Sciweavers

2027 search results - page 15 / 406
» When is it best to best-respond
Sort
View
ICASSP
2011
IEEE
13 years 1 months ago
Improved speaker recognition when using i-vectors from multiple speech sources
The concept of speaker recognition using i-vectors was recently introduced offering state-of-the-art performance. An i-vector is a compact representation of a speaker’s utteranc...
Mitchell McLaren, David A. van Leeuwen
FC
2010
Springer
141views Cryptology» more  FC 2010»
14 years 1 months ago
When Information Improves Information Security
We investigate a mixed economy of an individual rational expert and several na¨ıve near-sighted agents in the context of security decision making. Agents select between three ca...
Jens Grossklags, Benjamin Johnson, Nicolas Christi...
IJNSEC
2007
189views more  IJNSEC 2007»
13 years 10 months ago
When Fingerprints Are Combined with Iris - A Case Study: FVC2004 and CASIA
This paper presents novel studies on fusion strategies for personal identification using fingerprint and iris biometrics. The purpose of our paper is to investigate whether the ...
Alessandra Lumini, Loris Nanni
VRST
2009
ACM
14 years 4 months ago
Gaze behavior and visual attention model when turning in virtual environments
In this paper we analyze and try to predict the gaze behavior of users navigating in virtual environments. We focus on first-person navigation in virtual environments which invol...
Sébastien Hillaire, Anatole Lécuyer,...
CORR
2011
Springer
183views Education» more  CORR 2011»
13 years 1 months ago
Learning When Training Data are Costly: The Effect of Class Distribution on Tree Induction
For large, real-world inductive learning problems, the number of training examples often must be limited due to the costs associated with procuring, preparing, and storing the tra...
Foster J. Provost, Gary M. Weiss