Sciweavers

ICML
2008
IEEE
14 years 8 months ago
Graph transduction via alternating minimization
Graph transduction methods label input data by learning a classification function that is regularized to exhibit smoothness along a graph over labeled and unlabeled samples. In pr...
Jun Wang, Tony Jebara, Shih-Fu Chang
ICPR
2004
IEEE
14 years 8 months ago
Reconstructing a Dynamic Surface from Video Sequences Using Graph Cuts in 4D Space-Time
This paper is concerned with the problem of dynamically reconstructing the 3D surface of an object undergoing non-rigid motion. The problem is cast as reconstructing a continuous ...
Narendra Ahuja, Ning Xu, Tianli Yu
ICIP
2003
IEEE
14 years 9 months ago
A voting scheme for estimating the synchrony of moving-camera videos
Recovery of dynamic scene properties from multiple videos usually requires the manipulation of synchronous (simultaneously captured) frames. This paper is concerned with the autom...
D. W. Pooley, Michael J. Brooks, Anton van den Hen...
ECCV
2006
Springer
14 years 9 months ago
PoseCut: Simultaneous Segmentation and 3D Pose Estimation of Humans Using Dynamic Graph-Cuts
Abstract. We present a novel algorithm for performing integrated segmentation and 3D pose estimation of a human body from multiple views. Unlike other related state of the art tech...
Matthieu Bray, Pushmeet Kohli, Philip H. S. Torr
ICCV
2001
IEEE
14 years 9 months ago
Image Segmentation with Minimum Mean Cut
We introduce a new graph-theoretic approach to image segmentation based on minimizing a novel class of `mean cut' cost functions. Minimizing these cost functions corresponds ...
Song Wang, Jeffrey Mark Siskind
CVPR
2008
IEEE
14 years 9 months ago
Demosaicing by smoothing along 1D features
Most digital cameras capture color pictures in the form of an image mosaic, recording only one color channel at each pixel position. Therefore, an interpolation algorithm needs to...
Boris Ajdin, Matthias B. Hullin, Christian Fuchs, ...
CVPR
2008
IEEE
14 years 9 months ago
Local minima free Parameterized Appearance Models
Parameterized Appearance Models (PAMs) (e.g. Eigentracking, Active Appearance Models, Morphable Models) are commonly used to model the appearance and shape variation of objects in...
Minh Hoai Nguyen, Fernando De la Torre
CVPR
2005
IEEE
14 years 9 months ago
The Modified pbM-Estimator Method and a Runtime Analysis Technique for the RANSAC Family
Robust regression techniques are used today in many computer vision algorithms. Chen and Meer recently presented a new robust regression technique named the projection based M-est...
Stas Rozenfeld, Ilan Shimshoni
CVPR
2005
IEEE
14 years 9 months ago
Visual Tracking in the Presence of Motion Blur
We consider the problem of visual tracking of regions of interest in a sequence of motion blurred images. Traditional methods couple tracking with deblurring in order to correctly...
Hailin Jin, Paolo Favaro, Roberto Cipolla