The application of semi-supervised learning algorithms to large scale vision problems suffers from the bad scaling behavior of most methods. Based on the Expectation Regularization...
Dynamic visual category learning calls for efficient adaptation as new training images become available or new categories are defined, existing training images or categories becom...
The traditional co-training algorithm, which needs a great number of unlabeled examples in advance and then trains classifiers by iterative learning approach, is not suitable for ...
This paper describes the start-up phase of the ALAN-K (Advanced LeArning Network in Kyoto) project, which is part of a major effort to create new learning environments for element...