Deep learning is currently widely used in a variety of applications, including computer vision
and natural language processing. End devices, such as smartphones and Internet-of-Things …

Since the well-established navigation systems such as GPS are ineffective in indoor
environments, research into developing novel indoor positioning technologies has emerged …

The rapid emergence of head-mounted devices such as the Microsoft Holo-lens enables a
wide variety of continuous vision applications. Such applications often adopt deep-learning …

Abstract Machine vision faces bottlenecks in computing power consumption and large
amounts of data. Although opto-electronic hybrid neural networks can provide assistance …

We present DeepCache, a principled cache design for deep learning inference in
continuous mobile vision. DeepCache benefits model execution efficiency by exploiting …

Detecting and reacting to user behavior and ambient context are core elements of many
emerging mobile sensing and Internet-of-Things (IoT) applications. However, extracting …

Continuous mobile vision is limited by the inability to efficiently capture image frames and
process vision features. This is largely due to the energy burden of analog readout circuitry …

Visible Light Positioning (VLP) provides a promising means to achieve indoor localization
with sub-meter accuracy. We observe that the Visible Light Communication (VLC) methods …

Accurate tracking of objects in the real world is highly desirable in Augmented Reality (AR)
to aid proper placement of virtual objects in a user's view. Deep neural networks (DNNs) …

This paper presents the computing system design in our commercial autonomous vehicles,
and provides a detailed performance, energy, and cost analyses. Drawing from our …