Sciweavers

147 search results - page 17 / 30
» A Riemannian Framework for Tensor Computing
Sort
View
ICPR
2006
IEEE
14 years 9 months ago
Multi-layer Mosaics in the Presence of Motion and Depth Effects
In this paper, we present a new segmentation-based 2D mosaic framework. Most of current mosaic algorithms do not explicitly remove moving objects from images before registration, ...
Changki Min, Gérard G. Medioni, Qian Yu
CVPR
2005
IEEE
14 years 10 months ago
Hallucinating Faces: TensorPatch Super-Resolution and Coupled Residue Compensation
In this paper, we propose a new face hallucination framework based on image patches, which integrates two novel statistical super-resolution models. Considering that image patches...
Wei Liu, Dahua Lin, Xiaoou Tang
CVPR
2006
IEEE
14 years 2 months ago
Perceptually-Inspired and Edge-Directed Color Image Super-Resolution
Inspired by multi-scale tensor voting, a computational framework for perceptual grouping and segmentation, we propose an edge-directed technique for color image superresolution gi...
Yu-Wing Tai, Wai-Shun Tong, Chi-Keung Tang
ECCV
2008
Springer
14 years 10 months ago
Robust Visual Tracking Based on an Effective Appearance Model
Most existing appearance models for visual tracking usually construct a pixel-based representation of object appearance so that they are incapable of fully capturing both global an...
Xi Li, Weiming Hu, Zhongfei Zhang, Xiaoqin Zhang
WACV
2007
IEEE
14 years 2 months ago
Motion Estimation Using a General Purpose Neural Network Simulator for Visual Attention
Motion detection and estimation is a first step in the much larger framework of attending to visual motion based on Selective Tuning Model of Visual Attention [1]. In order to be ...
Florentin Dorian Vintila, John K. Tsotsos