Sciweavers

1546 search results - page 200 / 310
» Computing Pose Sequences Directly from Videos
Sort
View
CVPR
2000
IEEE
14 years 1 months ago
Scene Modeling for Wide Area Surveillance and Image Synthesis
We present a method for modeling a scene that is observed by a moving camera, where only a portion of the scene is visible at any time. This method uses mixture models to represen...
Anurag Mittal, Daniel P. Huttenlocher
ECUMN
2007
Springer
14 years 24 days ago
Characterization of Slice-Based H.264/AVC Encoded Video Traffic
An explicit slice-based mode type selection scheme for use in H.264/AVC has recently been developed, which preserves the coding efficiency of H.264/AVC without requiring any modif...
Astrid Undheim, Yuan Lin, Peder J. Emstad
CVPR
2007
IEEE
14 years 11 months ago
Multi-class object tracking algorithm that handles fragmentation and grouping
We propose a framework for detecting and tracking multiple interacting objects, while explicitly handling the dual problems of fragmentation (an object may be broken into several ...
Biswajit Bose, Xiaogang Wang, Eric Grimson
ECCV
2006
Springer
14 years 16 days ago
Wavelet-Based Super-Resolution Reconstruction: Theory and Algorithm
We present an analysis and algorithm for the problem of super-resolution imaging, that is the reconstruction of HR (high-resolution) images from a sequence of LR (lowresolution) im...
Hui Ji, Cornelia Fermüller
CVPR
2010
IEEE
13 years 6 months ago
P-N learning: Bootstrapping binary classifiers by structural constraints
This paper shows that the performance of a binary classifier can be significantly improved by the processing of structured unlabeled data, i.e. data are structured if knowing the ...
Zdenek Kalal, Jiri Matas, Krystian Mikolajczyk