Sciweavers

2192 search results - page 103 / 439
» Algorithms for Challenging Motif Problems
Sort
View
ICML
2009
IEEE
14 years 9 months ago
Learning when to stop thinking and do something!
An anytime algorithm is capable of returning a response to the given task at essentially any time; typically the quality of the response improves as the time increases. Here, we c...
Barnabás Póczos, Csaba Szepesv&aacut...
ICPR
2008
IEEE
14 years 2 months ago
Learning polynomial function based neutral-emotion GMM transformation for emotional speaker recognition
One of the biggest challenges in speaker recognition is dealing with speaker-emotion variability. The basic problem is how to train the emotion GMMs of the speakers from their neu...
Zhenyu Shan, Yingchun Yang
IBMRD
2006
58views more  IBMRD 2006»
13 years 8 months ago
Self-adapting numerical software (SANS) effort
The challenge for the development of next generation software is the successful management of the complex computational environment while delivering to the scientist the full powe...
Jack Dongarra, George Bosilca, Zizhong Chen, Victo...
MM
2005
ACM
145views Multimedia» more  MM 2005»
14 years 1 months ago
Multiple instance learning for labeling faces in broadcasting news video
Labeling faces in news video with their names is an interesting research problem which was previously solved using supervised methods that demand significant user efforts on lab...
Jun Yang 0003, Rong Yan, Alexander G. Hauptmann
CEC
2010
IEEE
12 years 12 months ago
Revisiting Evolutionary Information Filtering
— Adaptive Information Filtering seeks a solution to the problem of information overload through a tailored representation of the user’s interests, called user profile, which ...
Nikolaos Nanas, Stefanos Kodovas, Manolis Vavalis