5082 search results - page 501 / 1017 » Actionable Information in Vision |
214
click to vote
CVPR
2012
IEEE
13 years 9 months ago
2012
IEEE
Most image understanding algorithms begin with the extraction of information thought to be relevant to the particular task. This is commonly known as feature extraction and has, u...
222
click to vote
CVPR
2012
IEEE
13 years 9 months ago
2012
IEEE
We identify and study two types of “accidental” images that can be formed in scenes. The first is an accidental pinhole camera image. These images are often mistaken for shad...
203
click to vote
CVPR
2012
IEEE
13 years 9 months ago
2012
IEEE
For scene classification, patch-level linear features do not always work as well as handcrafted features. In this paper, we present a new model to greatly improve the usefulness ...
252
click to vote
CVPR
2012
IEEE
13 years 9 months ago
2012
IEEE
Motion segmentation based on point trajectories can integrate information of a whole video shot to detect and separate moving objects. Commonly, similarities are defined between ...
236
click to vote
CVPR
2012
IEEE
13 years 9 months ago
2012
IEEE
Point cloud is one of the primitive representations of 3D data nowadays. Despite that much work has been done in 2D image matching, matching 3D points achieved from different pers...