Sciweavers

13 search results - page 2 / 3
» A Gradient Descent Approximation for Graph Cuts
Sort
View
EMMCVPR
2011
Springer
12 years 9 months ago
Discrete Optimization of the Multiphase Piecewise Constant Mumford-Shah Functional
Abstract. The Mumford-Shah model has been one of the most powerful models in image segmentation and denoising. The optimization of the multiphase Mumford-Shah energy functional has...
Noha Youssry El-Zehiry, Leo Grady
CVPR
2008
IEEE
14 years 11 months ago
Shape prior segmentation of multiple objects with graph cuts
We present a new shape prior segmentation method using graph cuts capable of segmenting multiple objects. The shape prior energy is based on a shape distance popular with level se...
Nhat Vu, B. S. Manjunath
CVPR
2008
IEEE
14 years 11 months ago
FusionFlow: Discrete-continuous optimization for optical flow estimation
Accurate estimation of optical flow is a challenging task, which often requires addressing difficult energy optimization problems. To solve them, most top-performing methods rely ...
Victor S. Lempitsky, Stefan Roth, Carsten Rother
NIPS
2008
13 years 10 months ago
An Extended Level Method for Efficient Multiple Kernel Learning
We consider the problem of multiple kernel learning (MKL), which can be formulated as a convex-concave problem. In the past, two efficient methods, i.e., Semi-Infinite Linear Prog...
Zenglin Xu, Rong Jin, Irwin King, Michael R. Lyu
ECCV
2008
Springer
14 years 7 months ago
Toward Global Minimum through Combined Local Minima
There are many local and greedy algorithms for energy minimization over Markov Random Field (MRF) such as iterated condition mode (ICM) and various gradient descent methods. Local ...
Ho Yub Jung, Kyoung Mu Lee, Sang Uk Lee