We present an integrated model for visual object localization and continuous state estimation in a discriminative structured prediction framework. While existing discriminative `p...
Central to many problems in scene understanding based on using a network of tens, hundreds or even thousands of randomly distributed cameras with on-board processing and wireless c...
Shubao Liu, Kongbin Kang, Jean-Philippe Tarel and ...
Particle filters (PFs) are powerful samplingbased inference/learning algorithms for dynamic Bayesian networks (DBNs). They allow us to treat, in a principled way, any type of prob...
Arnaud Doucet, Nando de Freitas, Kevin P. Murphy, ...
A novel technique for multi-scale curvature computation on a free-form 3-D surface is presented. This is achieved by convolving local parametrisations of the surface with 2-D Gauss...
The paper makes a short presentation of three existing methods for estimation of orientation tensors, the so-called structure tensor, quadrature filter based techniques, and techn...