Sciweavers

821 search results - page 130 / 165
» Labeling images with a computer game
Sort
View
CVPR
2008
IEEE
14 years 10 months ago
Unsupervised feature selection via distributed coding for multi-view object recognition
Object recognition accuracy can be improved when information from multiple views is integrated, but information in each view can often be highly redundant. We consider the problem...
Chris Mario Christoudias, Raquel Urtasun, Trevor D...
ICCV
2003
IEEE
14 years 10 months ago
Gaze Manipulation for One-to-one Teleconferencing
A new algorithm is proposed for novel view generation in one-toone teleconferencing applications. Given the video streams acquired by two cameras placed on either side of a comput...
Antonio Criminisi, Jamie Shotton, Andrew Blake, Ph...
MM
2004
ACM
229views Multimedia» more  MM 2004»
14 years 1 months ago
Generating 3D views of facial expressions from frontal face video based on topographic analysis
In this paper, we report our newly developed 3D face modeling system with arbitrary expressions in a high level of detail using the topographic analysis and mesh instantiation pro...
Lijun Yin, Kenny Weiss
ECCV
2010
Springer
14 years 1 months ago
Detecting ground shadows in outdoor consumer photographs
Detecting shadows from images can significantly improve the performance of several vision tasks such as object detection and tracking. Recent approaches have mainly used illuminat...
CVPR
2007
IEEE
14 years 10 months ago
Optimizing Binary MRFs via Extended Roof Duality
Many computer vision applications rely on the efficient optimization of challenging, so-called non-submodular, binary pairwise MRFs. A promising graph cut based approach for optim...
Carsten Rother, Vladimir Kolmogorov, Victor S. Lem...