Sciweavers

CVPR
2006
IEEE
14 years 5 months ago
Hierarchical Statistical Learning of Generic Parts of Object Structure
With the growing interest in object categorization various methods have emerged that perform well in this challenging task, yet are inherently limited to only a moderate number of...
Sanja Fidler, Gregor Berginc, Ales Leonardis
CVPR
2006
IEEE
14 years 5 months ago
Uncertainty Models in Quasiconvex Optimization for Geometric Reconstruction
Geometric reconstruction problems in computer vision can be solved by minimizing the maximum of reprojection errors, i.e., the L-norm. Unlike L2-norm (sum of squared reprojection ...
Qifa Ke, Takeo Kanade
CVPR
2006
IEEE
14 years 5 months ago
A Design Principle for Coarse-to-Fine Classification
Coarse-to-fine classification is an efficient way of organizing object recognition in order to accommodate a large number of possible hypotheses and to systematically exploit shar...
Sachin Gangaputra, Donald Geman
CVPR
2006
IEEE
14 years 5 months ago
Reconstruction with Interval Constraints Propagation
In this paper we demonstrate how Interval Analysis and Constraint Logic Programming can be used to obtain an accurate geometric model of a scene that rigorously takes into account...
Michela Farenzena, Andrea Fusiello, Agostino Dovie...
CVPR
2006
IEEE
14 years 5 months ago
Aligning ASL for Statistical Translation Using a Discriminative Word Model
We describe a method to align ASL video subtitles with a closed-caption transcript. Our alignments are partial, based on spotting words within the video sequence, which consists o...
Ali Farhadi, David A. Forsyth
CVPR
2006
IEEE
14 years 5 months ago
Efficient Optimal Kernel Placement for Reliable Visual Tracking
This paper describes a novel approach to optimal kernel placement in kernel-based tracking. If kernels are placed at arbitrary places, kernel-based methods are likely to be trappe...
Zhimin Fan, Ming Yang, Ying Wu, Gang Hua, Ting Yu
CVPR
2006
IEEE
14 years 5 months ago
Learning Object Shape: From Drawings to Images
We consider the important challenge of recognizing a variety of deformable object classes in images. Of fundamental importance and particular difficulty in this setting is the pro...
Gal Elidan, Geremy Heitz, Daphne Koller
CVPR
2006
IEEE
14 years 5 months ago
Image Denoising with Shrinkage and Redundant Representations
Shrinkage is a well known and appealing denoising technique. The use of shrinkage is known to be optimal for Gaussian white noise, provided that the sparsity on the signal's ...
Michael Elad, Boaz Matalon, Michael Zibulevsky
CVPR
2006
IEEE
14 years 5 months ago
RANSAC for (Quasi-)Degenerate data (QDEGSAC)
Jan-Michael Frahm, Marc Pollefeys
CVPR
2006
IEEE
14 years 5 months ago
Image Denoising Via Learned Dictionaries and Sparse representation
We address the image denoising problem, where zeromean white and homogeneous Gaussian additive noise should be removed from a given image. The approach taken is based on sparse an...
Michael Elad, Michal Aharon