Localizing objects with smart dictionaries
We present an approach to determine the category and location of objects in images. It performs very fast categorization of each pixel in an image, a brute-force approach made feasible by three key developments: First, our method reduces the size of a large generic dictionary (on the order of ten th...
Main Authors: | Fulkerson, B, Vedaldi, A, Soatto, S |
---|---|
Format: | Journal article |
Language: | English |
Published: |
2008
|
Similar Items
-
Local features, all grown up
by: Vedaldi, A, et al.
Published: (2006) -
Knowing a good feature when you see it: Ground truth and methodology to evaluate local features for recognition
by: Vedaldi, A, et al.
Published: (2010) -
Quick shift and kernel methods for mode seeking
by: Vedaldi, A, et al.
Published: (2008) -
Relaxed matching kernels for robust image comparison
by: Vedaldi, A, et al.
Published: (2008) -
A complexity-distortion approach to joint pattern alignment
by: Vedaldi, A, et al.
Published: (2007)