Sciweavers

1713 search results - page 227 / 343
» Recognition of Parametrised Models from 3D Data
Sort
View
WWW
2004
ACM
16 years 2 months ago
Mining models of human activities from the web
The ability to determine what day-to-day activity (such as cooking pasta, taking a pill, or watching a video) a person is performing is of interest in many application domains. A ...
Mike Perkowitz, Matthai Philipose, Kenneth P. Fish...
WSC
1997
15 years 2 months ago
System Concept Development with Virtual Prototyping
Virtual prototyping with 3D drawing programs provides a means of rapidly developing system concepts and analyzing them for form, fit, logistics, human factors integration, and gen...
James C. Schaaf Jr., Faye Lynn Thompson
ECCV
2008
Springer
16 years 3 months ago
Constrained Maximum Likelihood Learning of Bayesian Networks for Facial Action Recognition
Probabilistic graphical models such as Bayesian Networks have been increasingly applied to many computer vision problems. Accuracy of inferences in such models depends on the quali...
Cassio Polpo de Campos, Yan Tong, Qiang Ji
KDD
2006
ACM
163views Data Mining» more  KDD 2006»
16 years 2 months ago
New EM derived from Kullback-Leibler divergence
We introduce a new EM framework in which it is possible not only to optimize the model parameters but also the number of model components. A key feature of our approach is that we...
Longin Jan Latecki, Marc Sobel, Rolf Lakämper
TSD
2005
Springer
15 years 7 months ago
Why Is the Recognition of Spontaneous Speech so Hard?
Although speech, derived from reading texts, and similar types of speech, e.g. that from reading newspapers or that from news broadcast, can be recognized with high accuracy, recog...
Sadaoki Furui, Masanobu Nakamura, Tomohisa Ichiba,...