2960 search results - page 516 / 592 » Learning from Multiple Sources |
130
Voted
ICCV
2009
IEEE
16 years 7 months ago
2009
IEEE
High-level, or holistic, scene understanding involves
reasoning about objects, regions, and the 3D relationships
between them. This requires a representation above the
level of ...
124
Voted
CVPR
2006
IEEE
16 years 4 months ago
2006
IEEE
Segmentation involves separating an object from the background. In this work, we propose a novel segmentation method combining image information with prior shape knowledge, within...
121
Voted
ICCV
2007
IEEE
16 years 4 months ago
2007
IEEE
A successful representation of objects in the literature is as a collection of patches, or parts, with a certain appearance and position. The relative locations of the different p...
119
Voted
CVPR
2007
IEEE
16 years 4 months ago
2007
IEEE
We present a novel framework for tracking of a long sequence of human activities, including the time instances of change from one activity to the next, using a closed-loop, non-li...
111
click to vote
ECCV
2008
Springer
16 years 4 months ago
2008
Springer
In this paper, we propose a component-based discriminative approach for face alignment without requiring initialization1 . Unlike many approaches which locally optimize in a small ...