Sciweavers

8491 search results - page 1459 / 1699
» Forecasting in Database Systems
Sort
View
EMNLP
2009
15 years 2 months ago
Feasibility of Human-in-the-loop Minimum Error Rate Training
Minimum error rate training (MERT) involves choosing parameter values for a machine translation (MT) system that maximize performance on a tuning set as measured by an automatic e...
Omar Zaidan, Chris Callison-Burch
ICASSP
2009
IEEE
15 years 2 months ago
Audiovisual celebrity recognition in unconstrained web videos
The number of video clips available online is growing at a tremendous pace. Conventionally, user-supplied metadata text, such as the title of the video and a set of keywords, has ...
Mehmet Emre Sargin, Hrishikesh Aradhye, Pedro J. M...
ICB
2009
Springer
173views Biometrics» more  ICB 2009»
15 years 2 months ago
Bayesian Networks to Combine Intensity and Color Information in Face Recognition
We present generative models dedicated to face recognition. Our models consider data extracted from color face images and use Bayesian Networks to model relationships between diffe...
Guillaume Heusch, Sébastien Marcel
152
Voted
ICDAR
2009
IEEE
15 years 2 months ago
Prototype Selection for Handwritten Connected Digits Classification
After the handwritten segmentation process, it is common to have connected digits. This is due to the great size and shape digit variations. In addition, the acquisition and the b...
Cristiano de Santana Pereira, George D. C. Cavalca...
TASLP
2011
14 years 11 months ago
Advances in Missing Feature Techniques for Robust Large-Vocabulary Continuous Speech Recognition
— Missing feature theory (MFT) has demonstrated great potential for improving the noise robustness in speech recognition. MFT was mostly applied in the log-spectral domain since ...
Maarten Van Segbroeck, Hugo Van Hamme
« Prev « First page 1459 / 1699 Last » Next »