Sciweavers

1048 search results - page 202 / 210
» A Robust Method for Data Hiding in Color Images
Sort
View
JMLR
2010
119views more  JMLR 2010»
13 years 2 months ago
Factorized Orthogonal Latent Spaces
Existing approaches to multi-view learning are particularly effective when the views are either independent (i.e, multi-kernel approaches) or fully dependent (i.e., shared latent ...
Mathieu Salzmann, Carl Henrik Ek, Raquel Urtasun, ...
ICCV
2011
IEEE
12 years 7 months ago
Means in spaces of tree-like shapes
The mean is often the most important statistic of a dataset as it provides a single point that summarizes the entire set. While the mean is readily defined and computed in Euclid...
Aasa Feragen, Søren Hauberg, Mads Nielsen, Franç...
RAS
2008
139views more  RAS 2008»
13 years 7 months ago
Unsupervised identification of useful visual landmarks using multiple segmentations and top-down feedback
In this paper, we tackle the problem of unsupervised selection and posterior recognition of visual landmarks in images sequences acquired by an indoor mobile robot. This is a high...
Pablo Espinace, Daniel Langdon, Alvaro Soto
CVPR
2005
IEEE
14 years 9 months ago
A Statistical Field Model for Pedestrian Detection
This paper presents a new statistical model for detecting and tracking deformable objects such as pedestrians, where large shape variations induced by local shape deformation can ...
Ying Wu, Ting Yu, Gang Hua
ISCAS
2008
IEEE
179views Hardware» more  ISCAS 2008»
14 years 2 months ago
Super resolution of video using key frames
— In many video compression systems, the frames are down-sampled before transmission. Also, in many scalable systems, the residual after down- and up-sampling is encoded and tran...
Fernanda Brandi, Ricardo L. de Queiroz, Debargha M...