Sciweavers

511 search results - page 50 / 103
» Combined visual attention model for video sequences
Sort
View
RAS
2008
139views more  RAS 2008»
14 years 9 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
2007
IEEE
15 years 11 months ago
Latent-Dynamic Discriminative Models for Continuous Gesture Recognition
Many problems in vision involve the prediction of a class label for each frame in an unsegmented sequence. In this paper, we develop a discriminative framework for simultaneous se...
Louis-Philippe Morency, Ariadna Quattoni, Trevor D...
CVPR
2004
IEEE
15 years 11 months ago
Detection and Removal of Rain from Videos
The visual effects of rain are complex. Rain consists of spatially distributed drops falling at high velocities. Each drop refracts and reflects the environment, producing sharp i...
Kshitiz Garg, Shree K. Nayar
DCC
2002
IEEE
15 years 9 months ago
Diagnostically Lossless 3D Wavelet Compression for Digital Angiogram Video
A novel method for the compression of angiogram video sequences is presented. The approach is based on the idea that not all of an angiogram image will de diagnostically significa...
David Gibson, Sandra I. Woolley, Michael Spann
ICIP
2009
IEEE
15 years 10 months ago
Efficient Motion Compensated Frame Rate Upconversion Using Multiple Interpolations And Median Filtering
Methods for motion compensated frame rate upconversion exploit motion in order to generate interpolated frames that are temporally located between the available original frames of...