2609 search results - page 253 / 522 » Optimizing for parallelism and data locality |
211
click to vote
ICANN
2005
Springer
16 years 4 days ago
2005
Springer
Abstract. Tuning hyper-parameters is a necessary step to improve learning algorithm performances. For Support Vector Machine classifiers, adjusting kernel parameters increases dra...
193
click to vote
IROS
2007
IEEE
16 years 28 days ago
2007
IEEE
— One primary goal in rescue robotics is to deploy a team of robots for coordinated victim search after a disaster. This requires robots to perform subtasks, such as victim detec...
189
click to vote
CGO
2006
IEEE
16 years 21 days ago
2006
IEEE
Software prefetching has been demonstrated as a powerful technique to tolerate long load latencies. However, to be effective, prefetching must target the most critical (frequently...
184
click to vote
CVPR
2010
IEEE
15 years 10 months ago
2010
IEEE
For various 3D shape analysis tasks, the LaplaceBeltrami(LB) embedding has become increasingly popular as it enables the efficient comparison of shapes based on intrinsic geometry...
168
click to vote
ICCV
2009
IEEE
16 years 11 months ago
2009
IEEE
Correspondence problems are of great importance in
computer vision. They appear as subtasks in many applications
such as object recognition, merging partial 3D reconstructions
a...