Sciweavers

115 search results - page 18 / 23
» Automatic scene activity modeling for improving object class...
Sort
View
PAMI
2012
12 years 12 months ago
Quantifying and Transferring Contextual Information in Object Detection
— Context is critical for reducing the uncertainty in object detection. However, context modelling is challenging because there are often many different types of contextual infor...
Wei-Shi Zheng, Shaogang Gong, Tao Xiang
BMVC
2010
14 years 7 months ago
StyP-Boost: A Bilinear Boosting Algorithm for Learning Style-Parameterized Classifiers
We introduce a novel bilinear boosting algorithm, which extends the multi-class boosting framework of JointBoost to optimize a bilinear objective function. This allows style param...
Jonathan Warrell, Philip H. S. Torr, Simon Prince
CVPR
2004
IEEE
15 years 11 months ago
Fast, Integrated Person Tracking and Activity Recognition with Plan-View Templates from a Single Stereo Camera
Copyright 2004 IEEE. Published in Conference on Computer Vision and Pattern Recognition (CVPR-2004), June 27 - July 2, 2004, Washington DC. Personal use of this material is permit...
Michael Harville, Dalong Li
ICCV
2009
IEEE
14 years 7 months ago
Jointly estimating demographics and height with a calibrated camera
One important problem in computer vision is to provide a demographic description a person from an image. In practice, many of the state-of-the-art methods use only an analysis of ...
Andrew C. Gallagher, Andrew C. Blose, Tsuhan Chen
CVPR
2007
IEEE
15 years 11 months ago
Monocular and Stereo Methods for AAM Learning from Video
The active appearance model (AAM) is a powerful method for modeling deformable visual objects. One of the major drawbacks of the AAM is that it requires a training set of pseudo-d...
Jason Saragih, Roland Göcke