Real-Time Facial Affective Computing on Mobile Devices

doi:10.3390/s20030870

CORC > 自动化研究所 > 中国科学院自动化研究所 > 复杂系统管理与控制国家重点实验室 > 先进控制与自动化团队

	Real-Time Facial Affective Computing on Mobile Devices
	Guo, Yuanyuan 1; Xia, Yifan 4; Wang, Jing 1,2; Yu, Hui 4; Chen, Rung-Ching 3
刊名	SENSORS
	2020-02-01
卷号	20 期号:3 页码:15
关键词	facial affective computing convolutional neural networks deep learning mobile development
DOI	10.3390/s20030870
通讯作者	Wang, Jing(wangjing2014@ia.ac.cn) ; Yu, Hui(hui.yu@port.ac.uk)
英文摘要	Convolutional Neural Networks (CNNs) have become one of the state-of-the-art methods for various computer vision and pattern recognition tasks including facial affective computing. Although impressive results have been obtained in facial affective computing using CNNs, the computational complexity of CNNs has also increased significantly. This means high performance hardware is typically indispensable. Most existing CNNs are thus not generalizable enough for mobile devices, where the storage, memory and computational power are limited. In this paper, we focus on the design and implementation of CNNs on mobile devices for real-time facial affective computing tasks. We propose a light-weight CNN architecture which well balances the performance and computational complexity. The experimental results show that the proposed architecture achieves high performance while retaining the low computational complexity compared with state-of-the-art methods. We demonstrate the feasibility of a CNN architecture in terms of speed, memory and storage consumption for mobile devices by implementing a real-time facial affective computing application on an actual mobile device.
资助项目	National Natural Science Foundation of China[61533019] ; Open Project of The State Key Laboratory of Management and Control for Complex Systems: Reaserch on the Precise Diagnosis and Treatment of Gout based on Parallel Intelligence ; Engineering and Physical Sciences Research Council (EPSRC) through project 4D Facial Sensing and Modelling[EP/N025849/1]
WOS关键词	EXPRESSION RECOGNITION ; FACE ; REGIONS
WOS研究方向	Chemistry ; Engineering ; Instruments & Instrumentation
语种	英语
出版者	MDPI
WOS记录号	WOS:000517786200294
资助机构	National Natural Science Foundation of China ; Open Project of The State Key Laboratory of Management and Control for Complex Systems: Reaserch on the Precise Diagnosis and Treatment of Gout based on Parallel Intelligence ; Engineering and Physical Sciences Research Council (EPSRC) through project 4D Facial Sensing and Modelling
内容类型	期刊论文
源URL	[http://ir.ia.ac.cn/handle/173211/38737]
专题	自动化研究所_复杂系统管理与控制国家重点实验室_先进控制与自动化团队
通讯作者	Wang, Jing; Yu, Hui
作者单位	1.Qingdao Acad Intelligent Ind, Inst Smart Healthcare Syst, Qingdao 266109, Peoples R China 2.Chinese Acad Sci, Inst Automat, Beijing 100190, Peoples R China 3.Chaoyang Univ Technol, Dept Informat Management, Taichung 41349, Taiwan 4.Univ Portsmouth, Sch Creat Technol, Portsmouth PO1 2DJ, Hants, England
推荐引用方式 GB/T 7714	Guo, Yuanyuan,Xia, Yifan,Wang, Jing,et al. Real-Time Facial Affective Computing on Mobile Devices[J]. SENSORS,2020,20(3):15.
APA	Guo, Yuanyuan,Xia, Yifan,Wang, Jing,Yu, Hui,&Chen, Rung-Ching.(2020).Real-Time Facial Affective Computing on Mobile Devices.SENSORS,20(3),15.
MLA	Guo, Yuanyuan,et al."Real-Time Facial Affective Computing on Mobile Devices".SENSORS 20.3(2020):15.