Sciweavers

888 search results - page 45 / 178
» Global pose estimation using non-tree models
Sort
View
ICCV
2005
IEEE
15 years 1 months ago
Identifying Individuals in Video by Combining "Generative" and Discriminative Head Models
The objective of this work is automatic detection and identification of individuals in unconstrained consumer video, given a minimal number of labelled faces as training data. Whi...
Mark Everingham, Andrew Zisserman
PAMI
2008
156views more  PAMI 2008»
13 years 11 months ago
Tied Factor Analysis for Face Recognition across Large Pose Differences
Face recognition algorithms perform very unreliably when the pose of the probe face is different from the gallery face: typical feature vectors vary more with pose than with identi...
Simon J. D. Prince, James H. Elder, Jonathan Warre...
AMDO
2006
Springer
14 years 2 months ago
Predicting 3D People from 2D Pictures
Abstract. We propose a hierarchical process for inferring the 3D pose of a person from monocular images. First we infer a learned view-based 2D body model from a single image using...
Leonid Sigal, Michael J. Black
CVIU
2008
132views more  CVIU 2008»
13 years 10 months ago
Global parametric image alignment via high-order approximation
The estimation of parametric global motion is one of the cornerstones of computer vision. Such schemes are able to estimate various motion models (translation, rotation, affine, p...
Yosi Keller, Amir Averbuch
ICCV
2007
IEEE
14 years 5 months ago
Real Time Body Pose Tracking in an Immersive Training Environment
Abstract. We describe a visual communication application for a dark, theaterlike interactive virtual simulation training environment. Our system visually estimates and tracks the b...
Chi-Wei Chu, Ramakant Nevatia