检索结果-内蒙古大学图书馆

您好，读者！请登录

内蒙古大学图书馆

首页
概况
党建
资源
服务
科研支持
- 论文收录引用证明
- 科技查新
知识产权
档案馆
帮助

咨询与建议

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

您的常用邮箱：*

您的手机号码：*

问题描述：

当前已输入0个字，您还可以输入200个字

全部搜索
期刊论文
图书
学位论文
标准
纸本馆藏
外文资源发现
数据库导航
超星发现

高级检索

时间限定

出版年份：

文献类型

图书期刊文献学位论文多媒体

馆藏选择

电子馆藏纸本馆藏

核心期刊

全部期刊 SCI 收录期刊 SSCI 收录期刊 EI 收录期刊 CSCD 收录期刊 CSSCI 收录期刊

语言

中文英文

文献类型

期刊文献图书学位论文标准纸本馆藏

帮助

文字说明：

T=题名（书名、题名），A=作者（责任者），K=主题词，P=出版物名称，PU=出版社名称，O=机构（作者单位、学位授予单位、专利申请人），L=中图分类号，C=学科分类号，U=全部字段，Y=年（出版发行年、学位年度、标准发布年）

检索规则说明：

AND代表“并且”；OR代表“或者”；NOT代表“不包含”；(注意必须大写,运算符两边需空一格)

检索范例：

范例一：(K=图书馆学 OR K=情报学) AND A=范并思 AND Y=1982-2016
范例二：P=计算机应用与软件 AND (U=C++ OR U=Basic) NOT K=Visual AND Y=2011-2016

分类表

所选分类

>> <<

限定检索结果

文献类型

108,393 篇 会议
15,710 册 图书
11,132 篇 期刊文献
5 篇 学位论文

馆藏范围

135,098 篇 电子文献
172 种 纸本馆藏

日期分布

学科分类号

107,593 篇 工学
- 93,034 篇 计算机科学与技术...
- 66,621 篇 软件工程
- 23,080 篇 信息与通信工程
- 12,523 篇 电气工程
- 8,335 篇 控制科学与工程
- 8,186 篇 生物工程
- 8,080 篇 生物医学工程（可授...
- 6,298 篇 光学工程
- 4,395 篇 电子科学与技术（可...
- 3,849 篇 机械工程
- 3,613 篇 化学工程与技术
- 2,782 篇 建筑学
- 2,344 篇 动力工程及工程热...
- 2,310 篇 土木工程
- 2,013 篇 安全科学与工程
55,645 篇 理学
- 41,034 篇 数学
- 9,541 篇 生物学
- 8,451 篇 物理学
- 7,807 篇 统计学（可授理学、...
- 4,824 篇 系统科学
- 3,129 篇 化学
22,327 篇 管理学
- 13,183 篇 图书情报与档案管...
- 10,142 篇 管理科学与工程(可...
- 6,928 篇 工商管理
5,726 篇 医学
- 5,270 篇 临床医学
- 4,545 篇 基础医学(可授医学...
- 3,132 篇 药学(可授医学、理...
3,692 篇 法学
- 3,126 篇 社会学
2,462 篇 教育学
- 2,420 篇 教育学
2,158 篇 经济学
- 2,152 篇 应用经济学
1,824 篇 农学
171 篇 军事学
107 篇 文学
74 篇 艺术学
17 篇 哲学
2 篇 历史学

主题

8,048 篇 artificial intel...
4,831 篇 computer communi...
3,512 篇 information syst...
2,777 篇 algorithm analys...
2,431 篇 software enginee...
2,003 篇 image processing...
1,991 篇 user interfaces ...
1,974 篇 semantics
1,939 篇 computers
1,917 篇 information stor...
1,657 篇 computer applica...
1,524 篇 pattern recognit...
1,468 篇 data mining and ...
1,432 篇 computer vision
1,424 篇 software enginee...
1,375 篇 database managem...
1,251 篇 distributed comp...
1,227 篇 theory of comput...
1,216 篇 computer circuit...
1,180 篇 computer systems...

机构

202 篇 university of sc...
152 篇 huazhong univers...
151 篇 department of co...
145 篇 institute of inf...
121 篇 department of co...
121 篇 tsinghua univers...
116 篇 shanghai jiao to...
112 篇 national institu...
96 篇 school of comput...
91 篇 chinese academy ...
85 篇 école des ponts ...
83 篇 department of co...
81 篇 university of el...
74 篇 karnataka bangal...
72 篇 department of co...
71 篇 college of compu...
68 篇 school of comput...
67 篇 university of ch...
63 篇 school of comput...
63 篇 college of compu...

作者

73 篇 vardi moshe y.
70 篇 wang lei
60 篇 zhang lei
59 篇 pnueli amir
47 篇 hancock edwin r.
41 篇 huang yueh-min
40 篇 li xin
40 篇 marina l. gavril...
38 篇 man ka lok
38 篇 li yang
37 篇 jiang xiaoyi
37 篇 stuckey peter j.
35 篇 zhang tao
34 篇 yu yong
34 篇 liu bo
33 篇 panayiotis zaphi...
33 篇 jianying zhou
32 篇 peleg david
31 篇 hsu tsan-sheng
31 篇 lee dong chun

语言

130,663 篇 英文
2,755 篇 其他
1,490 篇 中文
326 篇 德文
4 篇 法文
1 篇 加泰罗尼亚文
1 篇 俄文

检索条件"任意字段=Lecture Notes in Computer Science"

共 135240 条记录，以下是1211-1220 订阅

全选清除本页清除全部题录导出标记到"检索档案"

详细简洁

排序：

Multi-view Transformer-Based Network for Prerequisite Learning in Concept Graphs 23rd

Multi-view Transformer-Based Network for Prerequisite Learn...

引用

23rd International Semantic Web Conference, ISWC 2024

作者： Wang, Zhichun Shao, Yifeng Peng, Boci Li, Bangui Li, Yun Wang, Qianren Li, Nijun School of Artificial Intelligence Beijing Normal University Beijing China Engineering Research Center of Intelligent Technology and Educational Application Ministry of Education Beijing China School of Intelligence Science and Technology Peking University Beijing China School of Computer Science and Engineering Beihang University Beijing China Advanced Cognitive AI Lab Shanghai Huawei Technologies Shanghai China

ISBN: (纸本)9783031778438

Prerequisite learning is the task of identifying prerequisite relations among concepts, which is important for many AI-based educational applications. Previous approaches explore different kinds of learning resources to obtain useful features for predicting prerequisites. Early approaches use handcrafted features while recent approaches use neural networks to encode information of concepts. To further improve the results of prerequisite learning, we build concept graphs to include comprehensive information about concepts from open data and learning resources, and propose a Multi-view Transformer-based Network (MTN) to encode multi-view features of concepts in the graph. Multi-view features are fused to make accurate predictions of concept prerequisites. We evaluate our approach on four public datasets and compare it with recently published approaches. The results show that our approach can achieve state-of-the-art results in the task of prerequisite learning. The source code and data are available at https://***/kg-bnu/MTN. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2025.

关键词： Contrastive Learning

来源：评论

学校读者我要写书评

暂无评论

Efficient Remote Memory Paging for Disaggregated Memory Systems 1

引用

22nd International Conference on Algorithms and Architectures for Parallel Processing, ICA3PP 2022

作者： Wang, Tao Liu, Haikun Jin, Hai National Engineering Research Center for Big Data Technology and System Services Computing Technology and System Lab Cluster and Grid Computing Lab School of Computer Science and Technology Huazhong University of Science and Technology Wuhan430074 China

ISBN: (数字)9783031226779

ISBN: (纸本)9783031226762

Memory disaggregation has attracted increasing attention in recent years because it is a cost-efficient approach to scale memory capacity for applications in a data center. However, the latency of remote memory access is a major concern in disaggregated memory systems. This paper presents VANDI, a virtual memory paging mechanism that allows applications to use remote memory pools transparently. VANDI enables effective data caching and prefetching mechanisms to address the problem of high access latency in disaggregated memory systems. VANDI exploits a low-complexity cache replacement strategy to optimize the asynchronous staging queue so that the remote write latency can be significantly reduced. VANDI can also prefetch data in multi-granularity from a remote memory pool in an adaptive manner, and thus further improves the hit rate of the local cache to reduce the read latency of remote memory. Our extensive experiments using micro-benchmarks show that VANDI can improve the performance of typical remote paging system–Infiniswap by up to 15 × –102 ×. VANDI can also improve the performance of state-of-the-art disaggregated memory system–Valet by 1.2 × –2.7 ×. For typical machine learning workloads, VANDI can achieve 20% to 80% performance improvement compared with the state-of-the-art Valet. © 2023, Springer Nature Switzerland AG.

关键词： Paging systems

来源：评论

学校读者我要写书评

暂无评论

SpeechBalloon: A New Approach of Providing User Interface for Real-Time Generation of Meeting notes 17th

SpeechBalloon: A New Approach of Providing User Interface fo...

引用

17th International Conference on Universal Access in Human-computer Interaction (UAHCI) part of the 25th International Conference on Human-computer Interaction (HCI)

作者： Kim, Donghyeon Yoon, Suyeon Seo, Jiyoung Jeong, SeungHoon Lee, Bowon Inha Univ Dept Elect Engn Incheon South Korea Inha Univ Dept Elect & Comp Engn Incheon South Korea

ISBN: (纸本)9783031356803;9783031356810

This paper proposes SpeechBalloon, a solution for real-time generation of meeting notes for the purpose of facilitating effective communications among participants. This is especially important when some of the participants have hearing problems. To provide an assistive technology for the hearing-impaired, the proposed solution, consisting of a device application running speech-to-text and a server collecting the information from each device, provides users with meeting notes. The advantage of our proposed system is that it does not require any specific hardware for note taking as long as each meeting participant brings his/her own device such as a smartphone or a tablet. We expect our proposed SpeechBalloon can help hearing-impaired people to actively participate in real meetings and overcome any inconveniences that they have due to their disabilities.

关键词： Meeting notes Speech-to-Text UI for Hearing-Impaired Mobile Applications

来源：评论

学校读者我要写书评

暂无评论

A New Mining Consensus Algorithm: A Binary Matrix Representation Based 27th

A New Mining Consensus Algorithm: A Binary Matrix Representa...

引用

27th International Conference on Distributed computer and Communication Networks, DCCN 2024

作者： Kara, Mostefa Laouid, Abdelkader Hammoudeh, Mohammad Makeeva, Elena Bounceur, Ahcene Information and Computer Science Department King Fahd University of Petroleum and Minerals Academic Belt Road Dhahran31261 Saudi Arabia LIAP Laboratory University of El Oued PO Box 789 El Oued39000 Algeria RUDN University 6 Miklukho-Maklaya St. Moscow Russia Information Systems Department University of Sharjah University City Sharjah United Arab Emirates

ISBN: (纸本)9783031808524

Abdelkader et al. recently proposed a new data representation method designed to enable efficient storage and management of diverse data types on the blockchain, guarantee scalability, cost-effectiveness, and network efficiency. They transformed a binary matrix M of dimensions m×n bits into two vectors H and V with sizes m′ and n′, respectively. The compression rate given by (m′+n′+∣Hash(M)∣)×100(m×n) expands exponentially, i.e., 2λ with λ depends on m and n), making their technique highly effective for data size reduction. For instance, with a matrix M of size 512×512 bits, they achieved a reduction rate of 96.42%. The conversion from M to (H, V) is both fast and simple. The presented paper uses these parameters to create a new consensus algorithm based on solving the challenge of recovering the original data using H, V, and Hash(M) in order to determine the next miner. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2025.

关键词： Blockchain Consensus Distributed algorithm Energy Storage

来源：评论

学校读者我要写书评

暂无评论

Enhancing Multimodal Rumor Detection with Statistical Image Features and Modal Alignment via Contrastive Learning 21st

Enhancing Multimodal Rumor Detection with Statistical Image...

引用

21st Pacific Rim International Conference on Artificial Intelligence, PRICAI 2024

作者： Zhou, Chenyu Li, Xiuhong Li, Zhe Chen, Fan Sheng, Jiabao Chen, Bin Wang, Haoyu School of Computer Science and Technology Xinjiang University Xinjiang China Department of Electrical and Electronic Engineering The Hong Kong Polytechnic University Hong Kong Department of Electrical Engineering Stanford University CA United States Department of Health Technology and Informatics The Hong Kong Polytechnic University Hong Kong School of Mechanical Engineering University of Shanghai for Science and Technology Shanghai China School of Electronic and Electrical Engineering Shanghai University of Engineering Science Shanghai China

ISBN: (纸本)9789819601219

The swift proliferation of multimodal rumors on social media, particularly those with manipulated images and complex intermodal interactions, significantly challenges current detection methods. In response, we utilize statistical image features, including mean and variance, to capture spatial attributes effectively and improve the detection of image-tampered tweets. To tackle complex intermodal correlations, we introduce a contrastive learning approach that aligns features across modalities efficiently. Additionally, we introduce a cross-attention fusion module (CAFM) that enhances the integration of image and text modalities, thereby improving multimodal rumor detection performance. In conclusion, we propose the cross-attention fusion network (ConCAFN), leveraging contrastive learning for robust multimodal rumor detection. Extensive experiments on two real-world datasets confirm the model’s enhanced capability to detect multimodal rumors accurately, demonstrating our methods’ effectiveness. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

关键词： Contrastive Learning

来源：评论

学校读者我要写书评

暂无评论

Enhancing Parameter-Efficient Transformers with Contrastive Syntax and Regularized Dropout for Neural Machine Translation 21st

Enhancing Parameter-Efficient Transformers with Contrastive...

引用

21st Pacific Rim International Conference on Artificial Intelligence, PRICAI 2024

作者： Fan, Yunlong Yang, Zhiheng Li, Baixuan Gao, Zhiqiang School of Computer Science and Engineering Southeast University Nanjing China Key Laboratory of Computer Network and Information Integration Southeast University Ministry of Education Nanjing China

ISBN: (纸本)9789819601219

Transformers have significantly improved Neural Machine Translation (NMT) models, accompanied by the inherent space complexity of O(n2). While recent approaches aim to be parameter-efficient, they often exhibit limited generalization capabilities with fewer parameters and decreased performances in longer sentences. To this end, we propose two methods, Syntax-enhanced Contrastive Learning (Syn-CL) and JS divergence-based Regularized Dropout (JSR-Drop) for the cross-layer parameter-sharing Transformer (baseline) in NMT. In Syn-CL, we add the corresponding target-to-source instances for the same batch in an extra bidirectional training phase, and minimize the distances of syntax-enhanced representation between the bilingual sentence-pair while maximizing the ones among others. In JSR-Drop, we refine the regularized dropout strategy with JS divergence, and improve generalization capabilities by reducing Transformers’ inconsistencies between training and inference introduced by dropout. Extensive experiments on six NMT tasks, IWSLT2014 (German↔English) and IWSLT2017 (English↔French and English↔Romanian), show an average BLEU score of 37.55, surpassing the vanilla Transformer and the baseline up to 1.75 BLEU, and outperforming models with 1.5×, 2.0× parameters in translating long sentences. Our code is available at https://***/Anon1214/EnPeNMT. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

关键词： Contrastive Learning

来源：评论

学校读者我要写书评

暂无评论

A Graph Structure-Feature Learning Network for Diagnosing Alzheimer’s Disease Based on Multi-modal Brain Biometric Feature 18th

A Graph Structure-Feature Learning Network for Diagnosing A...

引用

18th Chinese Conference on Biometric Recognition, CCBR 2024

作者： Shang, Dongxu Wang, Huabin Zhang, Mengxin Peng, Yuhang Ye, Xingjian Wang, Zilin Anhui Provincial International Joint Research Center for Advanced Technology in Medical Imaging School of Computer Science and Technology Anhui University Anhui Hefei China Stony Brook Institute at Anhui University Anhui Hefei China

ISBN: (纸本)9789819610709

Alzheimer’s Disease (AD) is a neurodegenerative disease, typically identified and diagnosed through brain biometric feature. However, certain common brain biometric feature exist among patients in different stages of AD, which result in incorrect edges within the graph structure. To address above issues, this paper proposes a Graph Structure-Feature Learning Network (GSFLN) model. The model simultaneously learns a graph structure that appropriately represents the relationships among patients and selects the significant pathogenic brain biometric feature of patients. Firstly, a Graph Convolutional Clustering (GCC) module is designed to capture the relationships between non-image data of patients. Secondly, a Pathogenic Feature Selection (PFS) module is designed to capture the relationships between image data of patients and select the pathogenic brain biometric feature. Thirdly, an Unsupervised Predictive Clustering (UPC) module is designed to control the above two modules. Our proposed model has surpassed the current state-of-the-art level in diagnostic performance on both the NACC and Tadpole datasets. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

关键词： Alzheimer’s Disease brain biometric feature Feature Selection Graph Convolutional Network Graph Structure Learning

来源：评论

学校读者我要写书评

暂无评论

Offensive Tweets Detection in Hinglish Using HingBERT 1

引用

International Conference on Data Analytics and Management, ICDAM 2023

作者： Jain, Lakshit Sharma, Moolchand Abdulsada, Zainab R. Department of Computer Science and Engineering MAIT GGSIPU Delhi India National University of Science and Technology Thi-Qar Iraq

ISBN: (数字)9789819965472

ISBN: (纸本)9789819965465

Social media is the perfect platform for people to interact, share news, and express their own thoughts. Unfortunately, there is a lot of negativity in it, including hate and abusive speech. People in multilingual nations like India frequently blend two or more languages to create hybrids. Hinglish is an example of a hybrid language that combines Hindi and English. This research concentrates on identifying offensive Hinglish-language tweets. Fine-tuning on HingBERT, HingMBERT, and HingRoBERTa has been done to improve upon the existing results. With a 0.95 F1-score, HingRoBERTa achieved benchmark results, while HingMBERT and HingBERT scored 0.93 and 0.93, respectively. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd 2024.

关键词： HingBERT Hinglish tweets HingMBERT HingRoBERTa HOT Offensive speech

来源：评论

学校读者我要写书评

暂无评论

Frequency Domain Feature Learning with Wavelet Transform for Image Translation 20th

Frequency Domain Feature Learning with Wavelet Transform fo...

引用

20th Pacific Rim International Conference on Artificial Intelligence, PRICAI 2023

作者： Zhao, Huan Wang, Yujiang Li, Tingting Wang, Song Li, Lixuan Zha, Xupeng Zhang, Zixing College of Computer Science and Electronic Engineering Hunan University Changsha China

ISBN: (纸本)9789819970247

Image-to-image translation serves as an essential field of research in computer vision. Existing models frequently cause accidental distortion over non-target attributes, leading to overfitting of the generated image to the reference domain and poor visual quality. To address this problem, we propose Frequency Domain Feature Learning with Wavelet Transform, namely FDFL-WT, which with better non-target attributes retention and more precise image capture of style. This method utilizes the wavelet transform to capture the image’s approximation coefficients and diagonal coefficients, then we suggest wavelet reconstruction loss and wavelet translation loss. The former comprehensively records the context information of the source image to make the generated image realistic, whereas the latter improves the generator’s capacity to decouple attributes by assisting the model in efficiently retaining image content attributes. Experimental results on CelebA-HQ dataset indicate that FDFL-WT achieves about a 7.03 % performance improvement comparing with methods in the FID score of realism and disentanglement tests. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd 2024.

关键词： Wavelet transforms

来源：评论

学校读者我要写书评

暂无评论

D’OH: Decoder-Only Random Hypernetworks for Implicit Neural Representations 17th

D’OH: Decoder-Only Random Hypernetworks for Implicit Neura...

引用

17th Asian Conference on computer Vision, ACCV 2024

作者： Gordon, Cameron E. MacDonald, Lachlan Saratchandran, Hemanth Lucey, Simon Australian Institute for Machine Learning University of Adelaide AdelaideSA5000 Australia Mathematical Institute for Data Science John Hopkins University BaltimoreMD21218 United States

ISBN: (纸本)9789819609628

Deep implicit functions have been found to be an effective tool for efficiently encoding all manner of natural signals. Their attractiveness stems from their ability to compactly represent signals with little to no offline training data. Instead, they leverage the implicit bias of deep networks to decouple hidden redundancies within the signal. In this paper, we explore the hypothesis that additional compression can be achieved by leveraging redundancies that exist between layers. We propose to use a novel runtime decoder-only hypernetwork – that uses no offline training data – to better exploit cross-layer parameter redundancy. Previous applications of hypernetworks with deep implicit functions have employed feed-forward encoder/decoder frameworks that rely on large offline datasets that do not generalize beyond the signals they were trained on. We instead present a strategy for the optimization of runtime deep implicit functions for single-instance signals through a Decoder-Only randomly projected Hypernetwork (D’OH). By directly changing the latent code dimension, we provide a natural way to vary the memory footprint of neural representations without the costly need for neural architecture search on a space of alternative low-rate structures. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

关键词： Decoding

来源：评论

学校读者我要写书评

暂无评论

没有更多数据了...

全选清除本页清除全部题录导出标记到“检索档案”

共500页 << < 118 119 120 121 122 123 124 125 126 127 > >>

检索报告对象比较合并检索0

隐藏清空

合并搜索

回到顶部

执行限定条件

内容：

评分：

请选择保存的检索档案：

请选择收藏分类：

订阅名称：

通借通还

温馨提示：

图书名称：

借书校区：

取书校区：

手机号码：

邮箱地址：

一卡通帐号：

电话和邮箱必须正确填写，我们会与您联系确认。

联系人：

所在院系：

联系邮箱：

联系电话：

内蒙古自治区呼和浩特市赛罕区大学西街235号邮编: 010021

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：