We consider the problem of developing an automated visual solution for detecting human activities within industrial environments. This has been performed using an overhead view. Th...
Banafshe Arbab-Zavar, Imed Bouchrika, John N. Cart...
Machine learning with few training examples always leads to over-fitting problems, whereas human individuals are often able to recognize difficult object categories from only one ...
We present a novel mixed-state dynamic Bayesian network (DBN) framework for modeling and classifying timeseries data such as object trajectories. A hidden Markov model (HMM) of di...
Vladimir Pavlovic, Brendan J. Frey, Thomas S. Huan...
In this paper we explore the idea that the code that constitutes a program actually forms a higher-level, program specific language. The symbols of the language are the abstracti...
Recent advances in information retrieval over hyperlinked corpora have convincinglydemonstratedthat links carry less noisy information than text. We investigate the feasibility of...