Tracking-by-detection is increasingly popular in order to tackle the visual tracking problem. Existing adaptive methods suffer from the drifting problem, since they rely on selfup...
Jakob Santner, Christian Leistner, Amir Saffari, T...
Multiple instance (MI) learning is a recent learning paradigm that is more flexible than standard supervised learning algorithms in the handling of label ambiguity. It has been u...
In order to understand the evolution of online identities, we measured the correlation between past and current representations of self on the MySpace social network. We applied s...
The amount of physical variation among electronic components on a die is increasing rapidly. There is a need for a better understanding of variations in transient fault susceptibil...
The Virtual Math Teams (VMT) project investigates the innovative use of online collaborative environments to support effective mathematical problem-solving by small groups of lear...