—We present in this paper an integrated solution to rapidly recognizing dynamic objects in surveillance videos by exploring various contextual information. This solution consists...
Xiaobai Liu, Liang Lin, Shuicheng Yan, Hai Jin, We...
Object identification—the task of deciding that two observed objects are in fact one and the same object—is a fundamental requirement for any situated agent that reasons about...
The best of Kalman-filter-based frameworks reported in the literature for rigid object tracking work well only if the object motions are smooth (which allows for tight uncertainty ...
With the tremendous growth of World Wide Web (WWW), the door has been opened to a multitude of services and information for even the most casual of users. Today, many wireless and ...
We study the problem of object classification when training
and test classes are disjoint, i.e. no training examples of
the target classes are available. This setup has hardly be...
Christoph H. Lampert, Hannes Nickisch, Stefan Harm...