192
click to vote
PAMI
2012
13 years 7 months ago
2012
—We propose a probabilistic formulation of joint silhouette extraction and 3D reconstruction given a series of calibrated 2D images. Instead of segmenting each image separately i...
169
click to vote
PAMI
2012
13 years 7 months ago
2012
—We introduce a simple image descriptor referred to as the image signature. We show, within the theoretical framework of sparse signal mixing, that this quantity spatially approx...
187
click to vote
PAMI
2012
13 years 7 months ago
2012
—Detecting objects in cluttered scenes and estimating articulated human body parts from 2D images are two challenging problems in computer vision. The difficulty is particularly...
154
click to vote
PAMI
2012
13 years 7 months ago
2012
— Most recent approaches to monocular non-rigid 3D shape recovery rely on exploiting point correspondences and work best when the whole surface is well-textured. The alternative ...
184
click to vote
PAMI
2012
13 years 7 months ago
2012
A novel system for long-term tracking of a human face in unconstrained videos is built on Tracking-Learning-Detection (TLD) approach. The system extends TLD with the concept of a ...
168
click to vote
PAMI
2012
13 years 7 months ago
2012
—There has been a growing interest in exploiting contextual information in addition to local features to detect and localize multiple object categories in an image. A context mod...
167
click to vote
PAMI
2012
13 years 7 months ago
2012
—It has been shown that the Universum data, which do not belong to either class of the classification problem of interest, may contain useful prior domain knowledge for training...
165
click to vote
PAMI
2012
13 years 7 months ago
2012
— A novel framework to context modeling, based on the probability of co-occurrence of objects and scenes is proposed. The modeling is quite simple, and builds upon the availabili...