Sciweavers

28131 search results - page 5446 / 5627
» Images, Images, Billions of Images
Sort
View
CVPR
2008
IEEE
16 years 8 months ago
Principled fusion of high-level model and low-level cues for motion segmentation
High-level generative models provide elegant descriptions of videos and are commonly used as the inference framework in many unsupervised motion segmentation schemes. However, app...
Arasanathan Thayananthan, Masahiro Iwasaki, Robert...
CVPR
2008
IEEE
16 years 8 months ago
Enhanced biologically inspired model
It has been demonstrated by Serre et al. that the biologically inspired model (BIM) is effective for object recognition. It outperforms many state-of-the-art methods in challengin...
Yongzhen Huang, Kaiqi Huang, Liangsheng Wang, Dach...
CVPR
2008
IEEE
16 years 8 months ago
Information-theoretic active scene exploration
Studies support the need for high resolution imagery to identify persons in surveillance videos[13]. However, the use of telephoto lenses sacrifices a wider field of view and ther...
Eric Sommerlade, Ian Reid
CVPR
2008
IEEE
16 years 8 months ago
Learning Bayesian Networks with qualitative constraints
Graphical models such as Bayesian Networks (BNs) are being increasingly applied to various computer vision problems. One bottleneck in using BN is that learning the BN model param...
Yan Tong, Qiang Ji
CVPR
2008
IEEE
16 years 8 months ago
Constrained spectral clustering through affinity propagation
Pairwise constraints specify whether or not two samples should be in one cluster. Although it has been successful to incorporate them into traditional clustering methods, such as ...
Miguel Á. Carreira-Perpiñán, ...
« Prev « First page 5446 / 5627 Last » Next »