Sciweavers

11462 search results - page 155 / 2293
» Developing Application-Centric Methods
Sort
View
ISVC
2009
Springer
16 years 28 days ago
Two Step Variational Method for Subpixel Optical Flow Computation
We develop an algorithm for the super-resolution optical flow computation by combining variational super-resolution and the variational optical flow computation. Our method firs...
Yoshihiko Mochizuki, Yusuke Kameda, Atsushi Imiya,...
FCCM
2006
IEEE
268views VLSI» more  FCCM 2006»
16 years 13 days ago
Sparse Matrix-Vector Multiplication for Finite Element Method Matrices on FPGAs
We present an architecture and an implementation of an FPGA-based sparse matrix-vector multiplier (SMVM) for use in the iterative solution of large, sparse systems of equations ar...
Yousef El-Kurdi, Warren J. Gross, Dennis Giannacop...
ICCS
2005
Springer
15 years 12 months ago
Adaptive Model Trust Region Methods for Generalized Eigenvalue Problems
Computing a few eigenpairs of large-scale matrices is a significant problem in science and engineering applications and a very active area of research. In this paper, two methods...
Pierre-Antoine Absil, C. G. Baker, Kyle A. Galliva...
ISCAS
1994
IEEE
104views Hardware» more  ISCAS 1994»
15 years 10 months ago
A Homotopy Continuation Method for Parameter Estimation in MRF Models and Image Restoration
In this paper, we present an alternate approach to estimate the parameters of a Markov random field (MRF) model for images using the concepts of homotopy continuation method. We a...
P. K. Nanda, Uday B. Desai, P. G. Poonacha
ESANN
1997
15 years 7 months ago
Neural network cooperation for handwritten digit recognition: a comparison of four methods
In this paper we focus on "off-line digit recognition" with anknown scriptor. After presenting two neural recognisers, we evaluate four solutions to combine results obta...
Yvon Autret, Andre Thepaut