Sciweavers

633 search results - page 81 / 127
» Modeling Deformable Surfaces from Single Videos
Sort
View
ICIP
2010
IEEE
13 years 5 months ago
Face-TLD: Tracking-Learning-Detection applied to faces
A novel system for long-term tracking of a human face in unconstrained videos is built on Tracking-Learning-Detection (TLD) approach. The system extends TLD with the concept of a ...
Zdenek Kalal, Krystian Mikolajczyk, Jiri Matas
SCIA
2007
Springer
162views Image Analysis» more  SCIA 2007»
14 years 1 months ago
A Robust Approach for 3D Cars Reconstruction
Computing high quality 3D models from multi-view stereo reconstruction is an active topic as can be seen in a recent review [15]. Most approaches make the strong assumption that th...
Adrien Auclair, Laurent D. Cohen, Nicole Vincent
ICMCS
2009
IEEE
231views Multimedia» more  ICMCS 2009»
13 years 5 months ago
Dynamic face appearance modeling and sight direction estimation based on local region tracking and scale-space topo-represention
Dynamic modeling of facial appearances and sight directions are demanded for HCI and multimedia applications. Traditional approaches for face tracking and eye tracking from 2D vid...
Shaun J. Canavan, Lijun Yin
CVPR
2009
IEEE
14 years 1 months ago
Recovering Specular Surfaces Using Curved Line Images
We present a new shape-from-distortion framework for recovering specular (reflective/refractive) surfaces. While most existing approaches rely on accurate correspondences between 2...
Yuanyuan Ding, Jingyi Yu, Peter Sturm
ECCV
2006
Springer
13 years 11 months ago
View-Invariant Modeling and Recognition of Human Actions Using Grammars
In this paper, we represent human actions as short sequences of atomic body poses. The knowledge of body pose is stored only implicitly as a set of silhouettes seen from multiple ...
Abhijit S. Ogale, Alap Karapurkar, Yiannis Aloimon...