In this paper we present a method of parameter optimization, relative trust-region learning, where the trust-region method and the relative optimization [21] are jointly exploited...
Real-world action recognition applications require the development of systems which are fast, can handle a large variety of actions without a priori knowledge of the type of actio...
This paper presents a method for modeling the surface of an object from a sequence of range maps. Our method is based on a volumetric approach that produces a compact surface with...
Kari Pulli, Tom Duchamp, Hugues Hoppe, John Alan M...
We have developed methods for segmentation and tracking of cells in time-lapse phase-contrast microscopy images. Our multi-object Bayesian algorithm detects and tracks large num...
David House, Matthew Walker, Zheng Wu, Joyce Wong,...
In this paper we address the problem of registering 3D scattered data by the mean of a statistical shape model. This model is built from a training set on which a principal compon...