Sciweavers

1989 search results - page 150 / 398
» Learning to Select Useful Landmarks
Sort
View
TASLP
2010
144views more  TASLP 2010»
15 years 1 months ago
Active Learning With Sampling by Uncertainty and Density for Data Annotations
To solve the knowledge bottleneck problem, active learning has been widely used for its ability to automatically select the most informative unlabeled examples for human annotation...
Jingbo Zhu, Huizhen Wang, Benjamin K. Tsou, Matthe...
CVPR
2012
IEEE
13 years 8 months ago
Beyond spatial pyramids: Receptive field learning for pooled image features
In this paper we examine the effect of receptive field designs on classification accuracy in the commonly adopted pipeline of image classification. While existing algorithms us...
Yangqing Jia, Chang Huang, Trevor Darrell
ICMB
2005
IEEE
76views Business» more  ICMB 2005»
15 years 12 months ago
ZoneIT: Using Short-Range Radios to Control Mobile Device Functionality
This paper describes a prototype system, ZoneIT, for selectively controlling functionality of mobile devices, e.g. ringing of cellular telephones. ZoneIT exploits the fact that ma...
Tim Moors, Marvyn Mei, Agus Salim
ESANN
2006
15 years 7 months ago
Using sampling methods to improve binding site predictions
Currently the best algorithms for transcription factor binding site prediction are severely limited in accuracy. In previous work we combine random selection under-sampling with th...
Yi Sun, Mark Robinson, Rod Adams, Rene te Boekhors...
CVPR
2004
IEEE
16 years 8 months ago
Local Smoothing for Manifold Learning
We propose methods for outlier handling and noise reduction using weighted local linear smoothing for a set of noisy points sampled from a nonlinear manifold. The methods can be u...
Jin Hyeong Park, Zhenyue Zhang, Hongyuan Zha, Rang...