Sciweavers

748 search results - page 13 / 150
» Learning Feature Distance Measures for Image Correspondences
Sort
View
NIPS
2004
13 years 9 months ago
The Laplacian PDF Distance: A Cost Function for Clustering in a Kernel Feature Space
A new distance measure between probability density functions (pdfs) is introduced, which we refer to as the Laplacian pdf distance. The Laplacian pdf distance exhibits a remarkabl...
Robert Jenssen, Deniz Erdogmus, José Carlos...
CVPR
2000
IEEE
14 years 10 months ago
Structure from Motion without Correspondence
A method is presented to recover 3D scene structure and camera motion from multiple images without the need for correspondence information. The problem is framed as finding the ma...
Frank Dellaert, Steven M. Seitz, Charles E. Thorpe...
CVPR
2003
IEEE
14 years 10 months ago
The Optimal Distance Measure for Object Detection
We develop a multi-class object detection framework whose core component is a nearest neighbor search over object part classes. The performance of the overall system is critically...
Shyjan Mahamud, Martial Hebert
CVPR
2011
IEEE
13 years 4 months ago
Learning a Blind Measure of Perceptual Image Quality
It is often desirable to evaluate an image based on its quality. For many computer vision applications, a perceptually meaningful measure is the most relevant for evaluation; howe...
Huixuan Tang, Neel Joshi, Ashish Kapoor
MM
2004
ACM
167views Multimedia» more  MM 2004»
14 years 1 months ago
Learning an image manifold for retrieval
We consider the problem of learning a mapping function from low-level feature space to high-level semantic space. Under the assumption that the data lie on a submanifold embedded ...
Xiaofei He, Wei-Ying Ma, HongJiang Zhang