In this paper we present a new optimization technique for the neighborhood computation in connected component labeling focused on images stored in raster scan order. This new tech...
Large-scale scientific computing applications frequently make use of closely-coupled distributed parallel components. The performance of such scientific applications is therefore ...
Lei Zhao, Stephen A. Jarvis, Daniel P. Spooner, Gr...
We present a new algorithm for eliminating excess parameters and improving network generalization after supervised training. The method, \Principal Components Pruning (PCP)",...
This paper discusses problems faced by planners of real-world online behavioural change interventions who must select behavioural change frameworks from a variety of competing the...
We consider the problem of recovering a target matrix that is a superposition of low-rank and sparse components, from a small set of linear measurements. This problem arises in co...