181 search results - page 12 / 37 » iccv 2011 |
247
Voted
ICCV
2011
IEEE
14 years 11 days ago
2011
IEEE
Complex human activities occurring in videos can be defined in terms of temporal configurations of primitive actions. Prior work typically hand-picks the primitives, their total...
117
click to vote
ICCV
2011
IEEE
14 years 11 days ago
2011
IEEE
Human-nameable visual “attributes” can benefit various recognition tasks. However, existing techniques restrict these properties to categorical labels (for example, a person ...
107
click to vote
ICCV
2011
IEEE
14 years 11 days ago
2011
IEEE
This paper presents a novel approach to recovering temporally coherent estimates of 3D structure of a dynamic scene from a sequence of binocular stereo images. The approach is bas...
122
Voted
ICCV
2011
IEEE
14 years 11 days ago
2011
IEEE
This paper presents a novel schema to address the polysemy of visual words in the widely used bag-of-words model. As a visual word may have multiple meanings, we show it is possib...
149
Voted
ICCV
2011
IEEE
14 years 11 days ago
2011
IEEE
The number of applications in computer vision that model higher-order interactions has exploded over the last few years. The standard technique for solving such problems is to red...