… Abstract—In this paper we present deep learning based techniques for human activity
classification that are designed to run in real time on mobile devices. Our methods minimize the …

… a mobile application for real-time image classifications because of low specifications, limited
hardware resources (memory and power) and the computing ability of mobile devices. To …

… Towards pushing deep learning on devices, we present MDLdroid, a novel decentralized …
DL to mobile devices, we present MDLdroid, a novel decentralized Mobile Deep Learning …

… For inference acceleration in mobile devices, we … mobile devices. We achieve 10x speedup
and 13.2x speedup on these two applications, respectively, when testing on mobile devices. …

… a mobile device with MobileNETV2 deep learning model for sleep-stage identification. In
the experiments, 25 all-night recordings were acquired, 17 of which were used for training, and …

… , an on-device deep learning framework of mining interaction … intermediate results out of the
device, preserving user privacy … limitation of mobile devices, deploying deep learning based …

… DNN inference on mobile devices aiming for both real-time performance and high accuracy.
The difficulty of achieving real-time DNN inference on mobile devices necessitates the …

… study for ondevice deep learning inference applied for a … different classroom wireless devices
through a mobile edge device (… deep learning algorithms to assist or improve the learning …

… In this work we present an end-to-end deep learning approach that bridges this gap by
translating ordinary photos into DSLRquality images. We propose learning the translation func…

… MAKING deep learning (DL for short in the rest of this paper) tasks run on mobile devices
has raised huge interests in both the academia [1], [2], [3], [4], [5], [6], [7], [8] and the industry [9], …