Sciweavers

CVPR
2010
IEEE
1135views Computer Vision» more  CVPR 2010»
14 years 7 months ago
Towards Weakly Supervised Semantic Segmentation by Means of Multiple Instance and Multitask Learning.
We address the task of learning a semantic segmentation from weakly supervised data. Our aim is to devise a system that predicts an object label for each pixel by making use of on...
Alexander Vezhnevets, Joachim Buhmann
CVPR
2010
IEEE
14 years 7 months ago
Scene Classification and Detection with a Quasi-exhausitve Dataset
Scene categorization is a fundamental problem in computer vision. However, scene understanding research has been constrained by the limited scope of currently-used databases which...
Jianxiong Xiao, James Hays, Krista Ehinger, Antoni...
CVPR
2010
IEEE
14 years 7 months ago
Exploiting Simple Hierarchies for Unsupervised Human Behavior Analysis
We propose a data-driven, hierarchical approach for the analysis of human actions in visual scenes. In particular, we focus on the task of in-house assisted living. In such scenar...
Fabian Nater, Helmut Grabner, Luc Van Gool
CVPR
2010
IEEE
14 years 7 months ago
Convex Shape Decomposition
In this paper, we propose a new shape decomposition method, called convex shape decomposition. We formalize the convex decomposition problem as an integer linear programming probl...
Liu Hairong, Longin Jan Latecki, Liu Wenyu
CVPR
2010
IEEE
14 years 7 months ago
Non-Rigid Structure from Locally-Rigid Motion
We introduce locally-rigid motion, a general framework for solving the M-point, N-view structure-from-motion problem for unknown bodies deforming under orthography. The key idea i...
Jonathan Taylor, Allan Jepson, Kyros Kutulakos
CVPR
2010
IEEE
14 years 7 months ago
Manifold Blurring Mean Shift Algorithms
We propose a new family of algorithms for denoising data assumed to lie on a low-dimensional manifold. The algorithms are based on the blurring mean-shift update, which moves each...
Weiran Wang, Miguel Carreira-perpinan
CVPR
2010
IEEE
14 years 7 months ago
Estimating Camera Pose from a Single Urban Ground-View Omnidirectional Image and a 2D Building Outline Map
A framework is presented for estimating the pose of a camera based on images extracted from a single omnidirectional image of an urban scene, given a 2D map with building outlines...
Tat-Jen Cham, Ciptadi Arridhana, Wei-Chian Tan, Mi...
CVPR
2010
IEEE
14 years 7 months ago
Detecting and Sketching the Common
Given very few images containing a common object of interest under severe variations in appearance, we detect the common object and provide a compact visual representation of that...
Shai Bagon, Or Brostovski, Meirav Galun, Michal Ir...
CVPR
2010
IEEE
14 years 7 months ago
A Novel Riemannian Framework for Shape Analysis of 3D Objects
In this paper we introduce a novel Riemannian framework for shape analysis of parameterized surfaces. We derive a distance function between any two surfaces that is invariant to r...
Sebastian Kurtek, Eric Klassen, Anuj Srivastava, Z...
CVPR
2010
IEEE
1256views Computer Vision» more  CVPR 2010»
14 years 7 months ago
Multisensor-Fusion for 3D Full-Body Human Motion Capture
DATA available at http://www.tnt.uni-hannover.de/project/MPI08_Database/! In this work, we present an approach to fuse video with orientation data obtained from extended iner...
Gerard Pons-Moll, Andreas Baak, Thomas Helten, Mei...