Sciweavers

2278 search results - page 26 / 456
» Multiple-Instance Active Learning
Sort
View
ICALT
2008
IEEE
14 years 4 months ago
Realistic Learning Activity is Not Enough
John M. Carroll, Marcela Borge, Lu Xiao, Craig H. ...
MIR
2004
ACM
125views Multimedia» more  MIR 2004»
14 years 3 months ago
Autonomous visual model building based on image crawling through internet search engines
In this paper, we propose an autonomous learning scheme to automatically build visual semantic concept models from the output data of Internet search engines without any manual la...
Xiaodan Song, Ching-Yung Lin, Ming-Ting Sun
ECCV
2010
Springer
14 years 3 months ago
Object, Scene and Actions: Combining Multiple Features for Human Action Recognition
Abstract. In many cases, human actions can be identified not only by the singular observation of the human body in motion, but also properties of the surrounding scene and the rel...
CVPR
2010
IEEE
14 years 2 months ago
On the design of robust classifiers for computer vision
The design of robust classifiers, which can contend with the noisy and outlier ridden datasets typical of computer vision, is studied. It is argued that such robustness requires l...
Hamed Masnadi-Shirazi, Nuno Vasconcelos, Vijay Mah...