The measurement of image disparity is a fundamental precursor to binocular depth estimation. Recently, Jenkin and Jepson (1988) and Sanger (1988) described promising methods based on the output phase behaviour of band-pass Gabor lters. Here we discuss further justiication for such techniques based on the stability of band-pass phase behaviour as a function of typical distortions that exist betw...

The importance of the appearance of consumer products is widely understood. This paper considers an evaluation of the appearance of a technology-oriented product, the residential solar panel, from the perspective of individuals. This study uses a quantitative approach, visual conjoint analysis, to determine preferences for product appearance of solar panels, and further explores how presenting ...

This paper presents an application of the Minimum Description-Length (MDL) principle of inductive learning to the surface reconstruction problem of computer vision. The application demonstrates that the M D L principle can be applied to practical problems while preserving its convergence properties. It also illustrates how at least one aspect of computer vision (i.e., surface reconstruction) ca...

We propose a distributed approach to train deep neural networks (DNNs), which has guaranteed convergence theoretically and great scalability empirically: close to 6 times faster on instance of ImageNet data set when run with 6 machines. The proposed scheme is close to optimally scalable in terms of number of machines, and guaranteed to converge to the same optima as the undistributed setting. T...

ICT-related change is usually studied from the point when a technological artifact has arrived in an organization. Applying an activity-theoretical lens, this paper explores the contradictions within a medium-sized organization’s central activity system, the manifestations of which motivated the decision to engage in a substantial change and shaped the object of the initiative. It illuminates t...

In this paper we propose a paradigm called the Interactive Visual Dialog (IVD) as a means of facilitating a system’s ability to recognize objects presented to it by a human. The presentation centers around a supermarket checkout scenario in which an operator presents an item to be tallied to a stationary television camera. An active vision approach is used to provide feedback to the operator in...

effects. Some are Orwellian in depicting the threat that government would control citizens through massive files recording what individuals say in e-mails. Other visions are politically utopian. For example, Stanford economist Lawrence Lau (2000) rejects Schumpeter’s (1952) view of major societal changes imposing both costs and benefits, claiming that the Internet makes possible “creation witho...

Video surveillance and machine vision systems are attracting growing academic and industrial interests. The market for digital CCTV systems is constantly growing because of terror attacks, crime, vandalism, and violence in public and also in business domains. The turnover for CCTV products for video surveillance is estimated to grow by 10% per year in Europe and by 13% per year worldwide, reach...