Sciweavers

3719 search results - page 589 / 744
» RACER System Description
Sort
View
CVPR
2003
IEEE
16 years 8 months ago
Expectation Grammars: Leveraging High-Level Expectations for Activity Recognition
Video-based recognition and prediction of a temporally extended activity can benefit from a detailed description of high-level expectations about the activity. Stochastic grammars...
David Minnen, Irfan A. Essa, Thad Starner
ICCV
2005
IEEE
16 years 8 months ago
Integration of Conditionally Dependent Object Features for Robust Figure/Background Segmentation
We propose a new technique for fusing multiple cues to robustly segment an object from its background in video sequences that suffer from abrupt changes of both illumination and p...
Francesc Moreno-Noguer, Alberto Sanfeliu, Dimitris...
ICCV
1998
IEEE
16 years 8 months ago
Retrieving Images by Appearance
A system to retrieve images using a description of the image intensity surface is presented. Gaussian derivative lters at several scales are applied to the image and low order 2D ...
S. Ravela, R. Manmatha
ICIP
2008
IEEE
16 years 8 months ago
A master-slave approach for object detection and matching with fixed and mobile cameras
Typical object detection algorithms on mobile cameras suffer from the lack of a-priori knowledge on the object to be detected. The variability in the shape, pose, color distributi...
Alexandre Alahi, David Marimon, Michel Bierlaire, ...
ICIP
2004
IEEE
16 years 8 months ago
Systematic lossy forward error protection for error-resilient digital video broadcasting -a wyner-ziv coding approach
We present a practical scheme for error-resilient digital video broadcasting, using the Wyner-Ziv coding paradigm. We apply the general framework of systematic lossy source-channe...
Shantanu Rane, Anne Aaron, Bernd Girod