Noisy probabilistic relational rules are a promising world model representation for several reasons. They are compact and generalize over world instantiations. They are usually in...
We present a scalable approach to recognizing and describing complex activities in video sequences. We are interested in long-term, sequential activities that may have several par...
Convolutional networks have achieved a great deal of success in high-level vision problems such as object recognition. Here we show that they can also be used as a general method ...
Viren Jain, Joseph F. Murray, Fabian Roth, Sriniva...
Path probing is essential to maintaining an efficient overlay network topology. However, the cost of a full-scale probing is as high as O(n2 ), which is prohibitive in large-scale...