Sciweavers

CVPR
2001
IEEE
16 years 2 months ago
Structure and Motion from Uncalibrated Catadioptric Views
In this paper we present a new algorithm for structure from motion from point correspondences in images taken from uncalibrated catadioptric cameras with parabolic mirrors. We ass...
Christopher Geyer, Kostas Daniilidis
CVPR
2001
IEEE
16 years 2 months ago
Learning Similarity Measure for Natural Image Retrieval with Relevance Feedback
A new scheme of learning similarity measure is proposed for content-based image retrieval (CBIR). It learns a boundary that separates the images in the database into two parts. Im...
Guodong Guo, Anil K. Jain, Wei-Ying Ma, HongJiang ...
87
Voted
CVPR
2001
IEEE
16 years 2 months ago
Segmentation for Robust Tracking in the Presence of Severe Occlusion
Camillo Gentile, Octavia I. Camps, Mario Sznaier
71
Voted
CVPR
2001
IEEE
16 years 2 months ago
Virtual Sample Generation For Template-Based Shape Matching
Dariu Gavrila, Jan Giebel
CVPR
2001
IEEE
16 years 2 months ago
Convex and Non-convex Illuminant Constraints for Dichromatic Colour Constancy
The dichromatic reflectance model introduced by Shafer [16] predicts that the colour signals of most materials fall on a plane spanned by a vector due to the material and a vector...
Graham D. Finlayson, Gerald Schaefer
CVPR
2001
IEEE
16 years 2 months ago
An Adaptive Algorithm for Text Detection from Natural Scenes
We present a new adaptive algorithm for automatic detection of text from a natural scene. The initial cues of text regions are first detected from the captured image/video. An ada...
Jiang Gao, Jie Yang
127
Voted
CVPR
2001
IEEE
16 years 2 months ago
Real-time affine region tracking and coplanar grouping
We present a novel approach for tracking locally planar regions in an image sequence and their grouping into larger planar surfaces. The tracker recovers the affine transformation...
Vittorio Ferrari, Tinne Tuytelaars, Luc J. Van Goo...
96
Voted
CVPR
2001
IEEE
16 years 2 months ago
Learning Models for Object Recognition
We consider learning models for object recognition from examples. Our method is motivated by systems that use the Hausdorff distance as a shape comparison measure. Typically an ob...
Pedro F. Felzenszwalb
CVPR
2001
IEEE
16 years 2 months ago
Bayesian Learning of Sparse Classifiers
Bayesian approaches to supervised learning use priors on the classifier parameters. However, few priors aim at achieving "sparse" classifiers, where irrelevant/redundant...
Anil K. Jain, Mário A. T. Figueiredo
69
Voted
CVPR
2001
IEEE
16 years 2 months ago
Non parametric motion recognition using temporal multiscale Gibbs models
Ronan Fablet, Patrick Bouthemy