Sciweavers

5393 search results - page 429 / 1079
» Spatial Computing with Labels
Sort
View
200
Voted
ICMCS
2007
IEEE
203views Multimedia» more  ICMCS 2007»
16 years 1 months ago
Efficient Video Object Segmentation by Graph-Cut
Segmentation of video objects from background is a popular computer vision problem and has many important applications. Most existing methods are either computationally expensive ...
Jinjun Wang, Wei Xu, Shenghuo Zhu, Yihong Gong
216
Voted
JMLR
2012
13 years 10 months ago
Structured Output Learning with High Order Loss Functions
Often when modeling structured domains, it is desirable to leverage information that is not naturally expressed as simply a label. Examples include knowledge about the evaluation ...
Daniel Tarlow, Richard S. Zemel
220
Voted
CVPR
2012
IEEE
13 years 10 months ago
Curvature-based regularization for surface approximation
We propose an energy-based framework for approximating surfaces from a cloud of point measurements corrupted by noise and outliers. Our energy assigns a tangent plane to each (noi...
Carl Olsson, Yuri Boykov
252
Voted
CVPR
2012
IEEE
13 years 10 months ago
Linear solution to scale invariant global figure ground separation
We propose a novel linear method for scale invariant figure ground separation in images and videos. Figure ground separation is treated as a superpixel labeling problem. We optim...
Hao Jiang
CVPR
2012
IEEE
13 years 10 months ago
Discrete-continuous optimization for multi-target tracking
The problem of multi-target tracking is comprised of two distinct, but tightly coupled challenges: (i) the naturally discrete problem of data association, i.e. assigning image obs...
Anton Andriyenko, Konrad Schindler, Stefan Roth