ECCV
2004
Springer
15 years 4 months ago
2004
Springer
Methods based on local, viewpoint invariant features have proven capable of recognizing objects in spite of viewpoint changes, occlusion and clutter. However, these approaches fail...
CVPR
2004
IEEE
15 years 4 months ago
2004
IEEE
We describe a method for obtaining the principal objects, characters and scenes in a video by measuring the reoccurrence of spatial configurations of viewpoint invariant features....