Many approaches to active learning involve training one classifier by periodically choosing new data points about which the classifier has the least confidence, but designing a co...
Existing object tracking algorithms generally use some form of local optimisation, assuming that an object's position and shape change smoothly over time. In some situations ...
We study the prevalent problem when a test distribution differs from the training distribution. We consider a setting where our training set consists of a small number of sample d...
Ruslan Salakhutdinov, Sham M. Kakade, Dean P. Fost...
In this paper we present the experiences of usage of Viras, a collaborative virtual environment for social awareness support in educational settings. Collaborative Virtual environ...
Information extraction from HTML pages has been conventionally treated as plain text documents extended with HTML tags. However, the growing maturity and correct usage of HTML/XHT...