886 search results - page 145 / 178 » Computing Visual Attention from Scene Depth |
ICIP
2009
IEEE
15 years 10 months ago
2009
IEEE
We propose an illumination invariant and rotation insensitive texture representation based on a Markovian textural model. A texture is aligned with its dominant orientation and te...
SG
2010
Springer
15 years 2 months ago
2010
Springer
Hand-drawn pictures differ from ordinary perspective images in that the entire scene is composed of local feature regions each of which is projected individually as seen from its ...
CVPR
2004
IEEE
15 years 11 months ago
2004
IEEE
We present a method for space-time completion of large space-time "holes" in video sequences of complex dynamic scenes. The missing portions are filled-in by sampling sp...
ICCV
1999
IEEE
15 years 11 months ago
1999
IEEE
A family of axially symmetric mirror shapes are proposed for panoramic imaging. These shapes keep the resolution in the image invariant to changes in elevation in the scene. In ot...
121
click to vote
AIHC
2007
Springer
15 years 4 months ago
2007
Springer
This work addresses the problem of human action recognition by introducing a representation of a human action as a collection of short trajectories that are extracted in areas of ...