In this paper, we presen t the design and use of a comprehensiv e framework, SimplePower, for evaluating the e ect of high-level algorithmic, architectural, and compilation tradeo...
Wu Ye, Narayanan Vijaykrishnan, Mahmut T. Kandemir...
This paper deals with estimation of dense optical flow
and ego-motion in a generalized imaging system by exploiting
probabilistic linear subspace constraints on the flow.
We dea...
Richard Roberts (Georgia Institute of Technology),...
Segmentation is a popular technique for discovering structure in time series data. We address the largely open problem of estimating the number of segments that can be reliably di...
This paper deals with the problem of error estimation in 3D reconstruction. It shows how interval analysis can be used in this way for 3D vision applications. The description of a...
Real-time data services can benefit data-intensive real-time applications, e.g., e-commerce, via timely transaction processing using fresh data, e.g., the current stock prices. T...