CVPR
2008
IEEE
15 years 1 months ago
2008
IEEE
We propose a variational bayes approach to the problem of robust estimation of gaussian mixtures from noisy input data. The proposed algorithm explicitly takes into account the un...
CVPR
2008
IEEE
15 years 1 months ago
2008
IEEE
In background subtraction, cast shadows induce silhouette distortions and object fusions hindering performance of high level algorithms in scene monitoring. We introduce a nonpara...
CVPR
2008
IEEE
15 years 1 months ago
2008
IEEE
We present a method that is capable of tracking and estimating pose of articulated objects in real-time. This is achieved by using a bottom-up approach to detect instances of the ...
CVPR
2008
IEEE
15 years 1 months ago
2008
IEEE
We present a practical framework for detecting and modeling 3D static occlusions for wide-baseline, multi-camera scenarios where the number of cameras is small. The framework cons...
CVPR
2008
IEEE
15 years 1 months ago
2008
IEEE
The robust alignment of images and scenes seen from widely different viewpoints is an important challenge for camera and scene reconstruction. This paper introduces a novel class ...
CVPR
2008
IEEE
15 years 1 months ago
2008
IEEE
The Middlebury Multi-View Stereo evaluation [18] clearly shows that the quality and speed of most multi-view stereo algorithms depends significantly on the number and selection of...
CVPR
2008
IEEE
15 years 1 months ago
2008
IEEE
Image understanding involves analyzing many different aspects of the scene. In this paper, we are concerned with how these tasks can be combined in a way that improves the perform...
CVPR
2008
IEEE
15 years 1 months ago
2008
IEEE
Online boosting methods have recently been used successfully for tracking, background subtraction etc. Conventional online boosting algorithms emphasize on interchanging new weak ...
CVPR
2008
IEEE
15 years 1 months ago
2008
IEEE
Given an input video sequence of one person conducting a sequence of continuous actions, we consider the problem of jointly segmenting and recognizing actions. We propose a discri...
CVPR
2008
IEEE
15 years 1 months ago
2008
IEEE
We present a novel method for the discovery and detection of visual object categories based on decompositions using topic models. The approach is capable of learning a compact and...