125 search results - page 3 / 25 » Generative Models for Labeling Multi-object Configurations i... |
SGP
2003
13 years 6 months ago
2003
In this paper we present a novel algorithm for reconstructing 3D scenes from a set of images. The user defines a set of polygonal regions with corresponding labels in each image ...
ICCV
2005
IEEE
14 years 7 months ago
2005
IEEE
We present a two-layer hierarchical formulation to exploit different levels of contextual information in images for robust classification. Each layer is modeled as a conditional f...
PAMI
2006
13 years 5 months ago
2006
The problem we consider in this paper is to take a single two-dimensional image containing a human figure, locate the joint positions, and use these to estimate the body configura...
CLOR
2006
13 years 9 months ago
2006
We describe a novel method for real-time, simultaneous multi-view face detection and facial pose estimation. The method employs a convolutional network to map face images to point...
ECCV
2008
Springer
14 years 10 months ago
2008
Springer
We consider the problem of multi-label, supervised image segmentation when an initial labeling of some pixels is given. In this paper, we propose a new generative image segmentatio...