Sciweavers

10285 search results - page 1614 / 2057
» Composing Feature Models
Sort
View
ICCV
2009
IEEE
16 years 12 months ago
Automatic annotation of human actions in video
This paper addresses the problem of automatic temporal annotation of realistic human actions in video using mini- mal manual supervision. To this end we consider two asso- ciate...
Olivier Duchenne, Ivan Laptev, Josef Sivic, Franci...
CVPR
1999
IEEE
16 years 9 months ago
Independent Motion: The Importance of History
We consider a problem central in aerial visual surveillance applications { detection and tracking of small, independently moving objects in long and noisy video sequences. We dire...
Robert Pless, Tomás Brodský, Yiannis...
CVPR
2004
IEEE
16 years 9 months ago
Hidden Semantic Concept Discovery in Region Based Image Retrieval
This paper addresses Content Based Image Retrieval (CBIR), focusing on developing a hidden semantic concept discovery methodology to address effective semanticsintensive image ret...
Ruofei Zhang, Zhongfei (Mark) Zhang
CVPR
2005
IEEE
16 years 9 months ago
Automatic 3D to 2D Registration for the Photorealistic Rendering of Urban Scenes
This paper presents a novel and efficient algorithm for the 3D range to 2D image registration problem in urban scene settings. Our input is a set of unregistered 3D range scans an...
Lingyun Liu, Ioannis Stamos
CVPR
2005
IEEE
16 years 9 months ago
Strike a Pose: Tracking People by Finding Stylized Poses
We develop an algorithm for finding and kinematically tracking multiple people in long sequences. Our basic assumption is that people tend to take on certain canonical poses, even...
Deva Ramanan, David A. Forsyth, Andrew Zisserman
« Prev « First page 1614 / 2057 Last » Next »