200
click to vote
CVPR
2011
IEEE
14 years 10 months ago
2011
IEEE
Dictionary learning is a challenging theme in computer vision. The basic goal is to learn a sparse representation from an overcomplete basis set. Most existing approaches employ a...
203
click to vote
CVPR
2011
IEEE
14 years 10 months ago
2011
IEEE
Object segmentation needs to be driven by top-down knowledge to produce semantically meaningful results. In this paper, we propose a supervised segmentation approach that tightly ...
248
click to vote
CVPR
2011
IEEE
14 years 10 months ago
2011
IEEE
We propose a novel nonlinear, probabilistic and variational method for adding shape information to level setbased segmentation and tracking. Unlike previous work, we represent sha...
219
click to vote
CVPR
2011
IEEE
14 years 10 months ago
2011
IEEE
Online learned tracking is widely used for it’s adaptive ability to handle appearance changes. However, it introduces potential drifting problems due to the accumulation of erro...
199
click to vote
CVPR
2011
IEEE
14 years 10 months ago
2011
IEEE
We propose a new objective function for superpixel segmentation. This objective function consists of two components: entropy rate of a random walk on a graph and a balancing term....
230
click to vote
CVPR
2011
IEEE
14 years 10 months ago
2011
IEEE
In the square jigsaw puzzle problem one is required to reconstruct the complete image from a set of non-overlapping, unordered, square puzzle parts. Here we propose a fully automa...
182
click to vote
CVPR
2011
IEEE
14 years 10 months ago
2011
IEEE
In this paper, we address invariant keypoint-based texture characterization and recognition. Viewing keypoint sets associated with visual textures as realizations of point process...
252
click to vote
CVPR
2011
IEEE
14 years 10 months ago
2011
IEEE
3D object detection and importance regression/ranking are at the core for semantically interpreting 3D medical images of computer aided diagnosis (CAD). In this paper, we propose ...
191
click to vote
CVPR
2011
IEEE
14 years 10 months ago
2011
IEEE
Motions can occur over both short and long time scales. We introduce motion denoising, which treats short-term changes as noise, long-term changes as signal, and rerenders a video...