We present a method for unsupervised discovery of abnormal occurrences of activities in multi-dimensional time series data. Unsupervised activity discovery approaches differ from ...
Multi-robot systems researchers have been investigating adaptive coordination methods for improving spatial coordination in teams. Such methods adapt the coordination method to th...
Abstract. Popular approaches for solving the shallow water equations (SWE) for climate modeling are explicit and semi-implicit methods, both have certain constraints on the time st...
This paper presents a novel system that employs an adaptive neural network for the no-reference assessment of perceived quality of JPEG/JPEG2000 coded images. The adaptive neural ...
Helmholtz stereopsis is a surface reconstruction method that exploits reciprocity for the recovery of 3D shape without an assumed BRDF model, and it has been shown to yield high q...