中文版 | English

在结果中检索

CASIA OpenIR

浏览/检索结果: 共6条，第1-6条 帮助

限定条件                        
已选(0)清除 条数/页：   排序方式：
Towards Unified Multi-Domain Machine Translation With Mixture of Domain Experts 期刊论文
IEEE-ACM TRANSACTIONS ON AUDIO SPEECH AND LANGUAGE PROCESSING, 2023, 卷号: 31, 页码: 3488-3498
作者:  Lu, Jinliang;  Zhang, Jiajun
Adobe PDF(2882Kb)  |  收藏  |  浏览/下载：131/2  |  提交时间：2023/12/21
Machine Translation  Multi-domain  Mixture-of-expert  
A compliant leg design combining pantograph structure with leaf springs 期刊论文
ROBOTICA, 2023, 页码: 15
作者:  Wang, Boxing;  Zhang, Kunting;  Ma, Xueyan;  Jia, Lihao
收藏  |  浏览/下载：77/0  |  提交时间：2023/12/21
legged robots  biomimetic robots  design  bipeds  humanoid robots  
Multi-Correlation Siamese Transformer Network With Dense Connection for 3D Single Object Tracking 期刊论文
IEEE ROBOTICS AND AUTOMATION LETTERS, 2023, 卷号: 8, 期号: 12, 页码: 8066-8073
作者:  Feng, Shihao;  Liang, Pengpeng;  Gao, Jin;  Cheng, Erkang
收藏  |  浏览/下载：98/0  |  提交时间：2023/12/21
3D object tracking  Point cloud  Transformer  
So Many Heads, So Many Wits: Multimodal Graph Reasoning for Text-Based Visual Question Answering 期刊论文
IEEE TRANSACTIONS ON SYSTEMS MAN CYBERNETICS-SYSTEMS, 2023, 页码: 12
作者:  Zheng, Wenbo;  Yan, Lan;  Wang, Fei-Yue
收藏  |  浏览/下载：96/0  |  提交时间：2023/12/21
Graph attention  graph reasoning  multimodal graph  self-attention  text-based visual question answering  
A New Language-Independent Deep CNN for Scene Text Detection and Style Transfer in Social Media Images 期刊论文
IEEE TRANSACTIONS ON IMAGE PROCESSING, 2023, 卷号: 32, 页码: 3552-3566
作者:  Shivakumara, Palaiahnakote;  Banerjee, Ayan;  Pal, Umapada;  Nandanwar, Lokesh;  Lu, Tong;  Liu, Cheng-Lin
收藏  |  浏览/下载：33/0  |  提交时间：2023/11/17
Text detection  style transfer  deep learning  EfficientNet  social media images  
Knowledge-Embedded Mutual Guidance for Visual Reasoning 期刊论文
IEEE TRANSACTIONS ON CYBERNETICS, 2023, 页码: 13
作者:  Zheng, Wenbo;  Yan, Lan;  Chen, Long;  Li, Qiang;  Wang, Fei-Yue
收藏  |  浏览/下载：117/0  |  提交时间：2023/11/16
Attention model  joint learning  knowledge embedding  visual reasoning