111 search results - page 21 / 23 » Multi-class image segmentation using conditional random fiel... |
PAMI
2008
14 years 9 months ago
2008
Image denoising algorithms often assume an additive white Gaussian noise (AWGN) process that is independent of the actual RGB values. Such approaches cannot effectively remove colo...
WWW
2008
ACM
15 years 10 months ago
2008
ACM
Geographic information has spawned many novel Web applications where global positioning system (GPS) plays important roles in bridging the applications and end users. Learning kno...
NIPS
2008
14 years 11 months ago
2008
We present a discriminative part-based approach for human action recognition from video sequences using motion features. Our model is based on the recently proposed hidden conditi...
ACCV
2010
Springer
14 years 4 months ago
2010
Springer
Dynamic textures (DT) are videos of non-rigid dynamical objects, such as fire and waves, which constantly change their shape and appearance over time. Most of the prior work on DT ...
CVPR
2008
IEEE
15 years 11 months ago
2008
IEEE
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...