Sciweavers

385 search results - page 48 / 77
» Human Pose Estimation Using Consistent Max-Covering
Sort
View
MICCAI
2003
Springer
14 years 9 months ago
Extraction and Application of Expert Priors to Combine Multiple Segmentations of Human Brain Tissue
Abstract. This paper evaluates strategies to combine multiple segmentations of the same image, generated for example by different segmentation methods or by different human experts...
Torsten Rohlfing, Daniel B. Russakoff, Calvin R. M...
CVPR
2006
IEEE
14 years 2 months ago
Learning Joint Top-Down and Bottom-up Processes for 3D Visual Inference
We present an algorithm for jointly learning a consistent bidirectional generative-recognition model that combines top-down and bottom-up processing for monocular 3d human motion ...
Cristian Sminchisescu, Atul Kanaujia, Dimitris N. ...
ICCV
2011
IEEE
12 years 8 months ago
N-best maximal decoders for part models
We describe a method for generating N-best configurations from part-based models, ensuring that they do not overlap according to some user-provided definition of overlap. We ext...
Dennis Park, Deva Ramanan
TIP
2010
129views more  TIP 2010»
13 years 3 months ago
Image Segmentation by MAP-ML Estimations
Abstract--Image segmentation plays an important role in computer vision and image analysis. In this paper, image segmentation is formulated as a labeling problem under a probabilit...
Shifeng Chen, Liangliang Cao, Yueming Wang, Jianzh...
ECCV
2010
Springer
14 years 1 months ago
Combining Geometric and Appearance Priors for Robust Homography Estimation
Abstract. The homography between pairs of images are typically computed from the correspondence of keypoints, which are established by using image descriptors. When these descripto...