Inspired by the human immune system, and in particular the negative selection algorithm, we propose a learning mechanism that enables the detection of abnormal activities. Three ty...
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...
Recognizing human action in non-instrumented video is a challenging task not only because of the variability produced by general scene factors like illumination, background, occlu...
Many mobile devices have touch-sensitive screens that people interact with using fingers or thumbs. However, such interaction is difficult because targets become occluded, and bec...
Koji Yatani, Kurt Partridge, Marshall W. Bern, Mar...
Feature selection is one of key issues related with data pre-processing of classification task in a data mining process. Although many efforts have been done to improve typical fea...