CVPR
2011
IEEE
13 years 7 months ago
2011
IEEE
Traditional computer vision and machine learning algorithms have been largely studied in a centralized setting, where all the processing is performed at a single central location....
CVPR
2011
IEEE
13 years 7 months ago
2011
IEEE
CVPR
2011
IEEE
13 years 7 months ago
2011
IEEE
Specular flow is the motion field induced on the image plane by the movement of points reflected by a curved, mirror-like surface. This flow provides information about surface...
CVPR
2011
IEEE
13 years 7 months ago
2011
IEEE
This paper presents a new adaptive graph-cut based move-making algorithm for energy minimization. Traditional move-making algorithms such as Expansion and Swap operate by searchin...
CVPR
2011
IEEE
13 years 7 months ago
2011
IEEE
We present a hierarchical classification model that allows rare objects to borrow statistical strength from related objects that have many training examples. Unlike many of the e...
CVPR
2011
IEEE
13 years 7 months ago
2011
IEEE
The most popular way to use probabilistic models in vision is first to extract some descriptors of small image patches or object parts using well-engineered features, and then to...
CVPR
2011
IEEE
13 years 7 months ago
2011
IEEE
The recognition of text in everyday scenes is made difficult by viewing conditions, unusual fonts, and lack of linguistic context. Most methods integrate a priori appearance info...
CVPR
2011
IEEE
13 years 7 months ago
2011
IEEE
We present a novel framework for tree-structure embedded density estimation and its fast approximation for mode seeking. The proposed method could find diverse applications in co...
CVPR
2011
IEEE
13 years 7 months ago
2011
IEEE
Automatic face photo-sketch recognition has important applications to law enforcement. Recent research has focused on transforming photos and sketches into the same modality for m...
CVPR
2011
IEEE
13 years 7 months ago
2011
IEEE
This paper addresses the problem of learning similaritypreserving binary codes for efficient retrieval in large-scale image collections. We propose a simple and efficient altern...