157
click to vote
CVPR
2012
IEEE
13 years 7 months ago
2012
IEEE
In this work we present a unified view on Markov random fields and recently proposed continuous tight convex relaxations for multi-label assignment in the image plane. These rel...
177
click to vote
CVPR
2012
IEEE
13 years 7 months ago
2012
IEEE
Mode-seeking has been widely used as a powerful data analysis technique for clustering and filtering in a metric feature space. We introduce a versatile and efficient modeseekin...
182
click to vote
CVPR
2012
IEEE
13 years 7 months ago
2012
IEEE
We consider the problem of shape recovery for real world scenes, where a variety of global illumination (interreflections, subsurface scattering, etc.) and illumination defocus e...
167
click to vote
CVPR
2012
IEEE
13 years 7 months ago
2012
IEEE
In this work, we present intrinsic shape context (ISC) descriptors for 3D shapes. We generalize to surfaces the polar sampling of the image domain used in shape contexts: for this...
170
click to vote
CVPR
2012
IEEE
13 years 7 months ago
2012
IEEE
While Boltzmann Machines have been successful at unsupervised learning and density modeling of images and speech data, they can be very sensitive to noise in the data. In this pap...
162
click to vote
CVPR
2012
IEEE
13 years 7 months ago
2012
IEEE
Improving coding and spatial pooling for bag-of-words based feature design have gained a lot of attention in recent works addressing object recognition and scene classification. ...
206
click to vote
CVPR
2012
IEEE
13 years 7 months ago
2012
IEEE
We present a new spatio-temporal method for markerless motion capture. We reconstruct the pose and motion of a character from a multi-view video sequence without requiring the cam...
187
click to vote
CVPR
2012
IEEE
13 years 7 months ago
2012
IEEE
In this paper, we propose a method to select a discriminative set of image processing operations for Linear Discriminant Analysis (LDA) as an application of the use of generating ...
155
click to vote
CVPR
2012
IEEE
13 years 7 months ago
2012
IEEE
A widely used technique to recover a 3D surface from photographs is patch-based (multi-view) stereo reconstruction. Current methods are able to reproduce fine surface details, th...
163
click to vote
CVPR
2012
IEEE
13 years 7 months ago
2012
IEEE
We propose an approach for cross-view action recognition by way of ‘virtual views’ that connect the action descriptors extracted from one (source) view to those extracted from...