Zero-days attacks are one of the most dangerous threats against computer networks. These, by definition, are attacks never seen before. Thus, defense tools based on a database of ...
This paper presents a system that detects humans climbing fences. After extracting a binary blob contour, the system models the human with an extended star-skeleton representation...
We investigate the problem of acoustic modeling in which prior language-specific knowledge and transcribed data are unavailable. We present an unsupervised model that simultaneou...
We present a unified model of what was traditionally viewed as two separate tasks: data association and intensity tracking of multiple topics over time. In the data association pa...
We combine two complementary ideas for learning supertaggers from highly ambiguous lexicons: grammar-informed tag transitions and models minimized via integer programming. Each st...