Sciweavers

58 search results - page 9 / 12
» Segmentation-Based Motion with Occlusions Using Graph-Cut Op...
Sort
View
EUROGRAPHICS
2010
Eurographics
15 years 8 months ago
The Virtual Director: a Correlation-Based Online Viewing of Human Motion
Automatic camera control for scenes depicting human motion is an imperative topic in motion capture base animation, computer games, and other animation based fields. This challen...
Jackie Assa, Lior Wolf, Daniel Cohen-Or
CVPR
2006
IEEE
15 years 5 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. ...
EMMCVPR
2005
Springer
15 years 5 months ago
Dynamic Shape and Appearance Modeling Via Moving and Deforming Layers
Abstract. We propose a model of the shape, motion and appearance of a sequence of images that captures occlusions, scene deformations, arbitrary viewpoint variations and changes in...
Jeremy D. Jackson, Anthony J. Yezzi, Stefano Soatt...
ICIP
2009
IEEE
16 years 23 days ago
Localized Null Space Representation For Dynamic Updating And Downdating In Image And Video Databases
Event/object classification and recognition is an extremely challenging problem, particularly when the query or stored data undergo an affine transformation due to camera motion. ...
ICCV
2009
IEEE
14 years 9 months ago
Fast realistic multi-action recognition using mined dense spatio-temporal features
Within the field of action recognition, features and descriptors are often engineered to be sparse and invariant to transformation. While sparsity makes the problem tractable, it ...
Andrew Gilbert, John Illingworth, Richard Bowden