6005 search results - page 761 / 1201 » Graph-Theoretical Methods in Computer Vision |
181
Voted
CVPR
2010
IEEE
16 years 3 months ago
2010
IEEE
We propose a semi-supervised model which segments and annotates images using very few labeled images and a large unaligned text corpus to relate image regions to text labels. Give...
207
Voted
CVPR
2010
IEEE
16 years 3 months ago
2010
IEEE
We present two novel methods to automatically learn spatio-temporal dependencies of moving agents in complex dynamic scenes. They allow to discover temporal rules, such as the rig...
207
Voted
CVPR
2010
IEEE
2010
IEEE
Learning a Hierarchy of Discriminative Space-Time Neighborhood Features for Human Action Recognition
16 years 3 months ago
Recent work shows how to use local spatio-temporal features to learn models of realistic human actions from video. However, existing methods typically rely on a predefined spatial...
198
Voted
CVPR
2010
IEEE
16 years 3 months ago
2010
IEEE
How can knowing about some categories help us to discover new ones in unlabeled images? Unsupervised visual category discovery is useful to mine for recurring objects without huma...
164
Voted
CVPR
2010
IEEE
16 years 3 months ago
2010
IEEE
We present an automatic and efficient method to extract spatio-temporal human volumes from video, which combines top-down model-based and bottom-up appearancebased approaches. Fr...