Sciweavers

828 search results - page 28 / 166
» Robust Focused Image Estimation from Multiple Images in Vide...
Sort
View
CVPR
2007
IEEE
14 years 10 months ago
Towards Robust Pedestrian Detection in Crowded Image Sequences
Object class detection in scenes of realistic complexity remains a challenging task in computer vision. Most recent approaches focus on a single and general model for object class...
Edgar Seemann, Mario Fritz, Bernt Schiele
CVIU
2011
13 years 3 months ago
Action recognition with appearance-motion features and fast search trees
In this paper we propose an approach for action recognition based on a vocabulary of local motion-appearance features and fast approximate search in a large number of trees. Large...
Krystian Mikolajczyk, Hirofumi Uemura
ICIP
2010
IEEE
13 years 6 months ago
Compressed domain global motion estimation using the Helmholtz Tradeoff Estimator
Several algorithms for global motion estimation in video sequences using pixel- or block-based approaches have been published. Most known pixel-based methods lack in performance w...
Michael Tok, Alexander Glantz, Marina Georgia Arva...
ICIP
2008
IEEE
14 years 10 months ago
Live video object tracking and segmentation using graph cuts
Graph cuts have proven to be powerful tools in image segmentation. Previous graph cut research has proposed methods for cutting across large graphs constructed from multiple layer...
Zachary A. Garrett, Hideo Saito
CVPR
2004
IEEE
14 years 10 months ago
Multiple Bernoulli Relevance Models for Image and Video Annotation
Retrieving images in response to textual queries requires some knowledge of the semantics of the picture. Here, we show how we can do both automatic image annotation and retrieval...
Shaolei Feng, Raghavan Manmatha, Victor Lavrenko