In this paper we show that Ullman and Basri’s linear combination (LC) representation, which was originally proposed for alignment-based object recognition, can be used for outli...
We investigate fully parallel Newton-Krylov-Schwarz (NKS) algorithms for solving the large sparse nonlinear systems of equations arising from the finite element discretization of ...
With the success of local features in object recognition, feature-set representations are widely used in computer vision and related domains. Pyramid match kernel (PMK) is an effi...
Coarse piecewise linear approximation of surfaces causes undesirable polygonal appearance of silhouettes. We present an efficient method for smoothing the silhouettes of coarse tri...
Lu Wang, Changhe Tu, Wenping Wang, Xiangxu Meng, B...
PCA-SIFT is an extension to SIFT which aims to reduce SIFT’s high dimensionality (128 dimensions) by applying PCA to the gradient image patches. However PCA is not a discriminati...