objects are often interconnected, forming heterogeneous information networks. A major challenge for link-based clustering in such networks is its potent...
105
Voted
ICML
2010
IEEE
15 years 4 months ago
2010
IEEE
Deep learning has been successfully applied to perform non-linear embedding. In this paper, we present supervised embedding techniques that use a deep network to collapse classes....
103
click to vote
ICML
2005
IEEE
16 years 4 months ago
2005
IEEE
We introduce a family of kernels on discrete data structures within the general class of decomposition kernels. A weighted decomposition kernel (WDK) is computed by dividing objec...