Sciweavers

ICCV
2007
IEEE
14 years 12 months ago
Supervised Learning of Image Restoration with Convolutional Networks
Convolutional networks have achieved a great deal of success in high-level vision problems such as object recognition. Here we show that they can also be used as a general method ...
Viren Jain, Joseph F. Murray, Fabian Roth, Sriniva...
ICCV
2007
IEEE
14 years 12 months ago
Spectral Regression for Efficient Regularized Subspace Learning
Subspace learning based face recognition methods have attracted considerable interests in recent years, including Principal Component Analysis (PCA), Linear Discriminant Analysis ...
Deng Cai, Xiaofei He, Jiawei Han
ICCV
2007
IEEE
14 years 12 months ago
Linear Predictors for Fast Simultaneous Modeling and Tracking
An approach for fast tracking of arbitrary image features with no prior model and no offline learning stage is presented. Fast tracking is achieved using banks of linear displacem...
Liam Ellis, Nicholas Dowson, Jiri Matas, Richard B...
ICCV
2007
IEEE
14 years 12 months ago
Penrose Pixels Super-Resolution in the Detector Layout Domain
We present a novel approach to reconstruction based superresolution that explicitly models the detector's pixel layout. Pixels in our model can vary in shape and size, and th...
Moshe Ben-Ezra, Zhouchen Lin, Bennett Wilburn
ICCV
2007
IEEE
14 years 12 months ago
Convex Optimization for Deformable Surface 3-D Tracking
3?D shape recovery of non-rigid surfaces from 3?D to 2?D correspondences is an under-constrained problem that requires prior knowledge of the possible deformations. State-of-the-a...
Mathieu Salzmann, Richard Hartley, Pascal Fua
ICCV
2007
IEEE
14 years 12 months ago
N3M: Natural 3D Markers for Real-Time Object Detection and Pose Estimation
In this paper, a new approach for object detection and pose estimation is introduced. The contribution consists in the conception of entities permitting stable detection and relia...
Stefan Hinterstoisser, Selim Benhimane, Nassir Nav...
ICCV
2007
IEEE
14 years 12 months ago
Locally Smooth Metric Learning with Application to Image Retrieval
In this paper, we propose a novel metric learning method based on regularized moving least squares. Unlike most previous metric learning methods which learn a global Mahalanobis d...
Dit-Yan Yeung, Hong Chang
ICCV
2007
IEEE
14 years 12 months ago
Bottom-up saliency is a discriminant process
Dashan Gao, Nuno Vasconcelos
ICCV
2007
IEEE
14 years 12 months ago
An Invariant Large Margin Nearest Neighbour Classifier
The k-nearest neighbour (kNN) rule is a simple and effective method for multi-way classification that is much used in Computer Vision. However, its performance depends heavily on ...
M. Pawan Kumar, Philip H. S. Torr, Andrew Zisserma...
ICCV
2007
IEEE
14 years 12 months ago
Articulated Shape Matching Using Locally Linear Embedding and Orthogonal Alignment
In this paper we propose a method for matching articulated shapes represented as large sets of 3D points by aligning the corresponding embedded clouds generated by locally linear ...
Diana Mateus, Fabio Cuzzolin, Radu Horaud, Edmond ...