Knowing a good feature when you see it: Ground truth and methodology to evaluate local features for recognition
While the majority of computer vision systems are based on representing images by local features, the design of the latter has been so far mostly empirical. In this Chapter we propose to tie the design of local features to their systematic evaluation on a realistic ground-truthed dataset. We propose...
Main Authors: | Vedaldi, A, Ling, H, Soatto, S |
---|---|
Format: | Journal article |
Language: | English |
Published: |
2010
|
Similar Items
-
Features for recognition: Viewpoint invariance for non-planar scenes
by: Vedaldi, A, et al.
Published: (2005) -
Local features, all grown up
by: Vedaldi, A, et al.
Published: (2006) -
Professionalism: hard to measure but you know it when you see it
by: Robert P. Ferguson
Published: (2014-04-01) -
Viewpoint induced deformation statistics and the design of viewpoint invariant features: Singularities and occlusions
by: Vedaldi, A, et al.
Published: (2006) -
May I see what you see? Predicting visual features from neuronal activity
by: Vikram Ravindra, et al.
Published: (2024-02-01)