This paper describes a method of systematically generating visual sensing strategies based on knowledge of the assembly task to be performed. Since visual sensing is usually perfo...
We introduce the use of learned shaping rewards in reinforcement learning tasks, where an agent uses prior experience on a sequence of tasks to learn a portable predictor that est...
Keyword-based search returns its results without concern for the information needs of users at a particular time. In general, search queries are too short to represent what users ...
Abstract. We show that only languages in BPP have public-coin, blackbox zero-knowledge protocols that are secure under an unbounded (polynomial) number of parallel repetitions. Thi...
Rafael Pass, Wei-Lung Dustin Tseng, Douglas Wikstr...
This paper presents a novel approach for automatic person labelling in video sequences using costumes. The person recognition is carried out by extracting the costumes of all the p...