7978 search results - page 1334 / 1596 » Representation before computation |
214
click to vote
CVPR
2012
IEEE
13 years 9 months ago
2012
IEEE
Current object class recognition systems typically target 2D bounding box localization, encouraged by benchmark data sets, such as Pascal VOC. While this seems suitable for the de...
224
click to vote
CVPR
2012
IEEE
13 years 9 months ago
2012
IEEE
The bag-of-words (BoW) model treats images as an unordered set of local regions and represents them by visual word histograms. Implicitly, regions are assumed to be identically an...
234
click to vote
CVPR
2012
IEEE
13 years 9 months ago
2012
IEEE
Top-down visual saliency facilities object localization by providing a discriminative representation of target objects and a probability map for reducing the search space. In this...
220
click to vote
CVPR
2012
IEEE
13 years 9 months ago
2012
IEEE
The choice of the over-complete dictionary that sparsely represents data is of prime importance for sparse codingbased image super-resolution. Sparse coding is a typical unsupervi...
175
click to vote
ACL
2012
13 years 9 months ago
2012
Stanford dependencies are widely used in natural language processing as a semanticallyoriented representation, commonly generated either by (i) converting the output of a constitu...