We investigate the problem of learning document classifiers in a multilingual setting, from collections where labels are only partially available. We address this problem in the ...
Design traceability has been widely recognized as being an integral aspect of software development. In the past years this fact has been amplified due to the increased use of lega...
We present an efficient method for learning part-based object class models from unsegmented images represented as sets of salient features. A model includes parts' appearance...
On script-generated web sites, many documents share common HTML tree structure, allowing wrappers to effectively extract information of interest. Of course, the scripts and thus ...
In this paper we analyze and try to predict the gaze behavior of users navigating in virtual environments. We focus on first-person navigation in virtual environments which invol...