In realistic settings the prevalence of a class may change after a classifier is induced and this will degrade the performance of the classifier. Further complicating this scenari...
Temporal consistency is ubiquitous in video data, where temporally adjacent video shots usually share similar visual and semantic content. This paper presents a thorough study of ...
We consider classification of email messages as to whether or not they contain certain “email acts”, such as a request or a commitment. We show that exploiting the sequential ...
To help consumers dealing with their growing amount of home video, we have developed the Edit While Watching (EWW) system. It is designed to automatically create an edited version...
This paper describes an “experiential” learning approach to teaching a foundational course on Computer Networking. In additional to the traditional laboratory sessions and ana...