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

10,253 篇 会议
6,031 篇 期刊文献
140 册 图书

馆藏范围

16,424 篇 电子文献
0 种 纸本馆藏

日期分布

学科分类号

10,673 篇 工学
- 8,341 篇 计算机科学与技术...
- 6,834 篇 软件工程
- 2,207 篇 信息与通信工程
- 1,368 篇 控制科学与工程
- 1,127 篇 生物工程
- 877 篇 电气工程
- 736 篇 机械工程
- 659 篇 电子科学与技术（可...
- 606 篇 光学工程
- 606 篇 生物医学工程（可授...
- 391 篇 化学工程与技术
- 358 篇 仪器科学与技术
- 354 篇 安全科学与工程
- 322 篇 动力工程及工程热...
- 321 篇 交通运输工程
- 304 篇 网络空间安全
- 276 篇 建筑学
4,828 篇 理学
- 2,816 篇 数学
- 1,236 篇 生物学
- 956 篇 物理学
- 816 篇 统计学（可授理学、...
- 521 篇 系统科学
- 412 篇 化学
3,067 篇 管理学
- 1,857 篇 管理科学与工程(可...
- 1,332 篇 图书情报与档案管...
- 750 篇 工商管理
522 篇 医学
- 450 篇 临床医学
- 390 篇 基础医学(可授医学...
443 篇 法学
- 330 篇 社会学
276 篇 经济学
- 275 篇 应用经济学
236 篇 教育学
154 篇 农学
43 篇 军事学
42 篇 艺术学
39 篇 文学
9 篇 哲学
3 篇 历史学

主题

624 篇 computer science
481 篇 software enginee...
337 篇 semantics
318 篇 computational mo...
315 篇 feature extracti...
306 篇 deep learning
272 篇 training
224 篇 data mining
218 篇 optimization
214 篇 educational inst...
174 篇 predictive model...
172 篇 neural networks
170 篇 application soft...
167 篇 image segmentati...
157 篇 computer archite...
156 篇 machine learning
155 篇 internet of thin...
142 篇 authentication
137 篇 servers
136 篇 convolution

机构

428 篇 college of compu...
359 篇 school of comput...
267 篇 school of inform...
264 篇 school of comput...
221 篇 school of comput...
217 篇 school of comput...
187 篇 state key labora...
152 篇 school of softwa...
139 篇 school of electr...
134 篇 school of comput...
124 篇 national enginee...
109 篇 school of comput...
106 篇 school of softwa...
102 篇 school of softwa...
102 篇 state key labora...
99 篇 college of compu...
98 篇 college of compu...
96 篇 school of comput...
96 篇 school of softwa...
90 篇 school of softwa...

作者

69 篇 tao dacheng
52 篇 chen zhong
51 篇 liu yang
51 篇 zheng zibin
39 篇 wang ping
37 篇 hu ruimin
35 篇 huang di
34 篇 limin xiao
34 篇 wang yasha
34 篇 gao yang
32 篇 wang lei
32 篇 mian ajmal
31 篇 bo du
31 篇 miao huaikou
31 篇 ruimin hu
31 篇 qi lianyong
30 篇 jun zhang
28 篇 niyato dusit
28 篇 wang wei
27 篇 cui lizhen

语言

15,189 篇 英文
978 篇 其他
274 篇 中文
3 篇 日文
2 篇 朝鲜文
1 篇 德文
1 篇 斯洛文尼亚文

检索条件"机构=School of Computer Science& Software Engineering"

共 16424 条记录，以下是861-870 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：

Sentiment Analysis Scheme for Image-Text Comments based on Multimodal Deep Learning and Spatiotemporal Attention 6

Sentiment Analysis Scheme for Image-Text Comments based on M...

引用

6th International Conference on Mobile Computing and Sustainable Informatics, ICMCSI 2025

作者： Fanchang TangYaLing Yadav, Amit Sah, Abhishek Pratap Khan, Asif Department of Software Engineering Chengdu Neusoft University Chengdu China College of Engineering IT and Environment Charles Darwin University NT Australia School of Management Science and Engineering University of Electronic Science and Technology of China Chengdu China Department of Computer Application Integral University Lucknow India

ISBN: (纸本)9798331522667

A sentiment analysis scheme for image and text comments based on multimodal deep learning and spatiotemporal attention is proposed to address the issues of incomplete spatiotemporal considerations, incomplete implementation details, and cutting-edge theoretical algorithms in graphic and textual sentiment analysis schemes. The proposed model has clear layering including data preprocessing layer, modal encoding layer, modal fusion layer, sentiment classification layer, loss function and optimizer, evaluation and feedback. The implementation details of each layer are introduced. The entire scheme model incorporates Multimodal Fusion Neural Network (MFNN) deep learning and spatiotemporal attention mechanism, which makes the scheme perform well in terms of security, robustness and performance, making up for the shortcomings of existing research schemes. © 2025 IEEE.

关键词： Contrastive Learning

来源：评论

学校读者我要写书评

暂无评论

An Improved LVSL with View Consensus 25

An Improved LVSL with View Consensus

引用

Proceedings of the 2025 5th International Conference on Bioinformatics and Intelligent Computing

作者： Yuting Xu Qing Ai Bo Cui School of Computer Science and Software Engineering University of Science and Technology Liaoning Anshan China

ISBN: (纸本)9798400712203

In multi-view multi-label learning (MVML), each sample can be represented by multiple view features and associated with multiple labels. Most existing MVML algorithms are based on the assumption that all views share the same label set. However, in practice, different views may contain distinct label information, that means a single view cannot fully represent all labels. Based on this issue, the LVSL algorithm effectively learns view-specific labels and obtains superior classification performance. However, LVSL still has the limitation that it fails to consider the correlations between views, leading to suboptimal learning results. In this paper, we propose an improved LVSL algorithm named LVSL_VC (LVSL with view consensus). We incorporate view consensus learning into the original LVSL framework. Firstly, we employ view weights to model view consensus, assuming that views with similar weights will yield similar prediction outputs, conversely, they will be different. Secondly, we integrate the view consensus into the LVSL framework and construct a new classification model. Finally, we utilize an alternating optimization method to solve the problem. Extensive experimental results demonstrate that the LVSL_VC outperforms other state-of-the-art MVML algorithms.

关键词： Multi-view multi-label learning

来源：评论

学校读者我要写书评

暂无评论

When ControlNet Meets Inexplicit Masks: A Case Study of ControlNet on its Contour-following Ability 24

When ControlNet Meets Inexplicit Masks: A Case Study of Cont...

引用

32nd ACM International Conference on Multimedia, MM 2024

作者： Xuan, Wenjie Xu, Yufei Zhao, Shanshan Wang, Chaoyue Liu, Juhua Du, Bo Tao, Dacheng School of Computer Science National Engineering Research Center for Multimedia Software Wuhan University Wuhan China The University of Sydney Sydney Australia Nanyang Technological University Singapore Singapore

ISBN: (纸本)9798400706868

ControlNet excels at creating content that closely matches precise contours in user-provided masks. However, when these masks contain noise, as a frequent occurrence with non-expert users, the output would include unwanted artifacts. This paper first highlights the crucial role of controlling the impact of these inexplicit masks with diverse deterioration levels through in-depth analysis. Subsequently, to enhance controllability with inexplicit masks, an advanced Shape-aware ControlNet consisting of a deterioration estimator and a shape-prior modulation block is devised. The deterioration estimator assesses the deterioration factor of the provided masks. Then this factor is used in a modulation block to adaptively adjust the model's contour-following ability, which helps it dismiss the noise part in the inexplicit masks. Extensive experiments prove its effectiveness in encouraging ControlNet to interpret inaccurate spatial conditions robustly rather than blindly following the given contours, suitable for diverse kinds of conditions. We showcase application scenarios like modifying shape priors and composable shape-controllable generation. Codes are available at github. © 2024 ACM.

关键词： controlnet

来源：评论

学校读者我要写书评

暂无评论

Middle school Architect: Programmatic Modeling and Construction via a 3D Graphics Platform in Elm 2

Middle School Architect: Programmatic Modeling and Construct...

引用

2nd International Conference on Emerging Trends in Information Technology and engineering, ic-ETITE 2024

作者： Parcha, Anurag Mishra, Sanjana Anand, Christopher Kumar Pushparaj, Jagalingam Simon Fraser University BurnabyBC Canada McMaster University Computing and Software HamiltonON Canada School of Computer Science and Engineering Vellore Institute of Technology TN Vellore India

ISBN: (纸本)9798350328202

Today, school students are first introduced to geom-etry and advanced mathematical concepts by plotting a graph in 2D and they struggle with 3D concepts since current technologies are either too difficult to grasp or too simple with only drag-drop functionalities disconnected from coordinates. This article presents a 3D graphics library and an interactive, educational system for visualization of a 3D environment where planks of Cross Laminated Timber (CLT) can be manipulated by geometric and mathematical functions to produce a 3D building. Throughout, there is a focus on functions, 3D geometry and other underlying mathematics, and links are made with the world of computing, specifically computer graphics, to increase students' interest and confidence. Activities built on this library simultaneously meet multiple curricular objectives: mathematics (including 3D geometry), programming (in Elm, a web program-ming language used commercially), and sustainable development (using a negative embodied carbon building material). © 2024 IEEE.

关键词： Sustainable development

来源：评论

学校读者我要写书评

暂无评论

SP-Net: A Sparse Convolution and Point-Encoding Enhanced Network for 3D Object Detection in LiDAR Point Clouds

SP-Net: A Sparse Convolution and Point-Encoding Enhanced Net...

引用

2023 IEEE International Conference on Real-Time Computing and Robotics, RCAR 2023

作者： Liu, Meng Niu, Jianwei Liu, Yu China North Vehicle Research Institute Beijing100072 China Beihang University State Key Laboratory of Software Development Environment School of Computer Science and Engineering Beijing100191 China Beihang University School of Computer Science and Engineering Beijing100191 China

ISBN: (纸本)9798350327182

LiDAR 3D object detection for autonomous driving is an important issue. To address this issue, this paper provides a two-stage anchor-based solution. Firstly, voxel feature encoding and sparse convolution networks were employed for proposal generation. Secondly, we performed voxel feature aggregation and hierarchical feature learning in combination with the proposals, multi-level and multiscale voxel features, point encoding and voxel-wise ROI pooling. The aggregated object-wise voxel features were utilized to refine the proposals. Extensive experiments were conducted on three challenging datasets: KITTI, nuScenes and Waymo. Experimental results demonstrated that our SP-Net can effectively achieve multi-category 3D object detection in diverse scenarios offering satisfactory accuracy and speed (28.6 FPS). © 2023 IEEE.

关键词： Object detection

来源：评论

学校读者我要写书评

暂无评论

Time-Division Online Speculative Inference for Cost-Effective Intelligent Internet of Things 10

Time-Division Online Speculative Inference for Cost-Effectiv...

引用

10th IEEE World Forum on Internet of Things, WF-IoT 2024

作者： Du, Yao Wang, Zehua Leung, Cyril Leung, Victor C.M. The University of British Columbia Department of Electrical and Computer Engineering VancouverBCV6T 1Z4 Canada China University of Mining and Technology School of Computer Science and Technology Xuzhou221116 China Shenzhen University College of Computer Science and Software Engineering Shenzhen518060 China

ISBN: (纸本)9798350373011

Intelligent Internet of Things (IIoT), a network paradigm, is an interconnection of intelligent edge devices, empowered by machine learning models. The recent emergence of large language models (LLMs) opens a new path towards IIoT. Although device models are generally lightweight and suitable for edge devices with limited processing power, their performance is less impressive compared to LLMs running on large servers. Server models offer superior performance with the cost of significant computational resources for model inference. To realize cost-effective IIoT, we introduce a novel collaborative inference framework: the online speculative inference enabled by device collaboration and time divisions. We aim to find the minimum number of servers required for the immediate processing of arrived inference requests. To solve the problem, we propose an evolving directed acyclic graph along with a Proof-of-Deletion mechanism for cost reduction and privacy protection. Based on computer simulations using heterogeneous LLMs, it is found that time-division online speculative inference is a promising approach towards cost-effective IIoT. © 2024 IEEE.

关键词： Adversarial machine learning

来源：评论

学校读者我要写书评

暂无评论

Self-Driven Entropy Aggregation for Byzantine-Robust Heterogeneous Federated Learning 41

Self-Driven Entropy Aggregation for Byzantine-Robust Heterog...

引用

41st International Conference on Machine Learning, ICML 2024

作者： Huang, Wenke Shi, Zekun Ye, Mang Li, He Du, Bo National Engineering Research Center for Multimedia Software School of Computer Science Wuhan University Wuhan China Taikang Center for Life and Medical Sciences Wuhan University Wuhan China

Federated learning presents massive potential for privacy-friendly collaboration. However, federated learning is deeply threatened by byzantine attacks, where malicious clients deliberately upload crafted vicious updates. While various robust aggregations have been proposed to defend against such attacks, they are subject to certain assumptions: homogeneous private data and related proxy datasets. To address these limitations, we propose Self-Driven Entropy Aggregation (SDEA), which leverages the random public dataset to conduct Byzantine-robust aggregation in heterogeneous federated learning. For Byzantine attackers, we observe that benign ones typically present more confident (sharper) predictions than evils on the public dataset. Thus, we highlight benign clients by introducing learnable aggregation weight to minimize the instance-prediction entropy of the global model on the random public dataset. Besides, with inherent data heterogeneity, we reveal that it brings heterogeneous sharpness. Specifically, clients are optimized under distinct distribution and thus present fruitful predictive preferences. The learnable aggregation weight blindly allocates high attention to limited ones for sharper predictions, resulting in a biased global model. To alleviate this problem, we encourage the global model to offer diverse predictions via batch-prediction entropy maximization and conduct clustering to equally divide honest weights to accommodate different tendencies. This endows SDEA to detect Byzantine attackers in heterogeneous federated learning. Empirical results demonstrate the effectiveness. Copyright 2024 by the author(s)

关键词： Federated learning

来源：评论

学校读者我要写书评

暂无评论

InfoRM: Mitigating Reward Hacking in RLHF via Information-Theoretic Reward Modeling 38

InfoRM: Mitigating Reward Hacking in RLHF via Information-Th...

引用

38th Conference on Neural Information Processing Systems, NeurIPS 2024

作者： Miao, Yuchun Zhang, Sen Ding, Liang Bao, Rong Zhang, Lefei Tao, Dacheng National Engineering Research Center for Multimedia Software School of Computer Science Wuhan University China The University of Sydney Australia Fudan University China Nanyang Technological University Singapore

Despite the success of reinforcement learning from human feedback (RLHF) in aligning language models with human values, reward hacking, also termed reward overoptimization, remains a critical challenge. This issue primarily arises from reward misgeneralization, where reward models (RMs) compute reward using spurious features that are irrelevant to human preferences. In this work, we tackle this problem from an information-theoretic perspective and propose a framework for reward modeling, namely InfoRM, by introducing a variational information bottleneck objective to filter out irrelevant information. Notably, we further identify a correlation between overoptimization and outliers in the IB latent space of InfoRM, establishing it as a promising tool for detecting reward overoptimization. Inspired by this finding, we propose the Cluster Separation Index (CSI), which quantifies deviations in the IB latent space, as an indicator of reward overoptimization to facilitate the development of online mitigation strategies. Extensive experiments on a wide range of settings and RM scales (70M, 440M, 1.4B, and 7B) demonstrate the effectiveness of InfoRM. Further analyses reveal that InfoRM's overoptimization detection mechanism is not only effective but also robust across a broad range of datasets, signifying a notable advancement in the field of RLHF. Code is available at: https://***/miaoyuchun/InfoRM. © 2024 Neural information processing systems foundation. All rights reserved.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Bond Energy Assists Accurate Molecule Property Prediction

Bond Energy Assists Accurate Molecule Property Prediction

引用

2022 International Conference on Electrical, Electronics and Information engineering, EEIE 2022

作者： Yang, Xiaoting Du, Wenjie School of Computer Science and Technology University of Science and Technology of China China School of Software Engineering University of Science and Technology of China China

Molecule property prediction is a fundamental problem in many fields. To accurate and rapid prediction of molecules properties, molecule characterization and representation are key operations in the pretreatment stage. Generally, we represent molecule as graph based on different features such as element type, bond type, etc. The features we select could have the ability of enough representation and discrimination. However, in terms of bond embedding, one-hot coding is the most common processing method in the current research which means the features we used are discrete and could not distinguish different single or double bonds in a molecule. Here we add predicted bond energy feature as an extra chemical bond descriptor and compare three popular GNN models on two different datasets. The experiment shows that supplying additional unusual bond features - bond energy will improve the model performance significantly. The PDN model with bond energy has best performance among three model. Finally, we discuss the experimental result. © Published under licence by IOP Publishing Ltd.

关键词： Molecules

来源：评论

学校读者我要写书评

暂无评论

Surrogate-Assisted Flip for Evolutionary High-Dimensional Multiobjective Feature Selection 13

Surrogate-Assisted Flip for Evolutionary High-Dimensional Mu...

引用

13th IEEE Congress on Evolutionary Computation, CEC 2024

作者： Yang, Qi-Te Luo, Liu-Yue Chen, Chun-Hua Li, Jian-Yu Zhong, Jing-Hui Zhang, Jun Zhan, Zhi-Hui School of Computer Science and Engineering South China University of Technology Guangzhou510006 China School of Software Engineering South China University of Technology Guangzhou510006 China College of Artificial Intelligence Nankai University Tianjin300350 China

ISBN: (纸本)9798350308365

Feature selection (FS), which aims to minimize the classification error and the number of selected features, can essentially be modeled as a multiobjective optimization problem. To deal with such multiobjective FS (MOFS) problems, many multiobjective evolutionary algorithms (MOEAs) have been proposed. These MOEAs can find multiple optimal solutions, whereas substantial computational resources are required for fitness evaluations (FEs). More seriously, due to the high dimensionality and sparsity of FS problems, many FEs will be spent on unpromising solutions, resulting in a meaningless loss of computational resources. In this paper, two innovations are made so as to improve the performance of MOEAs for MOFS. First, we propose a surrogate-assisted flip (SF) strategy for MOEAs to reduce the FE waste on potentially unpromising solutions and improve search efficiency. This SF strategy is free of FE consumption and theoretically can be embedded in any MOEA to deal with MOFS problems. The experimental results show that this SF can improve the performance of different MOEAs, especially in reducing the number of selected features. Second, based on SF, we propose a more efficient SF -assisted MOEA for dealing with high-dimensional MOFS problems. The proposed algorithm divides the whole search space into different subspaces based on redundant feature subsets clustering to achieve parallel search, so as to reduce the search difficulty. The experimental results show that this algorithm is even more competitive than other SF -assisted MOEAs. © 2024 IEEE.

关键词： Optimization algorithms

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 << < 83 84 85 86 87 88 89 90 91 92 > >>

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：