This research is based on the realization that the desktop computing paradigm is not appropriate for television, because it is adapted to fundamentally different user aspirations ...
We present an algorithm that learns invariant features from real data in an entirely unsupervised fashion. The principal benefit of our method is that it can be applied without hu...
Given a set of algorithms, which one(s) should you apply to, i) compute optical flow, or ii) perform feature matching? Would looking at the sequence in question help you decide? I...
A novel method for crowd flow modeling and anomaly detection is proposed for both coherent and incoherent scenes. The novelty is revealed in three aspects. First, it is a unique ut...
State-of-the-art image retrieval systems achieve scalability by using bag-of-words representation and textual retrieval methods, but their performance degrades quickly in the face...