Sciweavers

130 search results - page 17 / 26
» Virtual Training for Multi-View Object Class Recognition
Sort
View
CVPR
2012
IEEE
11 years 10 months ago
Teaching 3D geometry to deformable part models
Current object class recognition systems typically target 2D bounding box localization, encouraged by benchmark data sets, such as Pascal VOC. While this seems suitable for the de...
Bojan Pepik, Michael Stark, Peter V. Gehler, Bernt...
ICDAR
2007
IEEE
14 years 1 months ago
Energy-Based Models in Document Recognition and Computer Vision
The Machine Learning and Pattern Recognition communities are facing two challenges: solving the normalization problem, and solving the deep learning problem. The normalization pro...
Yann LeCun, Sumit Chopra, Marc'Aurelio Ranzato, Fu...
ICIP
2005
IEEE
14 years 1 months ago
HMM-based motion recognition system using segmented PCA
In this paper, we propose a novel technique for modelbased recognition of complex object motion trajectories using Hidden Markov Models (HMM). We build our models on Principal Com...
Faisal I. Bashir, Wei Qu, Ashfaq A. Khokhar, Dan S...
ICIP
2010
IEEE
13 years 5 months ago
Distributed classification of multiple observations by consensus
We consider the problem of distributed classification of multiple observations of the same object that are collected in an ad-hoc network of vision sensors. Assuming that each sen...
Effrosini Kokiopoulou, Pascal Frossard
ICDM
2006
IEEE
225views Data Mining» more  ICDM 2006»
14 years 1 months ago
Adaptive Kernel Principal Component Analysis with Unsupervised Learning of Kernels
Choosing an appropriate kernel is one of the key problems in kernel-based methods. Most existing kernel selection methods require that the class labels of the training examples ar...
Daoqiang Zhang, Zhi-Hua Zhou, Songcan Chen