CARIn: Constraint-Aware and Responsive Inference on Heterogeneous Devices for Single-and Multi-DNN Workloads
The relentless expansion of deep learning (DL) applications in recent years has prompted a
pivotal shift towards on-device execution, driven by the urgent need for real-time processing …
pivotal shift towards on-device execution, driven by the urgent need for real-time processing …
HeteroPush: Communication-Efficient Video Analytics by Scheduling Heterogeneous Filters
YN Zhang, L Zhang, M Yuan… - 2023 9th International …, 2023 - ieeexplore.ieee.org
A large number of cameras have been deployed in different real world scenarios. Due to the
limited computing power and bandwidth, a combined device-cloud framework is typically …
limited computing power and bandwidth, a combined device-cloud framework is typically …