Sciweavers

CVPR
2008
IEEE
15 years 26 days ago
3D model matching with Viewpoint-Invariant Patches (VIP)
The robust alignment of images and scenes seen from widely different viewpoints is an important challenge for camera and scene reconstruction. This paper introduces a novel class ...
Changchang Wu, Brian Clipp, Xiaowei Li, Jan-Michae...
CVPR
2008
IEEE
15 years 26 days ago
3D occlusion recovery using few cameras
We present a practical framework for detecting and modeling 3D static occlusions for wide-baseline, multi-camera scenarios where the number of cameras is small. The framework cons...
Mark A. Keck, James W. Davis
CVPR
2008
IEEE
15 years 26 days ago
Image selection for improved Multi-View Stereo
The Middlebury Multi-View Stereo evaluation [18] clearly shows that the quality and speed of most multi-view stereo algorithms depends significantly on the number and selection of...
Alexander Hornung, Boyi Zeng, Leif Kobbelt
CVPR
2008
IEEE
15 years 26 days ago
Closing the loop in scene interpretation
Image understanding involves analyzing many different aspects of the scene. In this paper, we are concerned with how these tasks can be combined in a way that improves the perform...
Derek Hoiem, Alexei A. Efros, Martial Hebert
CVPR
2008
IEEE
15 years 26 days ago
Discriminative human action segmentation and recognition using semi-Markov model
Given an input video sequence of one person conducting a sequence of continuous actions, we consider the problem of jointly segmenting and recognizing actions. We propose a discri...
Qinfeng Shi, Li Wang, Li Cheng, Alexander J. Smola
CVPR
2008
IEEE
15 years 26 days ago
Boosting adaptive linear weak classifiers for online learning and tracking
Online boosting methods have recently been used successfully for tracking, background subtraction etc. Conventional online boosting algorithms emphasize on interchanging new weak ...
Toufiq Parag, Fatih Porikli, Ahmed M. Elgammal
CVPR
2008
IEEE
15 years 26 days ago
Physical simulation for probabilistic motion tracking
Human motion tracking is an important problem in computer vision. Most prior approaches have concentrated on efficient inference algorithms and prior motion models; however, few c...
Marek Vondrak, Leonid Sigal, Odest Chadwicke Jenki...
CVPR
2008
IEEE
15 years 26 days ago
Decomposition, discovery and detection of visual categories using topic models
We present a novel method for the discovery and detection of visual object categories based on decompositions using topic models. The approach is capable of learning a compact and...
Mario Fritz, Bernt Schiele
CVPR
2008
IEEE
15 years 26 days ago
Lost in quantization: Improving particular object retrieval in large scale image databases
The state of the art in visual object retrieval from large databases is achieved by systems that are inspired by text retrieval. A key component of these approaches is that local ...
James Philbin, Ondrej Chum, Michael Isard, Josef S...
CVPR
2008
IEEE
15 years 26 days ago
Shape prior segmentation of multiple objects with graph cuts
We present a new shape prior segmentation method using graph cuts capable of segmenting multiple objects. The shape prior energy is based on a shape distance popular with level se...
Nhat Vu, B. S. Manjunath