212
click to vote
CVPR
2012
IEEE
13 years 7 months ago
2012
IEEE
We address the problem of weakly supervised semantic segmentation. The training images are labeled only by the classes they contain, not by their location in the image. On test im...
173
click to vote
CVPR
2012
IEEE
13 years 7 months ago
2012
IEEE
Multi-atlas segmentation has been widely applied in medical image analysis. With deformable registration, this technique realizes label transfer from pre-labeled atlases to unknow...
151
click to vote
CVPR
2012
IEEE
13 years 7 months ago
2012
IEEE
We present a novel system that is capable of generating live dense volumetric reconstructions based on input from a micro aerial vehicle. The distributed reconstruction pipeline i...
158
click to vote
CVPR
2012
IEEE
13 years 7 months ago
2012
IEEE
We are interested in a general alpha matting approach for the simultaneous extraction of multiple image layers; each layer may have disjoint segments for material matting not limi...
182
click to vote
CVPR
2012
IEEE
13 years 7 months ago
2012
IEEE
In this paper we introduce a novel image descriptor enabling accurate object categorization even with linear models. Akin to the popular attribute descriptors, our feature vector ...
186
click to vote
CVPR
2012
IEEE
13 years 7 months ago
2012
IEEE
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...
158
click to vote
CVPR
2012
IEEE
13 years 7 months ago
2012
IEEE
Image based relighting techniques are a popular choice for generating photo-realistic images of objects under any lighting condition. A typical process for creating such a model i...
154
click to vote
CVPR
2012
IEEE
13 years 7 months ago
2012
IEEE
This paper proposes a simple “prior-free” method for solving non-rigid structure-from-motion factorization problems. Other than using the basic low-rank condition, our method ...
173
click to vote
CVPR
2012
IEEE
13 years 7 months ago
2012
IEEE
We describe a mid-level approach for action recognition. From an input video, we extract salient spatio-temporal structures by forming clusters of trajectories that serve as candi...