Sciweavers

2913 search results - page 466 / 583
» How Much to Copy
Sort
View
JMLR
2010
106views more  JMLR 2010»
13 years 4 months ago
Why Does Unsupervised Pre-training Help Deep Learning?
Much recent research has been devoted to learning algorithms for deep architectures such as Deep Belief Networks and stacks of auto-encoder variants, with impressive results obtai...
Dumitru Erhan, Yoshua Bengio, Aaron C. Courville, ...
TIP
2010
115views more  TIP 2010»
13 years 3 months ago
Constrained and Dimensionality-Independent Path Openings
Abstract--Path openings and closings are morphological operations with flexible line segments as structuring elements. These line segments have the ability to adapt to local image ...
Cris L. Luengo Hendriks
TSMC
2010
13 years 3 months ago
Toward Unconstrained Ear Recognition From Two-Dimensional Images
Abstract--Ear recognition, as a biometric, has several advantages. In particular, ears can be measured remotely and are also relatively static in size and structure for each indivi...
John D. Bustard, Mark S. Nixon
TWC
2010
13 years 3 months ago
Primary User Enters the Game: Performance of Dynamic Spectrum Leasing in Cognitive Radio Networks
Dynamic spectrum leasing (DSL) is one of the schemes proposed for dynamic spectrum sharing (DSS) in cognitive radio networks. In DSL, spectrum owners, denoted as primary users, dyn...
Gonzalo Vazquez-Vilar, Carlos Mosquera, Sudharman ...
ICPR
2008
IEEE
14 years 3 months ago
Automatic video annotation with adaptive number of key words
Retrieving videos using key words requires obtaining the semantic features of the videos. Most work reported in the literature focuses on annotating a video shot with a fixed numb...
Fangshi Wang, Wei Lu, Jingen Liu, Mubarak Shah, De...