Sciweavers

2191 search results - page 332 / 439
» Non-parametric image super-resolution using multiple images
Sort
View
CVPR
2004
IEEE
15 years 1 months ago
Visual Object Categorization Using Distance-Based Discriminant Analysis
This paper formulates the problem of object categorization in the discriminant analysis framework focusing on transforming visual feature data so as to make it conform to the comp...
Serhiy Kosinov, Stéphane Marchand-Maillet, ...
ICCV
2009
IEEE
2205views Computer Vision» more  ICCV 2009»
16 years 2 months ago
Video stabilization using robust feature trajectories
This paper proposes a new approach for video stabilization. Most existing video stabilization methods adopt a framework of three steps, motion estimation, motion compensation an...
Ken-Yi Lee, Yung-Yu, Chuang Bing-Yu, Chen Ming Ouh...
CVPR
2005
IEEE
15 years 12 months ago
Subspace Analysis Using Random Mixture Models
In [1], three popular subspace face recognition methods, PCA, Bayes, and LDA were analyzed under the same framework and an unified subspace analysis was proposed. However, since t...
Xiaogang Wang, Xiaoou Tang
CVPR
2008
IEEE
15 years 12 months ago
High resolution motion layer decomposition using dual-space graph cuts
We introduce a novel energy minimization method to decompose a video into a set of super-resolved moving layers. The proposed energy corresponds to the cost of coding the sequence...
Thomas Schoenemann, Daniel Cremers
AVSS
2006
IEEE
15 years 4 months ago
People Tracking Using a Time-of-Flight Depth Sensor
Visually track several moving persons engaged in close interactions is known to be a very hard problem, though 3-D approaches based on stereo vision and plan-view maps offer much ...
Alessandro Bevilacqua, Luigi di Stefano, Pietro Az...