Sciweavers

CVPR
2005
IEEE
14 years 7 months ago
Camera Matchmoving in Unprepared, Unknown Environments
Manolis I. A. Lourakis, Antonis A. Argyros
CVPR
2005
IEEE
1158views Computer Vision» more  CVPR 2005»
14 years 7 months ago
Flattening Curved Documents in Images
Compared to scanned images, document pictures captured by camera can suffer from distortions due to perspective and page warping. It is necessary to restore a frontal planar view ...
Jian Liang, Daniel DeMenthon, David S. Doermann
CVPR
2005
IEEE
14 years 7 months ago
Nonparametric Subspace Analysis for Face Recognition
Linear discriminant analysis (LDA) is a popular face recognition technique. However, an inherent problem with this technique stems from the parametric nature of the scatter matrix...
Zhifeng Li, Wei Liu, Dahua Lin, Xiaoou Tang
CVPR
2005
IEEE
14 years 7 months ago
A Bayesian Hierarchical Model for Learning Natural Scene Categories
We propose a novel approach to learn and recognize natural scene categories. Unlike previous work [9, 17], it does not require experts to annotate the training set. We represent t...
Fei-Fei Li 0002, Pietro Perona, California Institu...
CVPR
2005
IEEE
14 years 7 months ago
Segmentation of Edge Preserving Gradient Vector Flow: An Approach Toward Automatically Initializing and Splitting of Snakes
Active contours or snakes have been extensively utilized in handling image segmentation and classification problems. In traditional active contour models, snake initialization is ...
Chunming Li, Jundong Liu, Martin D. Fox
CVPR
2005
IEEE
14 years 7 months ago
Randomized Trees for Real-Time Keypoint Recognition
In earlier work, we proposed treating wide baseline matching of feature points as a classification problem, in which each class corresponds to the set of all possible views of suc...
Vincent Lepetit, Pascal Lagger, Pascal Fua
CVPR
2005
IEEE
14 years 7 months ago
Unsupervised Learning of Object Features from Video Sequences
Marius Leordeanu, Robert T. Collins
CVPR
2005
IEEE
14 years 7 months ago
Pedestrian Detection in Crowded Scenes
In this paper, we address the problem of detecting pedestrians in crowded real-world scenes with severe overlaps. Our basic premise is that this problem is too difficult for any t...
Bastian Leibe, Edgar Seemann, Bernt Schiele
CVPR
2005
IEEE
14 years 7 months ago
Hybrid Joint-Separable Multibody Tracking
Statistical models for tracking different moving bodies must be able to reason about occlusions in order to be effective. Representing the joint statistics across different bodies...
Oswald Lanz, Roberto Manduchi
CVPR
2005
IEEE
14 years 7 months ago
Online Learning of Probabilistic Appearance Manifolds for Video-Based Recognition and Tracking
This paper presents an online learning algorithm to construct from video sequences an image-based representation that is useful for recognition and tracking. For a class of object...
Kuang-Chih Lee, David J. Kriegman