150
Voted
CVPR
2005
IEEE
16 years 5 months ago
2005
IEEE
Automatic image categorization using low-level features is a challenging research topic in computer vision. In this paper, we formulate the image categorization problem as a multi...
125
Voted
CVPR
2005
IEEE
16 years 5 months ago
2005
IEEE
The problem of low-rank matrix factorization in the presence of missing data has seen significant attention in recent computer vision research. The approach that dominates the lit...
129
Voted
CVPR
2005
IEEE
16 years 5 months ago
2005
IEEE
We propose a new measure, the method noise, to evaluate and compare the performance of digital image denoising methods. We first compute and analyze this method noise for a wide c...
129
Voted
CVPR
2005
IEEE
16 years 5 months ago
2005
IEEE
This paper presents an approach that uses conformal mapping to parameterize a document's 3D shape to a 2D plane. Using this conformal parametrization, a restorative mapping b...
160
Voted
CVPR
2005
IEEE
16 years 5 months ago
2005
IEEE
This paper describes a novel multi-view matching framework based on a new type of invariant feature. Our features are located at Harris corners in discrete scale-space and oriente...
136
Voted
CVPR
2005
IEEE
16 years 5 months ago
2005
IEEE
We propose using simple mixture models to define a set of mid-level binary local features based on binary oriented edge input. The features capture natural local structures in the...
142
Voted
CVPR
2005
IEEE
16 years 5 months ago
2005
IEEE
We approach recognition in the framework of deformable shape matching, relying on a new algorithm for finding correspondences between feature points. This algorithm sets up corres...
119
Voted
CVPR
2005
IEEE
16 years 5 months ago
2005
IEEE
The objective of this work is to recognize all the frontal faces of a character in the closed world of a movie or situation comedy, given a small number of query faces. This is ch...
102
Voted
CVPR
2005
IEEE
16 years 5 months ago
2005
IEEE
164
Voted
CVPR
2005
IEEE
16 years 5 months ago
2005
IEEE
We present a new method for matching line segments between two uncalibrated wide-baseline images. Most current techniques for wide-baseline matching are based on viewpoint invaria...