Sciweavers

144 search results - page 27 / 29
» A Multistrategy Approach to Classifier Learning from Time Se...
Sort
View
JMM2
2006
218views more  JMM2 2006»
13 years 6 months ago
Automatic Recognition of Facial Actions in Spontaneous Expressions
Spontaneous facial expressions differ from posed expressions in both which muscles are moved, and in the dynamics of the movement. Advances in the field of automatic facial express...
Marian Stewart Bartlett, Gwen Littlewort, Mark G. ...
HUMO
2007
Springer
14 years 5 days ago
Multi-activity Tracking in LLE Body Pose Space
We present a method to simultaneously estimate 3d body pose and action categories from monocular video sequences. Our approach learns a lowdimensional embedding of the pose manifol...
Tobias Jaeggli, Esther Koller-Meier, Luc J. Van Go...
WSDM
2012
ACM
325views Data Mining» more  WSDM 2012»
12 years 1 months ago
Coupled temporal scoping of relational facts
Recent research has made significant advances in automatically constructing knowledge bases by extracting relational facts (e.g., Bill Clinton-presidentOf-US) from large text cor...
Partha Pratim Talukdar, Derry Tanti Wijaya, Tom Mi...
ECCV
2004
Springer
14 years 8 months ago
Weak Hypotheses and Boosting for Generic Object Detection and Recognition
In this paper we describe the first stage of a new learning system for object detection and recognition. For our system we propose Boosting [5] as the underlying learning technique...
Andreas Opelt, Michael Fussenegger, Axel Pinz, Pet...
TNN
2010
234views Management» more  TNN 2010»
13 years 22 days ago
Novel maximum-margin training algorithms for supervised neural networks
This paper proposes three novel training methods, two of them based on the back-propagation approach and a third one based on information theory for Multilayer Perceptron (MLP) bin...
Oswaldo Ludwig, Urbano Nunes