The internet of battlefield things (IoBT) is expected to be a major feature of future tactical
wireless networks. Multiple challenges arise from the expected scale, heterogeneity …

This paper presents AdaMask, a machine-centric video streaming framework for remote
deep neural network (DNN) inference. The objective is to optimize the accuracy of …

Deep neural networks (DNNs) have shown remarkable success in various machine-learning
(ML) tasks useful for many safety-critical, real-time embedded systems. The foremost design …

On-board computing capacity remains a key bottleneck in modern machine inference
pipelines that run on embedded hardware, such as aboard autonomous drones or cars. To …

As real-time object detection systems, such as autonomous cars, need to process input
images acquired from multiple cameras, they face significant challenges in delivering …

This paper explores criticality-based real-time scheduling of neural-network-based machine
inference pipelines in cyber-physical systems (CPS) to mitigate the effect of algorithmic …

This paper presents a real-time multi-view scheduling framework for DNN-based live video
analytics at the edge to minimize frame processing latency. The work is motivated by …

The ubiquity of smartphone cameras and IoT cameras, together with the recent boom of
deep learning and deep neural networks, proliferate various computer vision driven mobile …

This paper presents a self-cueing real-time frame-work for attention prioritization in AI-
enabled visual perception systems that minimizes a notion of state uncertainty. By attention …

This work focuses on the time-predictable execution of Deep Neural Networks (DNNs)
accelerated on FPGA System-on-Chips (SoCs). The modern DPU accelerator by **linx is …