130 search results - page 19 / 26 » Making Better Use of Global Discretization |
AVSS
2008
IEEE
13 years 9 months ago
2008
IEEE
Super-resolution (SR) of facial images from video suffers from facial expression changes. Most of the existing SR algorithms for facial images make an unrealistic assumption that ...
SIAMSC
2008
13 years 7 months ago
2008
In this study, nonnegative matrix factorization is recast as the problem of approximating a polytope on the probability simplex by another polytope with fewer facets. Working on th...
DAGM
2011
Springer
12 years 7 months ago
2011
Springer
Many unsupervised learning algorithms make use of kernels that rely on the Euclidean distance between two samples. However, the Euclidean distance is optimal for Gaussian distribut...
CVPR
2012
IEEE
11 years 10 months ago
2012
IEEE
In this paper, we deal with the estimation of body and head poses (i.e orientations) in surveillance videos, and we make three main contributions. First, we address this issue as ...
ISPD
2004
ACM
14 years 27 days ago
2004
ACM
VLSI placement tools usually work in two steps: First, the cells that have to be placed are roughly spread out over the chip area ignoring disjointness (global placement). Then, i...