… device-end solution to protect mobile devices from malware threats in real-time efficiently
by leveraging customized deep … to detect malware directly on mobile devices as a pre-installed …

… 2,000 images per second on mobile devices. Software: Beyond these hardware advances,
there are also software platforms that seek to optimize deep learning on mobile devices (eg, […

… In this work, a deep-learning model for face recognition on mobile devices is presented
and evaluated in terms of accuracy, size and timing. The analysis was oriented to provide a …

… This diversity is relatively recent for mobile devices and we propose a layer-wise partitioning
approach followed by solving an optimization equation (see §VA) to decide how this …

… In the present paper, we propose a source camera identification (SCI) method for mobile
devices based on deep learning. Recently, convolutional neural networks (CNNs) have shown …

… However, reliably inferring user behavior and context from noisy and complex sensor data
collected under mobile device constraints remains an open problem, and a key bottleneck to …

… This paper has reviewed different lightweight deep network structures and approaches for
mobile devices where the computational resource is very limited. Inspired by different network …

… Based on MDLBench and the diverse mobile devices, we perform extensive experiments
and analyze the results. The theme of this measurement is to quantitatively understand the …

… Offloading (CBO) framework for deep learning video analytics on mobile devices with NPU.
To ad… loss problem in deep learning video analytics on NPU based mobile devices, we study …

… traditional machine learning methods; we also tested convolutional deep learning networks
… Deep learning architectures did not produce competitive results with the tested architecture. …