Higher order energy functions have the ability to encode
high level structural dependencies between pixels, which
have been shown to be extremely powerful for image labeling
pro...
Carsten Rother (Microsoft Research Cambridge), Pus...
The computer aided diagnosis (CAD) problems of detecting
potentially diseased structures from medical images are
typically distinguished by the following challenging characterist...
We introduce a text-based image feature and demon-
strate that it consistently improves performance on hard
object classification problems. The feature is built using
an auxilia...
This paper studies a framework for matching an unknown
number of corresponding structures in two images
(shapes), motivated by detecting objects in cluttered background
and lear...
Most state-of-the-art nonrigid shape recovery methods
usually use explicit deformable mesh models to regularize
surface deformation and constrain the search space. These
triangu...
In this paper, we focus on the problem of detecting/
matching a query object in a given image. We propose a
new algorithm, shape band, which models an object within
a bandwidth ...
Xiang Bai (Huazhong University of Science and Tec...
Interactive image segmentation traditionally involves the
use of algorithms such as Graph Cuts or Random Walker.
Common concerns with using Graph Cuts are metrication
artifacts ...
We present an algorithm for clustering sets of detected
interest points into groups that correspond to visually dis-
tinct structure. Through the use of a suitable colour and tex...
We propose a novel probabilistic framework for learning
visual models of 3D object categories by combining appearance
information and geometric constraints. Objects are
represen...
This paper proposes a novel descriptor, granularitytunable
gradients partition (GGP), for human detection.
The concept granularity is used to define the spatial and angular
unce...
Yazhou Liu (Harbin Institute of Technology), Shigu...