CVPR
2012
IEEE
12 years 1 months ago
2012
IEEE
Scale invariant feature detectors often find stable scales in only a few image pixels. Consequently, methods for feature matching typically choose one of two extreme options: mat...
CVPR
2012
IEEE
12 years 1 months ago
2012
IEEE
This paper presents a general multi-view feature extraction approach that we call Generalized Multiview Analysis or GMA. GMA has all the desirable properties required for cross-vi...
ICCV
2011
IEEE
12 years 11 months ago
2011
IEEE
Linear subspace learning (LSL) is a popular approach to image recognition and it aims to reveal the essential features of high dimensional data, e.g., facial images, in a lower di...
TIFS
2008
13 years 11 months ago
2008
We present a theory for constructing linear subspace approximations to face-recognition algorithms and empirically demonstrate that a surprisingly diverse set of face-recognition a...
IJCV
2007
13 years 11 months ago
2007
Abstract. The appearance of an object greatly changes under different lighting conditions. Even so, previous studies have demonstrated that the appearance of an object under varyin...
PAMI
2006
13 years 11 months ago
2006
Linear subspace methods that provide sufficient reconstruction of the data, such as PCA, offer an efficient way of dealing with missing pixels, outliers, and occlusions that often ...
SOFSEM
2000
Springer
14 years 2 months ago
2000
Springer
Abstract. Since its very beginning, linear algebra is a highly algorithmic subject. Let us just mention the famous Gau
COLT
2006
Springer
14 years 2 months ago
2006
Springer
We address the problem of online de-noising a stream of input points. We assume that the clean data is embedded in a linear subspace. We present two online algorithms for tracking ...
ICCV
1999
IEEE
14 years 3 months ago
1999
IEEE
We show that the set of all ow- elds in a sequence of frames imaging a rigid scene resides in a lowdimensional linear subspace. Based on this observation, we develop a method for ...
COCO
2004
Springer
14 years 4 months ago
2004
Springer
We study the power of quantum proofs, or more precisely, the power of Quantum MerlinArthur (QMA) protocols, in two well studied models of quantum computation: the black box model ...