DAGM
2008
Springer
14 years 1 months ago
2008
Springer
We introduce the OneClassMaxMinOver (OMMO) algorithm for the problem of one-class support vector classification. The algorithm is extremely simple and therefore a convenient choice...
DAGM
2008
Springer
14 years 1 months ago
2008
Springer
Abstract. Virtually all variational methods for motion estimation regularize the gradient of the flow field, which introduces a bias towards piecewise constant motions in weakly te...
DAGM
2008
Springer
14 years 1 months ago
2008
Springer
Abstract. Applying real-time segmentation is a major issue when processing every frame of image sequences. In this paper, we propose a modification of the well known graph-cut algo...
DAGM
2008
Springer
14 years 1 months ago
2008
Springer
Three-dimensional electron-microscopic image stacks with almost isotropic resolution allow, for the first time, to determine the complete connection matrix of parts of the brain. I...
DAGM
2008
Springer
14 years 1 months ago
2008
Springer
This paper demonstrates how a simple, yet effective, set of features enables to integrate ensemble classifiers in optical flow based tracking. In particular, gray value differences...
DAGM
2008
Springer
14 years 1 months ago
2008
Springer
DAGM
2008
Springer
14 years 1 months ago
2008
Springer
This article presents a genetic learning algorithm to derive discrete patterns that can be used for classification and retrieval of 3D motion capture data. Based on boolean motion ...
DAGM
2008
Springer
14 years 1 months ago
2008
Springer
In particle image velocimetry (PIV) a temporally separated image pair of a gas or liquid seeded with small particles is recorded and analysed in order to measure fluid flows therei...
DAGM
2008
Springer
14 years 1 months ago
2008
Springer
The design of inference algorithms for discrete-valued Markov Random Fields constitutes an ongoing research topic in computer vision. Large state-spaces, none-submodular energy-fun...
DAGM
2008
Springer
14 years 1 months ago
2008
Springer
Abstract. In this paper, we propose a new approach to learn structured visual compound models from shape-based feature descriptions. We use captioned text in order to drive the pro...