Sciweavers

174 search results - page 18 / 35
» Dimensionality reduction using magnitude and shape approxima...
Sort
View
ICCV
2007
IEEE
15 years 11 months ago
Shape Reconstruction Based on Similarity in Radiance Changes under Varying Illumination
This paper presents a technique for determining an object's shape based on the similarity of radiance changes observed at points on its surface under varying illumination. To...
Imari Sato, Takahiro Okabe, Qiong Yu, Yoichi Sato
CIKM
2008
Springer
14 years 11 months ago
On low dimensional random projections and similarity search
Random projection (RP) is a common technique for dimensionality reduction under L2 norm for which many significant space embedding results have been demonstrated. However, many si...
Yu-En Lu, Pietro Liò, Steven Hand
WACV
2012
IEEE
13 years 5 months ago
CompactKdt: Compact signatures for accurate large scale object recognition
We present a novel algorithm, Compact Kd-Trees (CompactKdt), that achieves state-of-the-art performance in searching large scale object image collections. The algorithm uses an or...
Mohamed Aly, Mario E. Munich, Pietro Perona
CVPR
2008
IEEE
15 years 11 months ago
Large-scale manifold learning
This paper examines the problem of extracting lowdimensional manifold structure given millions of highdimensional face images. Specifically, we address the computational challenge...
Ameet Talwalkar, Sanjiv Kumar, Henry A. Rowley
FGR
2006
IEEE
217views Biometrics» more  FGR 2006»
15 years 3 months ago
Face Recognition with Image Sets Using Hierarchically Extracted Exemplars from Appearance Manifolds
An unsupervised nonparametric approach is proposed to automatically extract representative face samples (exemplars) from a video sequence or an image set for multipleshot face rec...
Wei Fan, Dit-Yan Yeung