3018 search results - page 436 / 604 » Leveraging the |
268
click to vote
ICCV
2011
IEEE
14 years 6 months ago
2011
IEEE
The saliency of regions or objects in an image can be significantly boosted if they recur in multiple images. Leveraging this idea, cosegmentation jointly segments common regions...
164
click to vote
ICCV
2011
IEEE
14 years 6 months ago
2011
IEEE
In this paper, we present a novel, threshold-free robust estimation framework capable of efficiently fitting models to contaminated data. While RANSAC and its many variants have...
197
click to vote
ICCV
2011
IEEE
14 years 6 months ago
2011
IEEE
We address the problem of reconstructing 3D face models from large unstructured photo collections, e.g., obtained by Google image search or from personal photo collections in iPho...
184
click to vote
ICCV
2011
IEEE
14 years 6 months ago
2011
IEEE
Invariant representations in object recognition systems are generally obtained by pooling feature vectors over spatially local neighborhoods. But pooling is not local in the featu...
201
click to vote
ICCV
2011
IEEE
14 years 6 months ago
2011
IEEE
We address the problem of automatic 3D segmentation of a stack of electron microscopy sections of brain tissue. Unlike previous efforts, where the reconstruction is usually done o...