Traditional non-parametric statistical learning techniques are often computationally attractive, but lack the same generalization and model selection abilities as state-of-the-art...
The objective of active recognition is to iteratively collect the next "best" measurements (e.g., camera angles or viewpoints), to maximally reduce ambiguities in recogn...
— The paper presents IRIS, an Integrated Routing and Interest dissemination System for wireless sensor networks. The proposed protocols are designed to work under very low duty c...
This paper introduces the notion of temporally constrained ranked retrieval, which, given a query and a time constraint, produces the best possible ranked list within the specifi...
Recent work on background subtraction has shown developments on two major fronts. In one, there has been increasing sophistication of probabilistic models, from mixtures of Gaussi...
Manjunath Narayana, Allen R. Hanson, Erik G. Learn...