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

107,731 篇 会议
15,604 册 图书
11,134 篇 期刊文献
5 篇 学位论文

馆藏范围

134,331 篇 电子文献
176 种 纸本馆藏

日期分布

学科分类号

106,596 篇 工学
- 92,327 篇 计算机科学与技术...
- 66,240 篇 软件工程
- 22,855 篇 信息与通信工程
- 12,397 篇 电气工程
- 8,177 篇 生物工程
- 8,157 篇 控制科学与工程
- 8,031 篇 生物医学工程（可授...
- 6,233 篇 光学工程
- 4,380 篇 电子科学与技术（可...
- 3,756 篇 机械工程
- 3,570 篇 化学工程与技术
- 2,753 篇 建筑学
- 2,307 篇 动力工程及工程热...
- 2,285 篇 土木工程
- 1,991 篇 安全科学与工程
55,336 篇 理学
- 40,807 篇 数学
- 9,521 篇 生物学
- 8,428 篇 物理学
- 7,763 篇 统计学（可授理学、...
- 4,799 篇 系统科学
- 3,118 篇 化学
22,099 篇 管理学
- 13,119 篇 图书情报与档案管...
- 9,975 篇 管理科学与工程(可...
- 6,902 篇 工商管理
5,675 篇 医学
- 5,222 篇 临床医学
- 4,499 篇 基础医学(可授医学...
- 3,132 篇 药学(可授医学、理...
3,671 篇 法学
- 3,114 篇 社会学
2,439 篇 教育学
- 2,397 篇 教育学
2,144 篇 经济学
- 2,138 篇 应用经济学
1,810 篇 农学
167 篇 军事学
108 篇 文学
51 篇 艺术学
15 篇 哲学
2 篇 历史学

主题

8,001 篇 artificial intel...
4,779 篇 computer communi...
3,519 篇 information syst...
2,775 篇 algorithm analys...
2,439 篇 software enginee...
2,001 篇 image processing...
1,972 篇 semantics
1,939 篇 computers
1,923 篇 information stor...
1,910 篇 user interfaces ...
1,590 篇 computer applica...
1,527 篇 pattern recognit...
1,470 篇 data mining and ...
1,435 篇 computer vision
1,403 篇 software enginee...
1,379 篇 database managem...
1,249 篇 distributed comp...
1,220 篇 theory of comput...
1,216 篇 computer circuit...
1,167 篇 computer systems...

机构

199 篇 university of sc...
153 篇 huazhong univers...
151 篇 department of co...
143 篇 institute of inf...
121 篇 department of co...
117 篇 tsinghua univers...
115 篇 shanghai jiao to...
112 篇 national institu...
95 篇 school of comput...
91 篇 chinese academy ...
85 篇 école des ponts ...
83 篇 department of co...
76 篇 karnataka bangal...
72 篇 department of co...
71 篇 college of compu...
71 篇 school of comput...
65 篇 university of el...
65 篇 university of ch...
64 篇 college of compu...
62 篇 school of comput...

作者

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

语言

130,977 篇 英文
1,668 篇 其他
1,497 篇 中文
327 篇 德文
4 篇 法文
1 篇 加泰罗尼亚文

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

共 134474 条记录，以下是4961-4970 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：

Binocular Vision and Vector-Summation Based Integration of Bilateral Innate and Learned Visual Cues in Insect Navigation 13th

Binocular Vision and Vector-Summation Based Integration of B...

引用

13th International Conference on Biomimetic and Biohybrid Systems, Living Machines 2024

作者： Sun, Qin Sun, Xuelong Li, Haiyang School of Mathematics and Information Science Guangzhou University Guangzhou China Machine Life and Intelligence Research Centre Guangzhou University Guangzhou China

ISBN: (纸本)9783031725968

Insects rely extensively on visual information for navigation, utilizing a combination of innate instincts and learned behaviors. The mushroom body (MB) has been identified as a key player in insect visual learning, with insects possessing bilateral MBs. However, the mechanisms underlying the interaction between the left and right MBs, and how innate and learned visual cues are integrated for accurate navigation, remain elusive. In this study, we employ a novel approach wherein visual models fusing MB and innate are initially provided with binocular (left and right) visual inputs, followed by the application of a bio-plausible vector-summation method to integrate binocular innate and learned (MB) visual guidance. We verify the efficacy of this integration method by reproducing recently published data from biologists, thus providing computational support for empirical findings. This research not only sheds light on the potential mechanism for integrating bilateral innate and learned visual cues in the insect brain but also offers insights that could inspire efficient solutions for information fusion in robotics. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2025.

关键词： Binocular vision

来源：评论

学校读者我要写书评

暂无评论

Contextual Bandit with Herding Effects: Algorithms and Recommendation Applications 21st

Contextual Bandit with Herding Effects: Algorithms and Rec...

引用

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

作者： Xu, Luyue Wang, Liming Xie, Hong Zhou, Mingqiang Chongqing University Chongqing China University of Science and Technology of China Hefei China State Key Laboratory of Cognitive Intelligence Beijing China

ISBN: (纸本)9789819601271

Contextual bandits serve as a fundamental algorithmic framework for optimizing recommendation decisions online. Though extensive attention has been paid to tailoring contextual bandits for recommendation applications, the "herding effects" in user feedback have been ignored. These herding effects bias user feedback toward historical ratings, breaking down the assumption of unbiased feedback inherent in contextual bandits. This paper develops a novel variant of the contextual bandit that is tailored to address the feedback bias caused by the herding effects. A user feedback model is formulated to capture this feedback bias. We design the TS-Conf (Thompson Sampling under Conformity) algorithm, which employs posterior sampling to balance the exploration and exploitation tradeoff. We prove an upper bound for the regret of the algorithm, revealing the impact of herding effects on learning speed. Extensive experiments on datasets demonstrate that TS-Conf outperforms four benchmark algorithms. Analysis reveals that TS-Conf effectively mitigates the negative impact of herding effects, resulting in faster learning and improved recommendation accuracy. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

关键词： contextual bandits herding effects recommendation

来源：评论

学校读者我要写书评

暂无评论

E-SAGE: Explainability-Based Defense Against Backdoor Attacks on Graph Neural Networks 18th

E-SAGE: Explainability-Based Defense Against Backdoor Attack...

引用

18th International Conference on Wireless Artificial Intelligent Computing Systems and Applications, WASA 2024

作者： Yuan, Dingqiang Xu, Xiaohua Yu, Lei Han, Tongchang Li, Rongchang Han, Meng University of Science and Technology of China Hefei230000 China Rensselaer Polytechnic Institute TroyNY12180 United States Zhejiang University Hangzhou310058 China

ISBN: (纸本)9783031714634

Graph Neural Networks (GNNs) have recently been widely adopted in multiple domains. Yet, they are notably vulnerable to adversarial and backdoor attacks. In particular, backdoor attacks based on subgraph insertion have been shown to be effective in graph classification tasks while being stealthy, successfully circumventing various existing defense methods. In this paper, we propose E-SAGE, a novel approach to defending GNN backdoor attacks based on explainability. We find that the malicious edges and benign edges have significant differences in the importance scores for explainability evaluation. Accordingly, E-SAGE adaptively applies an iterative edge pruning process on the graph based on the edge scores. Through extensive experiments, we demonstrate the effectiveness of E-SAGE against state-of-the-art graph backdoor attacks in different attack settings. In addition, we investigate the effectiveness of E-SAGE against adversarial attacks. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2025.

关键词： Generative adversarial networks

来源：评论

学校读者我要写书评

暂无评论

Learning Dynamic Representations in Large Language Models for Evolving Data Streams 27th

Learning Dynamic Representations in Large Language Models f...

引用

27th International Conference on Pattern Recognition, ICPR 2024

作者： Srivastava, Ashish Bhatnagar, Shalabh Narasimha Murty, M. Aravinda Raman, J. Indian Institute of Science Bangalore India Centre for AI & Robotics Bangalore India North Carolina State University RaleighNC United States

ISBN: (纸本)9783031781681

In the world of Large Language Modeling, incremental learning plays an important role in evolving data such as streaming text. We introduce an incremental learning approach for dynamic contextualized word embeddings in the setting of streaming data. We call the embeddings generated by our model as Incremental Dynamic Contextualized Word Embeddings (iDCWE). Our model introduces the incremental BERT (iBERT) (BERT stands for Bidirectional Encoder Representations from Transformers) to create a dynamic and incremental model to perform incremental training. Our model further captures the semantic drift of words using dynamic graphs. Our paper is the first in the line of research on (incremental) dynamic modeling of streaming text which we also refer to as Neural Dynamic Language Modeling. The performance of our model on the benchmark datasets is on par and even often out-performs the dynamic contextualized word embeddings which was the first paper to combine contextualization with dynamic word embeddings, to the best of our knowledge. Moreover, the compute time efficiency of our model is better than that of the aforementioned paper. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2025.

关键词： Modeling languages

来源：评论

学校读者我要写书评

暂无评论

Towards Adversarial Robustness and Reducing Uncertainty Bias through Expert Regularized Pseudo-Bidirectional Alignment in Transductive Zero Shot Learning 27th

Towards Adversarial Robustness and Reducing Uncertainty Bias...

引用

27th International Conference on Pattern Recognition, ICPR 2024

作者： Kumar Sinha, Abhishek Mishra, Deepak Moorthi, S. Manthira Signal and Image Processing Area Space Applications Center Ahmedabad India Indian Institute of Space Science and Technology Thiruvananthapuram India

ISBN: (纸本)9783031781827

Transductive zero-shot learning (TZSL) aims to minimize the domain shift between the learned and true distribution of the unseen classes by allowing access to the unpaired samples from unseen classes. While many distribution alignment based methods attempt to align both visual and semantic spaces to train the classifier, their performance is still limited by confirmation bias. Additionally, bidirectional alignment approaches are based on the strong assumption that the intrinsic dimensions of visual and semantic spaces are the same, which is rarely true. In this work, we first highlight the limitations of bidirectional alignment in terms of intrinsic dimensionality. We then present a pseudo-bidirectional approach that, without any underlying assumptions on these spaces, utilizes the learned visual-to-attribute mapping to minimize the distribution shift between learned and true unseen visual feature distributions. We further utilize an entangled loss between semantic and visual space to minimize the confirmation or uncertainty bias and improve the adversarial robustness. We, theoretically and empirically, show the performance gain in addition to the adversarial robustness under the proposed setting. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2025.

关键词： Adversarial machine learning

来源：评论

学校读者我要写书评

暂无评论

Dynamic Sharded Blockchain Architecture for Industrial Emergency Data Sharing 18th

Dynamic Sharded Blockchain Architecture for Industrial Emer...

引用

18th International Conference on Wireless Artificial Intelligent Computing Systems and Applications, WASA 2024

作者： Ren, Linjie Xu, Tianyi Guo, Runkun Wang, Cong Qiu, Tie College of Intelligence and Computing Tianjin University Tianjin300350 China Questrom School of Business Boston University BostonMA02215 United States School of Computer Qinghai Minzu University Xining810007 China

ISBN: (纸本)9783031714665

Sharding is a recognized solution for improving blockchain performance in industrial data sharing. Current sharding systems can periodically adjust shards to adapt to dynamic manufacturing scenarios, but they struggle to ensure low latency for emergency tasks that are massive, unpredictable, and time-sensitive because they cannot adjust shards at runtime. To address these problems, we present DSBA, a novel dynamic sharded blockchain architecture that enhances the performance of industrial emergency data sharing. Firstly, we propose a hierarchical architecture that segregates verification and consensus functions to prioritize time-sensitive emergency tasks while preserving the inherent concurrency of sharding. Secondly, we implement a dynamic sharding method based on reputation diffusion to select reliable endorsement nodes of high performance to construct shards, thereby ensuring efficient and secure emergency data sharing. Finally, we design an efficient micro-block synchronization mechanism to expedite the final consistency of emergency data. Through analysis and extensive experiments, DSBA achieves a 50% decrease in emergency transaction latency and reduces the failure rate to below 20% when compared to existing sharding systems. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2025.

关键词： Blockchain Dynamic Sharding Emergency Data Sharing Industrial Internet of Things(IIoT)

来源：评论

学校读者我要写书评

暂无评论

The Influence of Social Networking Usage Experience and Activity on Preferences of Explainable Artificial Intelligence (XAI) Representation Methods in a Hate Speech Detection System 25th

The Influence of Social Networking Usage Experience and Acti...

引用

25th International Conference on Web Information Systems Engineering, WISE 2024

作者： Al-Ansari, Noor Al-Thani, Dena Bahameish, Mariam College of Science and Engineering Hamad Bin Khalifa University Doha Qatar

ISBN: (纸本)9789819605668

Hate speech is widespread across social media platforms, where users can influence others positively or negatively through simple actions like typing. These platforms use AI to personalize content, and explainable AI (XAI) is integrated to clarify AI decision-making for users. While progress has been made in aligning XAI with user expectations through human-computer interaction (HCI) methods, the study of hate speech detection within XAI remains limited. This study investigated how social media experience and activity influence user preferences for XAI representation methods. Focusing on the Arab world, it introduces a high-fidelity prototype Arabic hate speech detection system and evaluates preferred XAI methods. Data were collected through subjective and objective measures, including Social Media Activity and Social Networking Usage Questionnaires on user preferences of XAI representation methods. The results show that active social media use correlates with social networking experience (SNUQpositive: r = .40, SNUQnegative = .23) and time spent on platforms (r = .22);however, mediation analysis found that hours spent did not influence XAI preference. Future research could explore additional factors affecting XAI preferences. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

关键词： Speech recognition

来源：评论

学校读者我要写书评

暂无评论

Micro-Expression Recognition via CNN and Multi-path Vision Transformer Integrated with Spatiotemporal Separated Self-attention 18th

Micro-Expression Recognition via CNN and Multi-path Vision T...

引用

18th Chinese Conference on Biometric Recognition, CCBR 2024

作者： Guo, Yingying Xie, Tingxuan Jia, Wenqiang Xu, Sen Ben, Xianye School of Information Science and Engineering Shandong University Qingdao266237 China School of Information Engineering Yancheng Institute of Technology Yancheng224051 China

ISBN: (纸本)9789819610709

Deep learning-based methods have exhibited outstanding performance in micro-expression recognition. However, convolutional operations are performed on fixed-size windows, which limits their ability to learn long-range relationships between different facial action units. To address this issue, we propose a novel Micro-Expression Recognition via CNN and Multi-Path Vision Transformer Integrated with Spatiotemporal Separated Self-Attention (CMVT). Among them, the combination of CNN and Vision Transformer is adopted to learn the local features and long-distance dependency of micro-expression facial action units. In addition, we use the motion magnification algorithm to amplify the motion amplitude of micro-expression apex frame for extracting more discriminative features. Experimental results on various datasets verify the effectiveness of the presented approach compared to the existing micro-expression methods. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

关键词： Deep learning

来源：评论

学校读者我要写书评

暂无评论

AdaSVaT: Adaptive Singular Value Thresholding for Adversarial Detection in Fundus Images 27th

AdaSVaT: Adaptive Singular Value Thresholding for Adversaria...

引用

27th International Conference on Pattern Recognition, ICPR 2024

作者： Joseph, Nirmal George, Sudhish N. Ameer, P.M. Raja, Kiran National Institute of Technology Calicut Kozhikode India Norwegian University of Science and Technology Trondheim Trondheim Norway

ISBN: (纸本)9783031783975

Existing detection methods for adversarial attacks in medical images mostly rely on prior knowledge about the attacks and the target models. This work introduces a new attack detector termed as AdaSVaT, that is both image and model agnostic, employing specific noise reduction technique through Adaptive Singular Value Thresholding (ASVT). The method exploits the significant impact of adversarial attacks on the lower singular values of an image. The AdaSVaT algorithm adaptively thresholds the singular values of the input image with the help of a linear regressor to generate a low-rank version of the same. Both the original and low-rank versions are experimented with the state-of-the-art classifiers. Adversarial examples are detected by examining the classification inconsistency between the input image and its low-rank version. Additionally, experimental results on three fundus image datasets (Kaggle EyePACS, IDRID and APTOS) prove the negligible loss of information from the images during reconstruction. The proposed method achieves improved adversarial detection accuracy with minimal computational burden while maintaining high structural similarity in both binary and multi-class classification tasks. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2025.

关键词： Adversarial machine learning

来源：评论

学校读者我要写书评

暂无评论

Back to Supervision: Boosting Word Boundary Detection Through Frame Classification 27th

Back to Supervision: Boosting Word Boundary Detection Throu...

引用

27th International Conference on Pattern Recognition, ICPR 2024

作者： Carnemolla, Simone Calcagno, Salvatore Palazzo, Simone Giordano, Daniela Department of Electrical Electronic and Computer Engineering University of Catania Via Santa Sofia Catania95123 Italy

ISBN: (纸本)9783031801358

Speech segmentation at both word and phoneme levels is crucial for various speech processing tasks. It significantly aids in extracting meaningful units from an utterance, thus enabling the generation of discrete elements. In this work we propose a model-agnostic framework to perform word boundary detection in a supervised manner also employing a labels augmentation technique and an output-frame selection strategy. We trained and tested on the Buckeye dataset and only tested on TIMIT one, using state-of-the-art encoder models, including pre-trained solutions (Wav2Vec 2.0 and HuBERT), as well as convolutional and convolutional recurrent networks. Our method, with the HuBERT encoder, surpasses the performance of other state-of-the-art architectures, whether trained in supervised or self-supervised settings on the same datasets. Specifically, we achieved F-values of 0.8427 on the Buckeye dataset and 0.7436 on the TIMIT dataset, along with R-values of 0.8489 and 0.7807, respectively. These results establish a new state-of-the-art for both datasets. Beyond the immediate task, our approach offers a robust and efficient preprocessing method for future research in audio tokenization. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2025.

关键词： Word processing

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 << < 491 492 493 494 495 496 497 498 499 500 > >>

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：