Sciweavers

ECCV
2006
Springer
14 years 6 months ago
Inter-modality Face Recognition
Recently, the wide deployment of practical face recognition systems gives rise to the emergence of the inter-modality face recognition problem. In this problem, the face images in ...
Dahua Lin, Xiaoou Tang
ECCV
2006
Springer
14 years 6 months ago
Conditional Infomax Learning: An Integrated Framework for Feature Extraction and Fusion
The paper introduces a new framework for feature learning in classification motivated by information theory. We first systematically study the information structure and present a n...
Dahua Lin, Xiaoou Tang
ECCV
2006
Springer
14 years 6 months ago
Learning Nonlinear Manifolds from Time Series
Abstract. There has been growing interest in developing nonlinear dimensionality reduction algorithms for vision applications. Although progress has been made in recent years, conv...
Ruei-Sung Lin, Che-Bin Liu, Ming-Hsuan Yang, Naren...
ECCV
2006
Springer
14 years 6 months ago
Tracking Dynamic Near-Regular Texture Under Occlusion and Rapid Movements
We present a dynamic near-regular texture (NRT) tracking algorithm nested in a lattice-based Markov-Random-Field (MRF) model of a 3D spatiotemporal space. One basic observation use...
Wen-Chieh Lin, Yanxi Liu
ECCV
2006
Springer
14 years 6 months ago
An Integrated Model for Accurate Shape Alignment
In this paper, we propose a two-level integrated model for accurate face shape alignment. At the low level, the shape is split into a set of line segments which serve as the nodes ...
Lin Liang, Fang Wen, Xiaoou Tang, Ying-Qing Xu
ECCV
2006
Springer
14 years 6 months ago
Monocular Tracking of 3D Human Motion with a Coordinated Mixture of Factor Analyzers
Filtering based algorithms have become popular in tracking human body pose. Such algorithms can suffer the curse of dimensionality due to the high dimensionality of the pose state ...
Rui Li, Ming-Hsuan Yang, Stan Sclaroff, Tai-Peng T...
ECCV
2006
Springer
14 years 6 months ago
Learning to Combine Bottom-Up and Top-Down Segmentation
Bottom-up segmentation based only on low-level cues is a notoriously difficult problem. This difficulty has lead to recent top-down segmentation algorithms that are based on class-...
Anat Levin, Yair Weiss
ECCV
2006
Springer
14 years 6 months ago
Oriented Visibility for Multiview Reconstruction
Visibility estimation is arguably the most difficult problem in dense 3D reconstruction from multiple arbitrary views. In this paper, we propose a simple new approach to estimating...
Victor S. Lempitsky, Yuri Boykov, Denis V. Ivanov
ECCV
2006
Springer
14 years 6 months ago
Geodesics Between 3D Closed Curves Using Path-Straightening
In order to analyze shapes of continuous curves in R3 , we parameterize them by arc-length and represent them as curves on a unit two-sphere. We identify the subset denoting the cl...
Eric Klassen, Anuj Srivastava
ECCV
2006
Springer
14 years 6 months ago
Learning Discriminative Canonical Correlations for Object Recognition with Image Sets
Abstract. We address the problem of comparing sets of images for object recognition, where the sets may represent arbitrary variations in an object's appearance due to changin...
Tae-Kyun Kim, Josef Kittler, Roberto Cipolla