104
Voted
CVPR
2006
IEEE
16 years 2 months ago
2006
IEEE
Stereo matching algorithms conventionally match over a range of disparities sufficient to encompass all visible 3D scene points. Human vision however does not do this. It works ov...
103
Voted
CVPR
2006
IEEE
16 years 2 months ago
2006
IEEE
Spectral clustering is a simple yet powerful method for finding structure in data using spectral properties of an associated pairwise similarity matrix. This paper provides new in...
187
Voted
CVPR
2006
IEEE
16 years 2 months ago
2006
IEEE
SIFT has been proven to be the most robust local invariant feature descriptor. SIFT is designed mainly for gray images. However, color provides valuable information in object desc...
86
Voted
CVPR
2006
IEEE
16 years 2 months ago
2006
IEEE
We present a novel algorithm (which we call "FragTrack") for tracking an object in a video sequence. The template object is represented by multiple image fragments or pa...
116
click to vote
CVPR
2006
IEEE
16 years 2 months ago
2006
IEEE
Given three or four synchronized videos taken at eye level and from different angles, we show that we can effectively use dynamic programming to accurately follow up to six indivi...
105
click to vote
CVPR
2005
IEEE
16 years 2 months ago
2005
IEEE
We combine local texture features (PCA-SIFT), global features (shape context), and spatial features within a single multi-layer AdaBoost model of object class recognition. The fir...
105
Voted
CVPR
2005
IEEE
16 years 2 months ago
2005
IEEE
Nearest neighborhood consistency is an important concept in statistical pattern recognition, which underlies the well-known k-nearest neighbor method. In this paper, we combine th...
110
click to vote
CVPR
2005
IEEE
16 years 2 months ago
2005
IEEE
Functional Magnetic Resonance Imaging (fMRI) has enabled scientists to look into the active human brain. FMRI provides a sequence of 3D brain images with intensities representing ...
106
Voted
CVPR
2005
IEEE
16 years 2 months ago
2005
IEEE
This paper presents a novel approach for estimating parameters for MRF-based stereo algorithms. This approach is based on a new formulation of stereo as a maximum a posterior (MAP...
100
Voted
CVPR
2005
IEEE
16 years 2 months ago
2005
IEEE
We address the problem of temporal unusual event detection. Unusual events are characterized by a number of features (rarity, unexpectedness, and relevance) that limit the applica...