49 search results - page 8 / 10 » Multiresolution Gaussian mixture models for visual motion es... |
JMM2
2007
13 years 7 months ago
2007
— The automatic extraction and analysis of visual information is becoming generalised. The first step in this processing chain is usually separating or segmenting the captured v...
ICCV
2003
IEEE
14 years 9 months ago
2003
IEEE
We present a method for unsupervised learning of classes of motions in video. We project optical flow fields to a complete, orthogonal, a-priori set of basis functions in a probab...
MIAR
2006
IEEE
14 years 1 months ago
2006
IEEE
This paper proposes a novel framework for robust click-point linking: efficient localized registration that allows users to interactively prescribe where the accuracy has to be hig...
ICML
2005
IEEE
14 years 8 months ago
2005
IEEE
We provide a general framework for learning precise, compact, and fast representations of the Bayesian predictive distribution for a model. This framework is based on minimizing t...
ECCV
2002
Springer
14 years 9 months ago
2002
Springer
Visual sensors provide exclusively uncertain and partial knowledge of a scene. In this article, we present a suitable scene knowledge representation that makes integration and fusi...