CASIA OpenIR

浏览/检索结果: 共36条,第1-10条 帮助

限定条件                    
已选(0)清除 条数/页:   排序方式:
A memory and attention-based reinforcement learning for musculoskeletal robots with prior knowledge of muscle synergies 期刊论文
Robotic Intelligence and Automation, 2024, 卷号: 44, 期号: 2, 页码: 316-333
作者:  Xiaona Wang;  Jiahao Chen;  Hong Qiao
Adobe PDF(2591Kb)  |  收藏  |  浏览/下载:65/20  |  提交时间:2024/06/04
Musculoskeletal robot  Partial observable  Reinforcement learning  LSTM  Attention  Muscle synergy  
Robotics Dexterous Grasping: The Methods Based on Point Cloud and Deep Learning 期刊论文
Frontiers in Neurorobotics, 2021, 卷号: 15, 页码: 658280
作者:  Duan, Haonan;  Wang, Peng;  Huang, Yayu;  Xu, Guangyun;  Wei, Wei;  Shen, Xiaofei
Adobe PDF(3145Kb)  |  收藏  |  浏览/下载:50/18  |  提交时间:2024/05/29
Robotics  Dexterous grasping  Point Cloud  Deep learning  
Understanding and Mitigating Overfitting in Prompt Tuning for Vision-Language Models 期刊论文
IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS FOR VIDEO TECHNOLOGY, 2023, 卷号: 33, 期号: 9, 页码: 4616-4629
作者:  Ma, Chengcheng;  Liu, Yang;  Deng, Jiankang;  Xie, Lingxi;  Dong, Weiming;  Xu, Changsheng
Adobe PDF(1644Kb)  |  收藏  |  浏览/下载:174/29  |  提交时间:2023/11/16
Vision-language model  prompt tuning  over-fitting  subspace learning  gradient projection  
Many Hands Make Light Work: Transferring Knowledge from Auxiliary Tasks for Video-Text Retrieval 期刊论文
IEEE Transactions on Multimedia, 2022, 页码: 1-15
作者:  Wang, Wei;  Gao, Junyu;  Yang, Xiaoshan;  Xu, Changsheng
Adobe PDF(3679Kb)  |  收藏  |  浏览/下载:151/35  |  提交时间:2023/04/25
Motion Learning and Rapid Generalization for Musculoskeletal Systems Based on Recurrent Neural Network Modulated by Initial States 期刊论文
IEEE TRANSACTIONS ON COGNITIVE AND DEVELOPMENTAL SYSTEMS, 2022, 卷号: 14, 期号: 4, 页码: 1691-1704
作者:  Wang, Xiaona;  Chen, Jiahao;  Qiao, Hong
Adobe PDF(2080Kb)  |  收藏  |  浏览/下载:166/22  |  提交时间:2023/03/20
Muscles  Recurrent neural networks  Mathematical models  Bio-inspired control  Robot kinematics  Tendons  Musculoskeletal system  Biologically inspired control  motor cortex  movement preparation  musculoskeletal system  recurrent neural network (RNN)  
SLAN: Similarity-aware aggregation network for embedding out-of-knowledge-graph entities 期刊论文
NEUROCOMPUTING, 2022, 卷号: 491, 页码: 186-196
作者:  Li, Mingda;  Sun, Zhengya;  Zhang, Wensheng
Adobe PDF(931Kb)  |  收藏  |  浏览/下载:360/70  |  提交时间:2022/06/10
Knowledge graph embedding  Out-of-knowledge-graph entities  Knowledge graph completion  Similarity search  
Transformers in computational visual media: A survey 期刊论文
Computational Visual Media, 2021, 卷号: 8, 期号: 1, 页码: 33-62
作者:  Xu,Yifan;  Wei,Huapeng;  Lin,Minxuan;  Deng,Yingying;  Sheng,Kekai;  Zhang,Mengdan;  Tang,Fan;  Dong,Weiming;  Huang,Feiyue;  Xu,Changsheng
Adobe PDF(5366Kb)  |  收藏  |  浏览/下载:337/49  |  提交时间:2021/12/28
visual transformer  computational visual media (CVM)  high-level vision  low-level vision  image generation  multi-modal learning  
Combining Convex Hull and Directed Graph for Fast and Accurate Ellipse Detection 期刊论文
Graphcal Models, 2021, 卷号: 116, 期号: July, 页码: 101110
作者:  Shen, Zeyu;  Zhao, Mingyang;  Jia, Xiaohong;  Liang, Yuan;  Fan, Lubin;  Yan, Dong-Ming
Adobe PDF(40927Kb)  |  收藏  |  浏览/下载:274/41  |  提交时间:2021/06/09
Ellipse Detection  Edge Following  Hough transform  RANSAC  
High-speed rail pole number recognition through deep representation and temporal redundancy 期刊论文
NEUROCOMPUTING, 2020, 卷号: 415, 页码: 201-214
作者:  Yang, Yang;  Zhang, Wensheng;  He, Zewen;  Li, Ding
Adobe PDF(2751Kb)  |  收藏  |  浏览/下载:331/62  |  提交时间:2021/01/07
Region-based convolutional neural network  Context information  Object detection  Number recognition  Pole number  High-speed rail  
Robust Text Image Recognition via Adversarial Sequence-to-Sequence Domain Adaptation 期刊论文
IEEE Transactions on Image Processing, IEEE Transactions on Image Processing, 2020, 2020, 卷号: 30, 30, 期号: 0, 页码: 0-0, 0-0
作者:  Yaping Zhang;  Shuai Nie;  Shan Liang;  Wenju Liu
浏览  |  Adobe PDF(1412Kb)  |  收藏  |  浏览/下载:238/104  |  提交时间:2020/10/22
Sequence-to-sequence  text image recognition  domain adaptation  Sequence-to-sequence  text image recognition  domain adaptation