112
click to vote
ICCV
2007
IEEE
16 years 2 months ago
2007
IEEE
Indisputably Normalized Cuts is one of the most popular segmentation algorithms in computer vision. It has been applied to a wide range of segmentation tasks with great success. A...
116
click to vote
ICCV
2007
IEEE
16 years 2 months ago
2007
IEEE
Most previous motion deblurring methods restore the degraded image assuming a shift-invariant linear blur filter. These methods are not applicable if the blur is caused by spatial...
ICCV
2007
IEEE
16 years 2 months ago
2007
IEEE
This paper presents a technique for determining an object's shape based on the similarity of radiance changes observed at points on its surface under varying illumination. To...
ICCV
2007
IEEE
16 years 2 months ago
2007
IEEE
We present a novel stochastic, adaptive strategy for tracking multiple people in a large network of video cameras. Similarities between features (appearance and biometrics) observ...
59
Voted
ICCV
2007
IEEE
16 years 2 months ago
2007
IEEE
101
Voted
ICCV
2007
IEEE
16 years 2 months ago
2007
IEEE
Capacity scaling is a hierarchical approach to graph representation that can improve theoretical complexity and practical efficiency of max-flow/min-cut algorithms. Introduced by ...
127
Voted
ICCV
2007
IEEE
16 years 2 months ago
2007
IEEE
We present a biologically-motivated system for the recognition of actions from video sequences. The approach builds on recent work on object recognition based on hierarchical feed...
122
Voted
ICCV
2007
IEEE
16 years 2 months ago
2007
IEEE
This paper presents a new method to detect and accurately extract the moving object from a video sequence taken by a hand-held camera. In order to extract the high quality moving ...
101
Voted
ICCV
2007
IEEE
16 years 2 months ago
2007
IEEE
Visual tracking is a very important front-end to many vision applications. We present a new framework for robust visual tracking in this paper. Instead of just looking forward in ...
114
Voted
ICCV
2007
IEEE
16 years 2 months ago
2007
IEEE
We propose a novel and robust model to represent and learn generic 3D object categories. We aim to solve the problem of true 3D object categorization for handling arbitrary rotati...