Sciweavers

2337 search results - page 397 / 468
» Extracting Sequences from the Web
Sort
View
ECCV
2008
Springer
15 years 2 days ago
Simultaneous Visual Recognition of Manipulation Actions and Manipulated Objects
Abstract. The visual analysis of human manipulation actions is of interest for e.g. human-robot interaction applications where a robot learns how to perform a task by watching a hu...
Danica Kragic, David Martínez Mercado, Hedv...
ICIP
2005
IEEE
14 years 12 months ago
Visual tracking via efficient kernel discriminant subspace learning
Robustly tracking moving objects in video sequences is one of the key problems in computer vision. In this paper we introduce a computationally efficient nonlinear kernel learning...
Chunhua Shen, Anton van den Hengel, Michael J. Bro...
ICIP
2001
IEEE
14 years 11 months ago
Tracking of human activities using shape-encoded particle propagation
We present an approach to tracking human activities in a monocular video. We model the human body by decomposing it into torso and limbs and use simple 3D shapes to approximate th...
Hankyu Moon, Rama Chellappa, Azriel Rosenfeld
ICIP
1999
IEEE
14 years 11 months ago
Automatic Caption Localization in Compressed Video
?We present a method to automatically localize captions in JPEG compressed images and the I-frames of MPEG compressed videos. Caption text regions are segmented from background ima...
Yu Zhong, HongJiang Zhang, Anil K. Jain
ICIP
1994
IEEE
14 years 11 months ago
Discrete-Cosine/Sine-Transform Based Motion Estimation
A new motion estimation scheme, Discrete-Cosine/SineTransform Based Motion Estimation (DXT-ME) utilizing the principle of orthogonality of cosine and sine functions to estimate, i...
Ut-Va Koc, K. J. Ray Liu