27274 search results - page 4846 / 5455 » A framework for framework documentation |
231
click to vote
CVPR
2011
IEEE
15 years 3 months ago
2011
IEEE
The bounding box representation employed by many popular object detection models [3, 6] implicitly assumes all pixels inside the box belong to the object. This assumption makes th...
250
click to vote
CVPR
2011
IEEE
15 years 3 months ago
2011
IEEE
We propose to bridge the gap between Random Field (RF) formulations for joint categorization and segmentation (JCaS), which model local interactions among pixels and superpixels, ...
217
click to vote
CVPR
2011
IEEE
15 years 3 months ago
2011
IEEE
We explore a polar representation of optical flow in which each element of the brightness motion field is represented by its magnitude and orientation instead of its Cartesian p...
188
click to vote
CVPR
2011
IEEE
15 years 3 months ago
2011
IEEE
For two consecutive frames in a video, we identify which pixels in the first frame become occluded in the second. Such general-purpose detection of occlusion regions is difficul...
238
click to vote
CVPR
2011
IEEE
15 years 3 months ago
2011
IEEE
It is often desirable to evaluate an image based on its quality. For many computer vision applications, a perceptually meaningful measure is the most relevant for evaluation; howe...