Zobrazeno 1 - 10
of 801
pro vyhledávání: '"Ma, Xiaoguang"'
Behavior cloning (BC) is a popular supervised imitation learning method in the societies of robotics, autonomous driving, etc., wherein complex skills can be learned by direct imitation from expert demonstrations. Despite its rapid development, it is
Externí odkaz:
http://arxiv.org/abs/2408.10568
Industrial managements, including quality control, cost and safety optimization, etc., heavily rely on high quality industrial human action recognitions (IHARs) which were hard to be implemented in large-scale industrial scenes due to their high cost
Externí odkaz:
http://arxiv.org/abs/2403.08420
Remarkable successes were made in Medical Image Classification (MIC) recently, mainly due to wide applications of convolutional neural networks (CNNs). However, adversarial examples (AEs) exhibited imperceptible similarity with raw data, raising seri
Externí odkaz:
http://arxiv.org/abs/2403.06798
Deep neural networks were significantly vulnerable to adversarial examples manipulated by malicious tiny perturbations. Although most conventional adversarial attacks ensured the visual imperceptibility between adversarial examples and corresponding
Externí odkaz:
http://arxiv.org/abs/2402.03095
Autor:
Gu, Hankang, Wang, Shangbo, Ma, Xiaoguang, Jia, Dongyao, Mao, Guoqiang, Lim, Eng Gee, Wong, Cheuk Pong Ryan
Multi-agent Deep Reinforcement Learning (MADRL) based traffic signal control becomes a popular research topic in recent years. To alleviate the scalability issue of completely centralized RL techniques and the non-stationarity issue of completely dec
Externí odkaz:
http://arxiv.org/abs/2303.11899
Publikováno v:
Chengshi guidao jiaotong yanjiu, Vol 27, Iss 5, Pp 163-166 (2024)
Objective The permanent magnet direct drive technology for metro trains, as a novel traction solution, offers certain advantages in energy saving and noise reduction. Thus, it is aimed to specifically investigate its energy-saving effect. Method Theo
Externí odkaz:
https://doaj.org/article/2d77db2c695c4a37b6c0d900f8fa39f6
Autor:
Huang, Youpei1 (AUTHOR) pz12621@163.com, Ma, Xiaoguang1,2 (AUTHOR), Ren, Lihui1 (AUTHOR) renlihui@tongji.edu.cn
Publikováno v:
Sensors (14248220). Aug2024, Vol. 24 Issue 16, p5385. 16p.
Most feature-based stereo visual odometry (SVO) approaches estimate the motion of mobile robots by matching and tracking point features along a sequence of stereo images. However, in dynamic scenes mainly comprising moving pedestrians, vehicles, etc.
Externí odkaz:
http://arxiv.org/abs/2205.08207
Autor:
Chen, Qiuying, Tan, Xiaoming, Dastan, Davoud, Zhang, Zhenkai, Liu, Zhenyue, Yue, Chen, Yang, Zhiguo, Mu, Yang, Wang, Xiaoning, Chen, Xingtai, Wang, Feifei, Yin, Xi-Tao, Ma, Xiaoguang
Publikováno v:
In Journal of Alloys and Compounds 25 October 2024 1003
Publikováno v:
In International Journal of Hydrogen Energy 18 October 2024 87:620-629