CASIA OpenIR

浏览/检索结果: 共15条,第1-10条 帮助

限定条件                        
已选(0)清除 条数/页:   排序方式:
多尺度视觉语义增强的多模态命名实体识别方法 期刊论文
自动化学报, 2024, 卷号: 50, 期号: 6, 页码: 1234-1245
作者:  王海荣;  徐玺;  王彤;  陈芳萍
Adobe PDF(2077Kb)  |  收藏  |  浏览/下载:17/7  |  提交时间:2024/07/02
多模态命名实体识别  多任务学习  多模态融合  Transformer  
基于表征学习的离线强化学习方法研究综述 期刊论文
自动化学报, 2024, 卷号: 50, 期号: 6, 页码: 1104-1128
作者:  王雪松;  王荣荣;  程玉虎
Adobe PDF(3333Kb)  |  收藏  |  浏览/下载:7/4  |  提交时间:2024/07/02
强化学习  离线强化学习  表征学习  历史经验数据  分布偏移  
The Journey/DAO/TAO of Embodied Intelligence: From Large Models to Foundation Intelligence and Parallel Intelligence 期刊论文
IEEE/CAA Journal of Automatica Sinica, 2024, 卷号: 11, 期号: 6, 页码: 1313-1316
作者:  Tianyu Shen;  Jinlin Sun;  Shihan Kong;  Yutong Wang;  Juanjuan Li;  Xuan Li;  Fei-Yue Wang
Adobe PDF(682Kb)  |  收藏  |  浏览/下载:51/18  |  提交时间:2024/05/22
Artificial intelligence  Chatbots  Autonomous systems  Intelligent systems  Robots  Digital humans  Robot kinematics  Learning (artificial intelligence)  Biological system modeling  Computational modeling  Human-robot interaction  Complex systems  Deep learning  Reinforcement learning  Large language models  
Comprehensive Relation Modelling for Image Paragraph Generation 期刊论文
Machine Intelligence Research, 2024, 卷号: 21, 期号: 2, 页码: 369-382
作者:  Xianglu Zhu;  Zhang Zhang;  Wei Wang;  Zilei Wang
Adobe PDF(1963Kb)  |  收藏  |  浏览/下载:52/21  |  提交时间:2024/04/23
Image paragraph generation, visual relationship, scene graph, graph convolutional network (GCN), long short-term memory  
Acquiring Weak Annotations for Tumor Localization in Temporal and Volumetric Data 期刊论文
Machine Intelligence Research, 2024, 卷号: 21, 期号: 2, 页码: 318-330
作者:  Yu-Cheng Chou;  Bowen Li;  Deng-Ping Fan;  Alan Yuille;  Zongwei Zhou
Adobe PDF(4008Kb)  |  收藏  |  浏览/下载:56/17  |  提交时间:2024/04/23
Weak annotation, detection, localization, segmentation, colonoscopy, abdomen  
The Life Cycle of Knowledge in Big Language Models: A Survey 期刊论文
Machine Intelligence Research, 2024, 卷号: 21, 期号: 2, 页码: 217-238
作者:  Boxi Cao;  Hongyu Lin;  Xianpei Han;  Le Sun
Adobe PDF(1430Kb)  |  收藏  |  浏览/下载:46/8  |  提交时间:2024/04/23
Pre-trained language model, knowledge acquisition, knowledge representation, knowledge probing, knowledge editing, knowledge application  
A Knowledge-enhanced Two-stage Generative Framework for Medical Dialogue Information Extraction 期刊论文
Machine Intelligence Research, 2024, 卷号: 21, 期号: 1, 页码: 153-168
作者:  Zefa Hu;  Ziyi Ni;  Jing Shi;  Shuang Xu;  Bo Xu
Adobe PDF(1525Kb)  |  收藏  |  浏览/下载:45/13  |  提交时间:2024/04/23
Medical dialogue understanding, information extraction, text generation, knowledge-enhanced prompt, low-resource setting, data augmentation  
AI for Supporting the Freedom of Drawing 期刊论文
Machine Intelligence Research, 2024, 卷号: 21, 期号: 1, 页码: 63-88
作者:  Xiaohua Sun;  Juexiao Qin
Adobe PDF(14055Kb)  |  收藏  |  浏览/下载:43/15  |  提交时间:2024/04/23
Intention understanding, drawing support, drawing, art, human-artificial intelligence (AI) collaboration  
Cogeneration of Innovative Audio-visual Content: A New Challenge for Computing Art 期刊论文
Machine Intelligence Research, 2024, 卷号: 21, 期号: 1, 页码: 4-28
作者:  Mengting Liu;  Ying Zhou;  Yuwei Wu;  Feng Gao
Adobe PDF(14438Kb)  |  收藏  |  浏览/下载:47/5  |  提交时间:2024/04/23
Artificial intelligence (AI) art, audio-visual, artificial intelligence generated content (AIGC), multimodal, artistic evaluation  
针对身份证文本识别的黑盒攻击算法研究 期刊论文
自动化学报, 2024, 卷号: 50, 期号: 1, 页码: 103-120
作者:  徐昌凯;  冯卫栋;  张淳杰;  郑晓龙;  张辉;  王飞跃
Adobe PDF(20872Kb)  |  收藏  |  浏览/下载:83/23  |  提交时间:2024/04/12
对抗样本  黑盒攻击  身份证文本识别  物理世界  二值化掩码