In recent years, artificial intelligence and automotive industry have developed rapidly, and autonomous driving has gradually become the focus of the industry. In road networks, the problem of proximity detection refe...In recent years, artificial intelligence and automotive industry have developed rapidly, and autonomous driving has gradually become the focus of the industry. In road networks, the problem of proximity detection refers to detecting whether two moving objects are close to each other or not in real time. However, the battery life and computing capability of mobile devices are limited in the actual scene,which results in high latency and energy consumption. Therefore, it is a tough problem to determine the proximity relationship between mobile users with low latency and energy consumption. In this article, we aim at finding a tradeoff between latency and energy consumption. We formalize the computation offloading problem base on mobile edge computing(MEC)into a constrained multiobjective optimization problem(CMOP) and utilize NSGA-II to solve it. The simulation results demonstrate that NSGA-II can find the Pareto set, which reduces the latency and energy consumption effectively. In addition, a large number of solutions provided by the Pareto set give us more choices of the offloading decision according to the actual situation.展开更多
While much progress has been made in capturing high-quality facial performances using motion capture markers and shape-from-shading,high-end systems typically also rely on rotoscope curves hand-drawn on the image.Thes...While much progress has been made in capturing high-quality facial performances using motion capture markers and shape-from-shading,high-end systems typically also rely on rotoscope curves hand-drawn on the image.These curves are subjective and difficult to draw consistently;moreover,ad-hoc procedural methods are required for generating matching rotoscope curves on synthetic renders embedded in the optimization used to determine three-dimensional(3D)facial pose and expression.We propose an alternative approach whereby these curves and other keypoints are detected automatically on both the image and the synthetic renders using trained neural networks,eliminating artist subjectivity,and the ad-hoc procedures meant to mimic it.More generally,we propose using machine learning networks to implicitly define deep energies which when minimized using classical optimization techniques lead to 3D facial pose and expression estimation.展开更多
基金supported in part by the National Natural Science Foundation of China (Grant No. 61901052)in part by the 111 project (Grant No. B17007)in part by the Director Funds of Beijing Key Laboratory of Network System Architecture and Convergence (Grant No. 2017BKL-NSACZJ-02)。
文摘In recent years, artificial intelligence and automotive industry have developed rapidly, and autonomous driving has gradually become the focus of the industry. In road networks, the problem of proximity detection refers to detecting whether two moving objects are close to each other or not in real time. However, the battery life and computing capability of mobile devices are limited in the actual scene,which results in high latency and energy consumption. Therefore, it is a tough problem to determine the proximity relationship between mobile users with low latency and energy consumption. In this article, we aim at finding a tradeoff between latency and energy consumption. We formalize the computation offloading problem base on mobile edge computing(MEC)into a constrained multiobjective optimization problem(CMOP) and utilize NSGA-II to solve it. The simulation results demonstrate that NSGA-II can find the Pareto set, which reduces the latency and energy consumption effectively. In addition, a large number of solutions provided by the Pareto set give us more choices of the offloading decision according to the actual situation.
基金supported in part by the Office of Naval Research(ONR)N00014-13-1-0346,ONR N00014-17-1-2174,ARL AHPCRC W911NF-07-0027generous gifts from Amazon and Toyota+1 种基金supported in part by the VMWare Fellowship in Honor of Ole Agesensupported in part by the Stanford School of Engineering Fellowship.
文摘While much progress has been made in capturing high-quality facial performances using motion capture markers and shape-from-shading,high-end systems typically also rely on rotoscope curves hand-drawn on the image.These curves are subjective and difficult to draw consistently;moreover,ad-hoc procedural methods are required for generating matching rotoscope curves on synthetic renders embedded in the optimization used to determine three-dimensional(3D)facial pose and expression.We propose an alternative approach whereby these curves and other keypoints are detected automatically on both the image and the synthetic renders using trained neural networks,eliminating artist subjectivity,and the ad-hoc procedures meant to mimic it.More generally,we propose using machine learning networks to implicitly define deep energies which when minimized using classical optimization techniques lead to 3D facial pose and expression estimation.