133
click to vote
ICCV
2009
IEEE
16 years 8 months ago
2009
IEEE
In this paper, we investigate the detection of semantic
human actions in complex scenes. Unlike conventional
action recognition in well-controlled environments,
action detection...
121
click to vote
ICCV
2009
IEEE
16 years 8 months ago
2009
IEEE
The classical approach to depth from defocus uses two
images taken with circular apertures of different sizes. We
show in this paper that the use of a circular aperture
severely...
135
click to vote
ICCV
2009
IEEE
16 years 8 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 ...
108
click to vote
ICCV
2009
IEEE
16 years 8 months ago
2009
IEEE
User-provided object bounding box is a simple and
popular interaction paradigm considered by many existing
interactive image segmentation frameworks. However,
these frameworks t...
121
click to vote
ICCV
2009
IEEE
16 years 8 months ago
2009
IEEE
This purely theoretical work investigates the problem
of artificial singularities in camera self-calibration. Selfcalibration
allows one to upgrade a projective reconstruction
t...