Sciweavers

113
Voted
CVPR
2007
IEEE
16 years 2 months ago
3D Pose Estimation Based on Multiple Monocular Cues
In this study we propose an integrated approach to the problem of 3D pose estimation. The main difference to the majority of known methods is the usage of complementary image info...
Björn Barrois, Christian Wöhler
85
Voted
CVPR
2007
IEEE
16 years 2 months ago
Using Stereo Matching for 2-D Face Recognition Across Pose
We propose using stereo matching for 2-D face recognition across pose. We match one 2-D query image to one 2-D gallery image without performing 3-D reconstruction. Then the cost o...
Carlos D. Castillo, David W. Jacobs
CVPR
2007
IEEE
16 years 2 months ago
Euclidean Path Modeling from Ground and Aerial Views
Weaddress the issue ofEuclideanpath mu& ling ina single camerafor activity monitoring in a multi-camera video surveillance system m e paperpmposes a novel linear solufwnro aut...
Imran N. Junejo, Hassan Foroosh
85
Voted
CVPR
2007
IEEE
16 years 2 months ago
Multi-Modal Biometrics Involving the Human Ear
Due to its semi-rigid shape and robustness against change over time, the ear has become an increasingly popular biometric feature. It has been shown that combining individual biom...
Christopher Middendorff, Kevin W. Bowyer, Ping Yan
90
Voted
CVPR
2007
IEEE
16 years 2 months ago
Kinematics from Lines in a Single Rolling Shutter Image
Recent work shows that recovering pose and velocity from a single view of a moving rigid object is possible with a rolling shutter camera, based on feature point correspondences. ...
Omar Ait-Aider, Adrien Bartoli, Nicolas Andreff
CVPR
2007
IEEE
16 years 2 months ago
Soft Edge Smoothness Prior for Alpha Channel Super Resolution
Effective image prior is necessary for image super resolution, due to its severely under-determined nature. Although the edge smoothness prior can be effective, it is generally di...
Shengyang Dai, Mei Han, Wei Xu, Ying Wu, Yihong Go...
99
Voted
CVPR
2007
IEEE
16 years 2 months ago
Learning Visual Similarity Measures for Comparing Never Seen Objects
In this paper we propose and evaluate an algorithm that learns a similarity measure for comparing never seen objects. The measure is learned from pairs of training images labeled ...
Eric Nowak, Frédéric Jurie
98
Voted
CVPR
2007
IEEE
16 years 2 months ago
Imaging the Finger Force Direction
This paper presents a method of imaging the coloration pattern in the fingernail and surrounding skin to infer fingertip force direction during planar contact. Nail images from 7 ...
Yu Sun, John M. Hollerbach, Stephen A. Mascaro
98
Voted
CVPR
2007
IEEE
16 years 2 months ago
OPTIMOL: automatic Online Picture collecTion via Incremental MOdel Learning
A well-built dataset is a necessary starting point for advanced computer vision research. It plays a crucial role in evaluation and provides a continuous challenge to stateof-the-...
Li-Jia Li, Gang Wang, Fei-Fei Li 0002
111
Voted
CVPR
2007
IEEE
16 years 2 months ago
Towards Scalable Representations of Object Categories: Learning a Hierarchy of Parts
This paper proposes a novel approach to constructing a hierarchical representation of visual input that aims to enable recognition and detection of a large number of object catego...
Sanja Fidler, Ales Leonardis