Sciweavers

CVPR
2008
IEEE
14 years 6 months ago
Modeling and generating complex motion blur for real-time tracking
This article addresses the problem of real-time visual tracking in presence of complex motion blur. Previous authors have observed that efficient tracking can be obtained by match...
Christopher Mei, Ian Reid
CVPR
2008
IEEE
14 years 6 months ago
What can missing correspondences tell us about 3D structure and motion?
Practically all existing approaches to structure and motion computation use only positive image correspondences to verify the camera pose hypotheses. Incorrect epipolar geometries...
Christopher Zach, Arnold Irschara, Horst Bischof
CVPR
2008
IEEE
14 years 6 months ago
Precise detailed detection of faces and facial features
Face detection has advanced dramatically over the past three decades. Algorithms can now quite reliably detect faces in clutter in or near real time. However, much still needs to ...
Liya Ding, Aleix M. Martínez
CVPR
2008
IEEE
14 years 6 months ago
Structure learning in random fields for heart motion abnormality detection
Coronary Heart Disease can be diagnosed by assessing the regional motion of the heart walls in ultrasound images of the left ventricle. Even for experts, ultrasound images are dif...
Glenn Fung, Kevin Murphy, Mark Schmidt, Róm...
CVPR
2008
IEEE
14 years 6 months ago
Regression from patch-kernel
In this paper, we present a patch-based regression framework for addressing the human age and head pose estimation problems. Firstly, each image is encoded as an ensemble of order...
Shuicheng Yan, Xi Zhou, Ming Liu, Mark Hasegawa-Jo...
CVPR
2008
IEEE
14 years 6 months ago
Optical flow estimation using Fourier Mellin Transform
In this paper, we propose a novel method of computing the optical flow using the Fourier Mellin Transform (FMT). Each image in a sequence is divided into a regular grid of patches...
Huy Tho Ho, Roland Göcke
CVPR
2008
IEEE
14 years 6 months ago
Recognition by association via learning per-exemplar distances
We pose the recognition problem as data association. In this setting, a novel object is explained solely in terms of a small set of exemplar objects to which it is visually simila...
Tomasz Malisiewicz, Alexei A. Efros
CVPR
2008
IEEE
14 years 6 months ago
Action recognition using exemplar-based embedding
In this paper, we address the problem of representing human actions using visual cues for the purpose of learning and recognition. Traditional approaches model actions as space-ti...
Daniel Weinland, Edmond Boyer
CVPR
2008
IEEE
14 years 6 months ago
A mobile vision system for robust multi-person tracking
We present a mobile vision system for multi-person tracking in busy environments. Specifically, the system integrates continuous visual odometry computation with tracking-bydetect...
Andreas Ess, Bastian Leibe, Konrad Schindler, Luc ...
CVPR
2008
IEEE
14 years 6 months ago
Action snippets: How many frames does human action recognition require?
Visual recognition of human actions in video clips has been an active field of research in recent years. However, most published methods either analyse an entire video and assign ...
Konrad Schindler, Luc J. Van Gool