中文版 | English

在结果中检索

CASIA OpenIR

浏览/检索结果: 共5条，第1-5条 帮助

限定条件            
已选(0)清除 条数/页：   排序方式：
Connecting Model-Based and Model-Free Control With Emotion Modulation in Learning Systems 期刊论文
IEEE Transactions on Systems, Man, and Cybernetics: Systems, 2019, 卷号: 10, 期号: 4, 页码: 1-15
作者:  Huang, Xiao;  Wu, Wei;  Qiao, Hong
浏览  |  Adobe PDF(1614Kb)  |  收藏  |  浏览/下载：258/86  |  提交时间：2020/06/09
Brain-inspired computing  decision-making  emotion modulation  emotion-cognition interactions  reinforcement learning  
From Rough to Precise: Human-Inspired Phased Target Learning Framework for Redundant Musculoskeletal Systems 期刊论文
FRONTIERS IN NEUROROBOTICS, 2019, 卷号: 13, 期号: 61, 页码: 14
作者:  Zhou, Junjie;  Chen, Jiahao;  Deng, Hu;  Qiao, Hong
Adobe PDF(3654Kb)  |  收藏  |  浏览/下载：344/39  |  提交时间：2019/12/16
musculoskeletal system  human-inspired motion learning  noise in nervous system  reinforcement learning  phased target learning  
Realizing human-like manipulation with a musculoskeletal system and biologically inspired control scheme 期刊论文
NEUROCOMPUTING, 2019, 卷号: 339, 期号: 暂无, 页码: 116-129
作者:  Jiahao Chen;  Shanlin Zhong;  Erlong Kang;  Hong Qiao
Adobe PDF(4018Kb)  |  收藏  |  浏览/下载：375/49  |  提交时间：2019/07/12
Human-like manipulation  Musculoskeletal system  Biologically inspired  Muscle synergy  Attractive region in environment  
Un-supervised and semi-supervised hand segmentation in egocentric images with noisy label learning 期刊论文
NEUROCOMPUTING, 2019, 卷号: 334, 期号: 2019, 页码: 11-24
作者:  Li, Yinlin;  Jia, Lihao;  Wang, Zidong;  Qian, Yang;  Qiao, Hong
Adobe PDF(4423Kb)  |  收藏  |  浏览/下载：477/94  |  提交时间：2019/07/12
Hand segmentation  Un-supervised  Semi-supervised  Deep convolutional neural network  Noisy label  
Salient object detection based on an efficient End-to-End Saliency Regression Network 期刊论文
NEUROCOMPUTING, 2019, 卷号: 323, 期号: 1, 页码: 265-276
作者:  Xi, Xuanyang;  Luo, Yongkang;  Wang, Peng;  Qiao, Hong
Adobe PDF(3011Kb)  |  收藏  |  浏览/下载：464/82  |  提交时间：2019/01/08
Salient object detection  Saliency regression  Deep convolutional neural networks  Fully convolutional networks