检索结果-内蒙古大学图书馆

Proceedings of the 41st International Conference on Machine Learning

作者： Cong Hua Qianqian Xu Shilong Bao Zhiyong Yang Qingming Huang Key Laboratory of Intelligent Information Processing Institute of Computing Technology Chinese Academy of Sciences Beijing China and School of Computer Science and Technology University of Chinese Academy of Sciences Beijing China Key Laboratory of Intelligent Information Processing Institute of Computing Technology Chinese Academy of Sciences Beijing China Institute of Information Engineering Chinese Academy of Sciences Beijing China and School of Cyber Security University of Chinese Academy of Sciences Beijing China School of Computer Science and Technology University of Chinese Academy of Sciences Beijing China School of Computer Science and Technology University of Chinese Academy of Sciences Beijing China and Key Laboratory of Intelligent Information Processing Institute of Computing Technology Chinese Academy of Sciences Beijing China and Key Laboratory of Big Data Mining and Knowledge Management Chinese Academy of Sciences Beijing China

This paper explores a novel multi-modal alternating learning paradigm pursuing a reconciliation between the exploitation of uni-modal features and the exploration of cross-modal interactions. This is motivated by the fact that current paradigms of multi-modal learning tend to explore multi-modal features simultaneously. The resulting gradient prohibits further exploitation of the features in the weak modality, leading to modality competition, where the dominant modality overpowers the learning process. To address this issue, we study the modality-alternating learning paradigm to achieve reconcilement. Specifically, we propose a new method called ReconBoost to update a fixed modality each time. Herein, the learning objective is dynamically adjusted with a reconcilement regularization against competition with the historical models. By choosing a KL-based reconcilement, we show that the proposed method resembles Friedman's Gradient-Boosting (GB) algorithm, where the updated learner can correct errors made by others and help enhance the overall performance. The major difference with the classic GB is that we only preserve the newest model for each modality to avoid overfitting caused by ensembling strong learners. Furthermore, we propose a memory consolidation scheme and a global rectification scheme to make this strategy more effective. Experiments over six multi-modal benchmarks speak to the efficacy of the method. We release the code at https://***/huacong/ReconBoost.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Overview of the Tenth Dialog System Technology Challenge: DSTC10

引用

IEEE/ACM Transactions on Audio Speech and Language Processing 2024年 32卷 765-778页

作者： Yoshino, Koichiro Chen, Yun-Nung Crook, Paul Kottur, Satwik Li, Jinchao Hedayatnia, Behnam Moon, Seungwhan Fei, Zhengcong Li, Zekang Zhang, Jinchao Feng, Yang Zhou, Jie Kim, Seokhwan Liu, Yang Jin, Di Papangelis, Alexandros Gopalakrishnan, Karthik Hakkani-Tur, Dilek Damavandi, Babak Geramifard, Alborz Hori, Chiori Shah, Ankit Zhang, Chen Li, Haizhou Sedoc, Joao D'haro, Luis F. Banchs, Rafael Rudnicky, Alexander Guardian Robot Project R-IH RIKEN 2-2-2 Hikaridai Seika Shoraku619-0288 Japan Information Science Nara Institute of Science and Technology Ikoma630-0101 Japan Computer Science and Information Engineering National Taiwan University Taipei10617 Taiwan Inc. Palo AltoCA95054 United States Alexa AI *** Inc. SunnyvaleCA94089 United States Meta Seattle RedmondWA98052 United States Institute of Computing Technology Chinese Academy of Sciences Beijing100190 China Key Laboratory of Intelligent Information Processing Institute of Computing Technology Chinese Academy of Sciences Beijing100190 China Tencent AI Lab Beijing Beijing China Kexueyuan South Road Zhongguancun Beijing100190 China Beijing 100190 China Alexa AI *** Inc. SunnyvaleCA United States 1120 Enterprise way Sunnyvale94089 United States *** Inc. SeattleWA United States Menlo Park CA United States Audio and Speech Group Mitsubishi Electric Research Laboratories CambridgeMA02139-1955 United States Carnegie Mellon University Department of Language and Information Technologies or just Carnegie Mellon University Pittsburgh United States National University of Singapore Singapore Singapore Department of Electrical and Computer Engineering National University of Singapore Singapore Singapore Shenzhen Research Institute of Big Data School of Data Science Chinese University of Hong Kong Shenzhen518172 China New York University New YorkNY United States ETSI de Telecomunicacion - Speech Technology and Machine Learning Group Universidad Politecnica de Madrid Ciudad Universitaria Madrid28040 Spain Nanyang Technological University Singapore Singapore Carnegie Mellon University PittsburghPA United States

This article introduces the Tenth Dialog System Technology Challenge (DSTC-10). This edition of the DSTC focuses on applying end-to-end dialog technologies for five distinct tasks in dialog systems, namely 1. Incorporation of Meme images into open domain dialogs, 2. knowledge-grounded Task-oriented Dialogue Modeling on Spoken Conversations, 3. Situated Interactive Multimodal dialogs, 4. Reasoning for Audio Visual Scene-Aware Dialog, and 5. Automatic Evaluation and Moderation of Open-domainDialogue Systems. This article describes the task definition, provided datasets, baselines, and evaluation setup for each track. We also summarize the results of the submitted systems to highlight the general trends of the state-of-the-art technologies for the tasks. © 2023 The Authors.

关键词： Job analysis

来源：评论

学校读者我要写书评

暂无评论

Corrigendum to “Do we measure novelty when we analyze unusual combinations of cited references? A validation study of bibliometric novelty indicators based on F1000Prime data” [Journal of Informetrics 13/4 (2019) 100979]

引用

Journal of Informetrics 2024年第3期18卷

作者： Lutz Bornmann Alexander Tekles Helena H. Zhang Fred Y. Ye Science Policy and Strategy Department Administrative Headquarters of the Max Planck Society Hofgartenstr. 8 80539 Munich Germany University of Passau Innstr. 41 94032 Passau Germany Jiangsu Key Laboratory of Data Engineering and Knowledge Service School of Information Management Nanjing University Nanjing 210023 China

来源：评论

学校读者我要写书评

暂无评论

基于主题语义的非合作结构化Top-N深网数据源选择

基于主题语义的非合作结构化Top-N深网数据源选择

引用

第29届中国数据库学术会议

作者： Deng Song 邓松 Wan Changxuan 万常选 Liu Xiping 刘喜平 Jiang Tengjiao 江腾蛟 Lei Gang 雷刚 School of Information and Technology Jiangxi University of Finance and Economics Nanchang 330013 江西财经大学信息管理学院南昌 330013 Jiangxi Key Laboratory of Data and Knowledge Engineering Jiangxi University of Finance and Economic 江西财经大学数据与知识工程江西省高校重点实验室南昌 330013

高效且准确地找出存在于深网中的与用户查询意图最相关的Top-N元组，是深网数据集成中的关键问题。针对数据源内容概括未见成果的现状，本文提出了一种能够有效概括非数字、非离散属性特征的非合作结构化深网数据源摘要构建方法。利用... 详细信息

高效且准确地找出存在于深网中的与用户查询意图最相关的Top-N元组，是深网数据集成中的关键问题。针对数据源内容概括未见成果的现状，本文提出了一种能够有效概括非数字、非离散属性特征的非合作结构化深网数据源摘要构建方法。利用主题词抽样，依据主题语义选择与主题词相关的特征词，通过主题词及特征词构建数据源语义摘要。实验结果表明与传统的基于词频的方法相比较，该方法在召回率及准确度方面均有较大幅度的提升。

关键词：深网数据集成检索系统优化设计信息提取主题语义

来源：评论

学校读者我要写书评

暂无评论

Author Correction:data augmentation in microscopic images for material data mining

引用

npj Computational Materials 2020年第1期6卷 476-476页

作者： Boyuan Ma Xiaoyan Wei Chuni Liu Xiaojuan Ban Haiyou Huang Hao Wang Weihua Xue Stephen Wu Mingfei Gao Qing Shen Michele Mukeshimana Adnan Omer Abuassba Haokai Shen Yanjing Su Beijing Advanced Innovation Center for Materials Genome Engineering University of Science and Technology Beijing Beijing China School of Computer and Communication Engineering University of Science and Technology Beijing Beijing China Beijing Key Laboratory of Knowledge Engineering for Materials Science Beijing China Institute for Advanced Materials and Technology University of Science and Technology Beijing Beijing China School of Materials Science and Engineering University of Science and Technology Beijing Beijing China School of Materials Science and Technology Liaoning Technical University Liaoning China The Institute of Statistical Mathematics Research Organization of Information and Systems Tachikawa Tokyo Japan National Intellectual Property Administration Beijing China Faculty of Engineering Sciences University of Burundi Bujumbura Burundi Faculty of Engineering and Technology Palestine Technical University – Kadoorie Tulkarem Palestine College of Information Science and Engineering China University of Petroleum Beijing China Key Lab of Petroleum Data Mining China University of Petroleum Beijing China

The original version of this article omitted the following from the Acknowledgements:“This work was supported by Beijing Top Discipline for Artificial Intelligent Science and engineering,University of Science and Tec... 详细信息

关键词： HTML knowledge mining

来源：评论

学校读者我要写书评

暂无评论

Linked data Crowdsourcing Quality Assessment based on Domain Professionalism

引用

Journal of Physics: Conference Series 2019年第5期1187卷

作者： Lu Yang Li Huang Zhenzhen Liu School of Computer Science and Technology Wuhan University of Science and Technology Wuhan 430065 China Key Laboratory of Intelligent Information Processing and Real-time Industrial System in Hubei Province Wuhan 430065 China Institute of Big Data Science and Engineering Wuhan University of Science and Technology Wuhan 430065 China Key Laboratory of Rich-media Knowledge Organization and Service of Digital Publishing Content National Press and Publication Administration Beijing 100038 China

With the rapid development of Internet technology, crowdsourcing, as a flexible, effective and low-cost problem-solving method, has begun to receive more and more attention. The use of crowdsourcing to evaluate the quality of linked data has also become a research hotspot. This paper proposes the concept of Domain Specialization Test (DST), which uses domain professional testing tasks DSTs to evaluate the professionalism of workers, and combines the idea of Mini-batch Gradient Descent (MBGD) to improve the EM algorithm, and the MBEM algorithm is proposed to achieve efficient and accurate evaluation of task results. The experimental results show that the proposed method can screen out the appropriate workers for the linked data crowdsourcing task and improve the accuracy and iteration efficiency of the results.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Emergency Event Matching using Hierarchical Blocking Method

引用

Journal of Physics: Conference Series 2019年第5期1187卷

作者： Chang Wen Yu Liu College of Computer Science and Technology Wuhan University of Science and Technology Wuhan 430065 China Key Laboratory of Intelligent Information Processing and Real-time Industrial System in Hubei Province Wuhan 430065 China Institute of Big Data Science and Engineering Wuhan University of Science and Technology Wuhan 430065 China Key Laboratory of Rich-media Knowledge Organization and Service of Digital Publishing Content National Press and Publication Administration Beijing 100038 China

With the extensive application of the knowledge base (KB), how to complete it is a hot topic on Semantic Web. However, many problems go with the big data, and the event matching is one of these problems, which is finding out the entities referring to the same things in the real world and also the key point in the extending process. To enrich the emergency knowledge base (E-SKB) we constructed before, we need to filter out the news from several web pages and find the same news to avoid data redundancy. In this paper, we proposed a hierarchy blocking method to reduce the times of comparisons and narrow down the scope by extracting the news properties as the blocking keys. The method transforms the event matching problem into a clustering problem. Experimental results show that the proposed method is superior to the existing text clustering algorithm with high precision and less comparison times.

关键词：

来源：评论

学校读者我要写书评

暂无评论

基于划分的集合相似连接

基于划分的集合相似连接

引用

第29届中国数据库学术会议

作者： Rong Chuitian 荣垂田 Xu Tianren 徐天任 Du Xiaoyong 杜小勇 Key Laboratory of Data Engineering and Knowledge Engineering(Renmin University of China) Ministry o 教育部数据工程与知识工程重点实验室(中国人民大学) 北京 100872 中国人民大学信息学院北京 100872 School of Information Renmin University of China Beijing 100872 Key Laboratory of Education Inform 中国人民大学信息学院北京 100872 民族教育信息化教育部重点实验室(云南师范大学) 昆明 650500

集合相似连接(set similarity join)是指在给定的数据集中，按照基于集合间覆盖关系的相似度计算方法来衡量数据之间的相似度、并找出所有相似度不小于给定阈值的数据对的操作。集合相似连接作为一种新的基本操作在很多领域中有重要应... 详细信息

集合相似连接(set similarity join)是指在给定的数据集中，按照基于集合间覆盖关系的相似度计算方法来衡量数据之间的相似度、并找出所有相似度不小于给定阈值的数据对的操作。集合相似连接作为一种新的基本操作在很多领域中有重要应用。随着社会网络、移动应用以及在线服务的发展，使得数据收集的效率和规模得到了很大的提高，同时给相似连接操作带来新的挑战。根据集合相似的必要条件，提出了相似集合之间的差异度。利用差异度和鸽巢原理，提出了一种新颖的基于数据划分的集合相似连接计算方法，该方法对集合进行自适应的均衡划分，并利用基于划分块的过滤方法来提高过滤的效率。为了进一步提高过滤的效果和相似连接的效率，利用划分块的位置信息提出了增强的过滤方法。针对提出的方法，在不同的环境下进行了实验，实验结果表明，该方法与已有的方法相比可以有效地提高相似连接的效率。

关键词：数据库集合相似连接均衡划分法阈值

来源：评论

学校读者我要写书评

暂无评论

Edge-centric functional network reveals new spatiotemporal biomarkers of early mild cognitive impairment

Brain‐X

引用

Brain‐X 2023年第3期1卷

作者： Weiping Wang Ruiying Du Zhen Wang Xiong Luo Haiyan Zhao Ping Luan Jipeng Ouyang Song Liu School of Computer and Communication Engineering University of Science and Technology Beijing Beijing China Shunde Graduate School Beijing University of Science and Technology Shunde Guangdong China Beijing Key Laboratory of Knowledge Engineering for Materials Science Beijing China Contribution: Investigation Writing - original draft Writing - review & editing The Center for Optical Imagery Analysis and Learning and School of Mechanical Engineering Northwestern Polytechnical University Xi'an Shaanxi China Weiping Wang Zhen Wang and Haiyan Zhao. Contribution: Conceptualization Formal analysis Contribution: Formal analysis Supervision Department of Neurology Peking University Third Hospital Beijing China Contribution: Data curation Formal analysis Guangdong Second People's Hospital Guangzhou Guangdong China Department of Neurology Shunde Hospital Southern Medical University Shunde Guangdong China Contribution: Conceptualization Data curation Southeast Asia Project Manager Department of China Petroleum Pipeline Engineering Co. Ltd. Langfang Hebei China Contribution: Software Supervision

Most neuroimaging studies of the pathogenesis of early mild cognitive impairment (EMCI) rely on a node-centric network model, which only calculates correlations between brain regions. Considering the interaction of low-order correlations between pairs of brain regions, we use an edge-centric network model to study high-order functional network correlations. Here, we compute edge time series (eTS) to obtain overlapping communities and study the relationship between subnetworks and communities in space. Then, based on the overlapping communities, we calculate the normalized entropy to measure the diversity of each node. Next, we compute the high-amplitude co-fluctuation of the eTS to explore the pattern of brain activity with temporal precision. Our results show that the normal control and EMCI patients differ in brain regions, subnetworks, and the whole brain. In particular, entropy values show a gradual decrease, and brain network co-fluctuation increases with disease progression. Our study is the first to investigate the pathogenesis of EMCI from the perspective of spatiotemporal flexibility and cognitive diversity based on high-order edge connectivity, further characterizing brain dynamics and providing new insights into the search for biomarkers of EMCI.

关键词： co-fluctuation edge-centric functional flexibility overlapping community spatiotemporal

来源：评论

学校读者我要写书评

暂无评论

Bimagnetic Core/Shell Nanoprobes with Tunable Exchange Coupling for High Resolution and Sensitive Magnetic Particle Imaging

引用

Angewandte Chemie 2024年第6期137卷

作者： Qilong Li Changjian Li Yueqi Wang Miaomiao Li Zeyu Liang Qiyue Wang Bingzhe Wang Canyu Huang Jie Tian Fangyuan Li Prof. Daishun Ling Frontiers Science Center for Transformative Molecules School of Chemistry and Chemical Engineering School of Biomedical Engineering National Center for Translational Medicine Shanghai Jiao Tong University Shanghai 200240 China These authors contributed equally to this work School of Engineering Medicine Beihang University Beijing 100191 China Key Laboratory of Big Data-Based Precision Medicine (Beihang University) Ministry of Industry and Information Technology Beijing 100191 China CAS Key Laboratory of Molecular Imaging Beijing Key Laboratory of Molecular Imaging Institute of Automation Chinese Academy of Sciences Beijing 100190 China Clinical College of Armed Police General Hospital of Anhui Medical University Department of Gastroenterology of The Third Medical Center of Chinese PLA General Hospital Beijing 100039 China Songjiang Research Institute Shanghai Key Laboratory of Emotions and Affective Disorders (LEAD) Songjiang Hospital Affiliated to Shanghai Jiao Tong University School of Medicine Shanghai 201600 China World Laureates Association (WLA) Laboratories Shanghai 201203 China

Magnetic particle imaging (MPI) has demonstrated versatile applications in biomedicine, including tumor imaging, cell tracking, and image-guided hyperthermia. Despite these advancements, the prevalent use of clinically approved tracers has posed limitations on MPI′s resolution and sensitivity. In this study, we engineered a bimagnetic core/shell nanocrystals (BMCS) tailored for MPI by optimizing the heterostructure and modulating the exchange coupling effect between the two magnetic components. The resulting BMCS exhibited remarkably heightened susceptibility and magnetization while maintaining low coercivity, thereby substantially improved both MPI resolution and sensitivity compared to conventional tracers such as VivoTrax. At an equivalent mass concentration, BMCS demonstrated a notable 5.08-fold increase in signal intensity and achieved an unprecedentedly high resolution down to 1 mm. The excellent MPI performance contributes to high resolution MPI and the sensitive detection of orthotopic colorectal cancer in mice. The design strategy employed in BMCS, centered on the exchange coupling effect, introduces an efficacious approach for the development of high performance MPI tracers.

关键词： bimagnetic core/shell nanocrystals exchange coupling effect high resolution and sensitivity magnetic particle imaging

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：