Sciweavers

1159 search results - page 226 / 232
» Effect of segmentation method on video retrieval performance
Sort
View
INFOCOM
2012
IEEE
11 years 9 months ago
Sherlock is around: Detecting network failures with local evidence fusion
—Traditional approaches for wireless sensor network diagnosis are mainly sink-based. They actively collect global evidences from sensor nodes to the sink so as to conduct central...
Qiang Ma, Kebin Liu, Xin Miao, Yunhao Liu
ICCV
2007
IEEE
14 years 9 months ago
An Invariant Large Margin Nearest Neighbour Classifier
The k-nearest neighbour (kNN) rule is a simple and effective method for multi-way classification that is much used in Computer Vision. However, its performance depends heavily on ...
M. Pawan Kumar, Philip H. S. Torr, Andrew Zisserma...
NIPS
2007
13 years 8 months ago
People Tracking with the Laplacian Eigenmaps Latent Variable Model
Reliably recovering 3D human pose from monocular video requires models that bias the estimates towards typical human poses and motions. We construct priors for people tracking usi...
Zhengdong Lu, Miguel Á. Carreira-Perpi&ntil...
TOG
2012
297views Communications» more  TOG 2012»
11 years 9 months ago
Adaptive manifolds for real-time high-dimensional filtering
We present a technique for performing high-dimensional filtering of images and videos in real time. Our approach produces high-quality results and accelerates filtering by compu...
Eduardo S. L. Gastal, Manuel M. Oliveira
CVPR
2007
IEEE
14 years 9 months ago
Learning a Spatially Smooth Subspace for Face Recognition
Subspace learning based face recognition methods have attracted considerable interests in recently years, including Principal Component Analysis (PCA), Linear Discriminant Analysi...
Deng Cai, Xiaofei He, Yuxiao Hu, Jiawei Han, Thoma...