Human action recognition using a time-delayed photonic reservoir computing  

作　　者：Chao KAI Pu LI Yi YANG Bingjie WANG KAlan SHORE Yuncai WANG 

机构地区：[1]Key Laboratory of Advanced Transducers and Intelligent Control System,Ministry of Education,Taiyuan University of Technology,Taiyuan 030024,China [2]Guangdong Provincial Key Laboratory of Photonics Information Technology,School of Information Engineering,Guangzhou 510006,China [3]School of Computer Science and Electronic Engineering,Bangor University,Wales LL571UT,UK

出　　处：《Science China(Information Sciences)》2023年第11期305-306,共2页中国科学（信息科学）（英文版）

基　　金：supported in part by National Natural Science Foundation of China(Grant Nos.61927811,62175177,U19A2076);Program for Guangdong Introducing Innovative and Entrepreneurial Teams;Natural Science Foundation of Shanxi Province(Grant Nos.201901D211116,201901D211077)。

摘　　要：Human action recognition(HAR)has important applications,including video retrieval,entertainment,autonomous navigation systems,and visual surveillance systems[1].Unfortunately,accurate and efficient HAR remains a challenging task in the field of computer vision because its modeling and characteristic representation belong to threedimensional space-time instead of common two-dimensional space[2].

关 键 词：COMPUTER COMPUTING action 

分 类 号：TP391.41[自动化与计算机技术—计算机应用技术]