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

3,368 篇 会议
3,121 篇 期刊文献
34 册 图书

馆藏范围

6,523 篇 电子文献
0 种 纸本馆藏

日期分布

学科分类号

4,312 篇 工学
- 2,537 篇 计算机科学与技术...
- 2,057 篇 软件工程
- 851 篇 信息与通信工程
- 567 篇 控制科学与工程
- 514 篇 电气工程
- 442 篇 电子科学与技术（可...
- 414 篇 化学工程与技术
- 385 篇 生物工程
- 379 篇 机械工程
- 288 篇 动力工程及工程热...
- 286 篇 生物医学工程（可授...
- 264 篇 光学工程
- 258 篇 材料科学与工程（可...
- 199 篇 仪器科学与技术
- 150 篇 土木工程
- 130 篇 力学（可授工学、理...
- 125 篇 矿业工程
- 122 篇 建筑学
- 118 篇 安全科学与工程
2,630 篇 理学
- 1,270 篇 数学
- 928 篇 物理学
- 464 篇 生物学
- 360 篇 统计学（可授理学、...
- 359 篇 化学
- 258 篇 系统科学
1,057 篇 管理学
- 652 篇 管理科学与工程(可...
- 451 篇 图书情报与档案管...
- 262 篇 工商管理
255 篇 医学
- 216 篇 临床医学
- 190 篇 基础医学(可授医学...
118 篇 法学
103 篇 经济学
90 篇 教育学
84 篇 农学
18 篇 军事学
17 篇 文学
13 篇 艺术学
1 篇 历史学

主题

134 篇 feature extracti...
128 篇 computer science
103 篇 training
100 篇 accuracy
94 篇 computational mo...
86 篇 deep learning
78 篇 educational inst...
74 篇 data mining
69 篇 optimization
66 篇 neural networks
61 篇 image segmentati...
61 篇 machine learning
59 篇 algorithm design...
56 篇 face recognition
56 篇 monitoring
54 篇 hadrons
54 篇 clustering algor...
53 篇 robustness
52 篇 semantics
51 篇 wireless sensor ...

机构

338 篇 department of ph...
318 篇 school of comput...
281 篇 cavendish labora...
274 篇 iccub universita...
248 篇 horia hulubei na...
243 篇 h.h. wills physi...
243 篇 university of ch...
238 篇 infn sezione di ...
233 篇 van swinderen in...
232 篇 school of physic...
219 篇 yandex school of...
214 篇 massachusetts in...
210 篇 department of ph...
201 篇 infn sezione di ...
196 篇 oliver lodge lab...
195 篇 national researc...
195 篇 university of ci...
194 篇 national researc...
193 篇 warsaw
190 篇 university of ma...

作者

199 篇 barter w.
195 篇 brundu d.
195 篇 bellee v.
190 篇 beiter a.
177 篇 blake t.
173 篇 bowcock t.j.v.
171 篇 borsato m.
171 篇 betancourt c.
168 篇 amato s.
165 篇 boettcher t.
163 篇 casse g.
158 篇 baker s.
157 篇 baryshnikov f.
153 篇 byczynski w.
151 篇 bediaga i.
151 篇 bizzeti a.
147 篇 braun s.
147 篇 bencivenni g.
146 篇 borisyak m.
141 篇 bjørn m.

语言

5,809 篇 英文
536 篇 其他
177 篇 中文
2 篇 德文
2 篇 法文
1 篇 日文

检索条件"机构=School of Computer Science and Technology Henan Polytechnic University"

共 6523 条记录，以下是491-500 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：

QSVG: Quaternion Vision Graph Neural Network with Structure Inference for Texture Classification 16

QSVG: Quaternion Vision Graph Neural Network with Structure ...

引用

16th International Conference on Signal Processing Systems, ICSPS 2024

作者： Wen, Haiyuan Huang, Guoheng Cheng, Lianglun Liao, Xianglian Wu, Shiting Yuan, Xiaochen Zhong, Guo School of Computer Science and Technology Guangdong University of Technology Guangzhou510006 China Huizhou Boluo Power Supply Bureau Guangdong Power Grid Co. Ltd. Huizhou China Faculty of Applied Sciences Macao Polytechnic University China School of Information Science and Technology Guangdong University of Foreign Studies Guangzhou510006 China

ISBN: (纸本)9781510689251

In the realm of texture classification, while traditional approaches like Bag of Words (BoW) and Convolutional Neural Networks (CNNs) are commonly used, recent research highlights the remarkable flexibility offered by Graph Neural Networks (GNNs). Specifically, GNNs can effectively represent image blocks as one-dimensional multi-channel node features from three-dimensional data, interconnecting node feature channels. However, existing methods tend to process channels separately during graph convolution, overlooking critical inter-channel connections that are integral to capture intricate relationships between texture features, potentially limiting the effectiveness of GNNs in texture classification. Moreover, textures contain vital global information essential for classification performance, but GNNs tend to focus on information from similar neighboring nodes, which can restrict their capability to capture the global feature of the entire image during data processing. To address the aforementioned challenges, we propose a novel GNN architecture called Quaternion Structure inference Vision Graph neural network (QSVG) for texture classification, which combines quaternions and structure inference. Unlike previous approaches, QSVG comprises two key components: first, Quaternion Max-related convolution (Qmax), which uses the Hamilton transform to enhance node characterization by exploiting inter-channel connections;second, Structure Inference Block (SIF Block), which enriches node information through Bidirectional Gated Recurrent Unit (Bi-GRU)-based structure inference, fusing graph neural network node features with global features. Experimental results on three standard texture datasets demonstrate the competitive classification performance of our method. © 2025 SPIE.

关键词： Graph neural networks

来源：评论

学校读者我要写书评

暂无评论

TAGE: Trustworthy Attribute Group Editing for Stable Few-shot Image Generation 16

TAGE: Trustworthy Attribute Group Editing for Stable Few-sho...

引用

16th International Conference on Signal Processing Systems, ICSPS 2024

作者： Zhang, Ruicheng Huang, Guoheng Huo, Yejing Yuan, Xiaochen Zhou, Zhizhen Wu, Shiting Zhong, Guo School of Computer Science and Technology Guangdong University of Technology Guangzhou510006 China Faculty of Applied Sciences Macao Polytechnic University China Huizhou Boluo Power Supply Bureau Guangdong Power Grid Co. Ltd. 516001 China School of Information Science and Technology Guangdong University of Foreign Studies Guangzhou510006 China

ISBN: (纸本)9781510689251

Generative Adversarial Networks (GANs) have emerged as a prominent research focus for image editing tasks, leveraging the powerful image generation capabilities of the GAN framework to produce remarkable results. However, prevailing approaches are contingent upon extensive training datasets and explicit supervision, presenting a significant challenge in manipulating the diverse attributes of new image classes with limited sample availability. To surmount this hurdle, we introduce TAGE, an innovative image generation network comprising three integral modules: the Codebook Learning Module (CLM), the Code Prediction Module (CPM) and the Prompt-driven Semantic Module (PSM). The CPM module delves into the semantic dimensions of category-agnostic attributes, encapsulating them within a discrete codebook. This module is predicated on the concept that images are assemblages of attributes, and thus, by editing these category-independent attributes, it is theoretically possible to generate images from unseen categories. Subsequently, the CPM module facilitates naturalistic image editing by predicting indices of category-independent attribute vectors within the codebook. Additionally, the PSM module generates semantic cues that are seamlessly integrated into the Transformer architecture of the CPM, enhancing the model’s comprehension of the targeted attributes for editing. With these semantic cues, the model can generate images that accentuate desired attributes more prominently while maintaining the integrity of the original category, even with a limited number of samples. We have conducted extensive experiments utilizing the Animal Faces, Flowers, and VGGFaces datasets. The results of these experiments demonstrate that our proposed method not only achieves superior performance but also exhibits a high degree of stability when compared to other few-shot image generation techniques. © 2025 SPIE.

关键词： Image coding

来源：评论

学校读者我要写书评

暂无评论

System programming of a disease identification model based on medical images 16

System programming of a disease identification model based o...

引用

16th International Conference on Correlation Optics, COR 2023

作者： Hu, Zhengbing Uhryn, Dmytro Ushenko, Yurii Korolenko, Viktor Lytvyn, Vasyl Vysotska, Victoria School of Computer Science Hubei University of Technology Wuhan China Chernivtsi National University 2 Kotsiubynskyi Str. Chernivtsi58012 Ukraine Lviv Polytechnic National University Lviv79013 Ukraine

ISBN: (纸本)9781510671829

This study examined the problems associated with the registration and visualisation of medical images. Scientific computing in the field of medicine was carried out and an intelligent system was developed to identify diseases based on these images. An approach to detecting affected tissue areas in medical images was proposed. To achieve this goal, a neural network was used, which was trained to identify masks of affected areas. The masks were identified by annotation, where polygons with affected tissues were highlighted. The objects under study were classified by disease type. © COPYRIGHT SPIE. Downloading of the abstract is permitted for personal use only.

关键词： Machine learning

来源：评论

学校读者我要写书评

暂无评论

Adaptive Control Scheme for Clustering of Nodes Based on the Signs of Connections in Dynamical Signed Networks 19th

Adaptive Control Scheme for Clustering of Nodes Based on ...

引用

19th EAI International Conference on Heterogeneous Networking for Quality, Reliability, Security and Robustness, QShine 2023

作者： Wang, Qi Wang, Yinhe Gao, Zilin Gao, Peitao Xiong, Jianbin Cen, Jian Gao, Ying School of Automation Guangdong Polytechnic Normal University Guangzhou510665 China School of Automation Guangdong University of Technology Guangzhou510006 China College of Computer Science and Engineering Chongqing Three Gorges University Chongqing404020 China School of Electronics and Information Guangdong Polytechnic Normal University Guangzhou510665 China Guangzhou Intelligent Building Equipment Information Integration and Control Key Laboratory Guangzhou510665 China School of Computer Science and Engineering South China University of Technology Guagnzhou510641 China

ISBN: (纸本)9783031651229

The concept of clustering has garnered significant attention within the field of complex networks. Numerous clustering algorithms have been documented in the extant academic literature. However, most of them consider static signed networks, which are not suitable for dynamical networks. For dynamical signed networks, there is a class of algorithms called cluster dynamics. Nevertheless, they regard the connection to be time-invariant, which is a constraint. In this paper, for a kind of dynamical signed networks with time-varying connections, we discuss the adaptive control scheme for clustering of nodes, such that the network evolves asymptotically into a classifiable network that contains several friends’ groups with clear sign boundaries. In other words, through the careful design of the controller for the nodes and the establishment of coupling relationships between the nodes and their connections, we ensure that the connection of the dynamical signed network can approximate asymptotically the connection of a given classifiable network, as measured by the concept of uniformly ultimately bounded (UUB). Finally, the simulation is used to illustrate the validity of the method proposed in this paper. © ICST Institute for computer sciences, Social Informatics and Telecommunications Engineering 2024.

关键词： Adaptive control Classifiable networks Multi-clustering

来源：评论

学校读者我要写书评

暂无评论

An Adaptive Multiform Evolutionary Algorithm for Global Continuous Optimization

An Adaptive Multiform Evolutionary Algorithm for Global Cont...

引用

2023 IEEE Symposium Series on Computational Intelligence, SSCI 2023

作者： Ling, Hongtao Zhong, Jinghui Dong, Junlan Wang, Shanxia Wang, Shibin Zhang, Qin School of Computer Science and Engineering South China University of Technology Guangzhou510006 China Henan Normal University Xinxiang China Communication University of China Beijing China

ISBN: (纸本)9781665430654

Evolutionary algorithm(EA) with knowledge trans-fer is an emerging research topic that has attracted a lot of attention in the EA community. The multiform evolutionary algorithm is a promising algorithm framework concept falling in this direction, but little work has been done so far to design and discuss this new EA framework. In this paper, we proposed an adaptive multiform evolutionary framework, which integrates the idea of transfer optimization and population-based evolutionary algorithms. The main idea is to utilize multiple equivalent or similar formulations to solve the given problem cooperatively. By adaptively adjusting computational resources of different formulations and transferring knowledge among formulations, the search efficiency and the population diversity can be improved. Furthermore, a new multiform algorithm is implemented based on the proposed framework, which utilizes two different coordinate systems, namely the Cartesian and polar coordinate systems, to model the given problem. To test the effectiveness of the proposed algorithm, we conducted numerical experiments on CEC2013 benchmark test functions, and the experimental results have verified the efficacy of the proposed algorithm. © 2023 IEEE.

关键词： Continuous Optimization DE Multiform Optimization

来源：评论

学校读者我要写书评

暂无评论

Predicting and Analyzing IoT Performance Based on Improved Resnet

Predicting and Analyzing IoT Performance Based on Improved R...

引用

On-Line Conference (ONCON), Industrial Electronics Society Annual

作者： Jianchun Zhang Wenpeng Liu College of Computer Science and Technology Henan Polytechnic University Jiaozuo China

With the increasing maturity of smart communication technologies and the rapid popularization of mobile IoT devices, technological development has gradually stepped into the world of the Internet of Everything, and the mobile Internet of Things (IoT) is booming, resulting in numerous applications of great significance. The complex and changing environment of mobile communication requires that mobile IoT applications can en-sure reliable delivery, more agile and accurate performance pre-diction methods are required. Outage probability (OP) is an important metric if one wants to evaluate the performance of mobile IoT networks. In this paper, we investigate the OP performance of mobile IoT communication networks based on an improved deep residual network (Resnet) and propose an prediction algorithm for OP based on the improved net-work. We first study the mobile OP performance and derive the accurate OP expression under a specific channel. Then, an improved residual network is designed to improve the prediction accuracy, the pooling layer of network is removed due to the characteristics of mobile communication data. The pro-posed prediction method based on improved residual network is compared with traditional convolutional neural network (CNN), generalized regression (GR) and radial basis function (RBF) methods. The simulation results verify that the proposed improved residual network prediction method can obtain better prediction results than the above traditional methods. The prediction accuracy of the Resnet method is improved by 44%.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Multi-Scale Residual Attention Network for Image Super-Resolution

Multi-Scale Residual Attention Network for Image Super-Resol...

引用

Telecommunications, Electronics and Informatics (ICTEI), International Conference on

作者： Shuiping Ni Shijie Wang Huifang Li Pengkun Li College of Computer Science and Technology Henan Polytechnic University Jiaozuo China

ISBN: (数字)9798350342963

ISBN: (纸本)9798350342970

Single image super-resolution (SISR) reconstruction algorithms mostly use a single scale convolution kernel to extract the features of low-resolution images, which will easily cause a large number of details loss. Usually, the depth of the model network is increased to achieve better image reconstruction effect. With the increase of the depth of the network, the model gradient disappears, and increase network parameters, making the training difficult. A multi-scale residual attention model is proposed to achieve single image super-resolution reconstruction. The model consists of shallow feature extraction, multi-scale residual attention network and reconstruction. The convolution kernels of different scales are used for feature extraction of low-resolution image convolution. Residual attention network can eliminate gradient disappearance and network degradation. Adding attention mechanism in residual network can make the high-frequency region characteristics of network channel get more attention, and enhance the texture and detail information of reconstructed image.

关键词： Training Attention mechanisms Convolution Superresolution Reconstruction algorithms Feature extraction Telecommunications

来源：评论

学校读者我要写书评

暂无评论

DNTextSpotter: Arbitrary-Shaped Scene Text Spotting via Improved Denoising Training 24

DNTextSpotter: Arbitrary-Shaped Scene Text Spotting via Impr...

引用

32nd ACM International Conference on Multimedia, MM 2024

作者： Qiao, Qian Xie, Yu Gao, Jun Wu, Tianxiang Huang, Shaoyao Fan, Jiaqing Cao, Ziqiang Wang, Zili Zhang, Yue School of Computer Science and Technology Soochow University Suzhou China Bilibili Inc. China The Hong Kong Polytechnic University Hong Kong Hong Kong Inf Tech Shanghai China

ISBN: (纸本)9798400706868

More and more end-to-end text spotting methods based on Transformer architecture have demonstrated superior performance. These methods utilize a bipartite graph matching algorithm to perform one-to-one optimal matching between predicted objects and actual objects. However, the instability of bipartite graph matching can lead to inconsistent optimization targets, thereby affecting the training performance of the model. Existing literature applies denoising training to solve the problem of bipartite graph matching instability in object detection tasks. Unfortunately, this denoising training method cannot be directly applied to text spotting tasks, as these tasks need to perform irregular shape detection tasks and more complex text recognition tasks than classification. To address this issue, we propose a novel denoising training method (DNTextSpotter) for arbitrary-shaped text spotting. Specifically, we decompose the queries of the denoising part into noised positional and noised content queries. We use the four Bezier control points of the Bezier center curve to generate the noised positional queries. For the noised content queries, considering that the output of the text in a fixed positional order is not conducive to aligning position with content, we employ a masked character sliding method to initialize noised content queries, thereby assisting in the alignment of text content and position. Additionally, to improve the model's perception of the background, we further utilize an additional loss function for background characters classification in the denoising training part. DNTextSpotter outperforms state-of-the-art methods on four benchmarks-Total-Text, SCUT-CTW1500, ICDAR15, and Inverse-Text-most notably achieving an 11.3% improvement over the best approach on Inverse-Text. © 2024 ACM.

关键词： Inverse problems

来源：评论

学校读者我要写书评

暂无评论

EEG-based Emotion Recognition using Graph Attention Network with Dual-Branch Attention Module 46

EEG-based Emotion Recognition using Graph Attention Network ...

引用

46th Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBC 2024

作者： Li, Cheng Pun, Sio Hang Li, Jia Wen Chen, Fei University of Macau State Key Laboratory of Analog and Mixed-Signal Vlsi China Southern University of Science and Technology Department of Electrical and Electronic Engineering Shenzhen China Guangdong Polytechnic Normal University School of Computer Science Guangzhou China

ISBN: (纸本)9798350371499

EEG reveals human brain activities for emotion and becomes an important aspect of affective computing. In this study, we developed a novel approach, namely DAM-GAT, which incorporated a dual-branch attention module (DAM) into a graph attention network (GAT) for EEG-based emotion recognition. This method used the GAT to capture the local features of emotional EEG signals. To enhance the important EEG features for emotion recognition, the proposed method also included a DAM that calculated weights considering both channel and frequency information. Additionally, the relationship between EEG channels was determined using the phase-locking value (PLV) connectivity of corresponding EEG signals. Based on the SEED datasets, the proposed approach provided an accuracy of up to 94.63% for emotion recognition, demonstrating its impressive performance compared with other existing methods. © 2024 IEEE.

关键词： Emotion Recognition

来源：评论

学校读者我要写书评

暂无评论

MIN: Multi-stage Interactive Network for Multimodal Recommendation 25th

MIN: Multi-stage Interactive Network for Multimodal Recomme...

引用

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

作者： Mo, Minghao Lu, Weihai Xie, Qixiao Lv, Xiang Xiao, Zikai Yang, Hong Zhang, Yanchun Cyberspace Institute of Advanced Technology Guangzhou University Guangzhou China School of Computer Science and Technology Zhejiang Normal University Zhejiang China Peking University Beijing China Department of Industrial and Systems Engineering The Hong Kong Polytechnic University Hung Hom China

ISBN: (纸本)9789819605699

With the surge in multimedia applications and the explosion of multimedia information, multimodal recommendation has garnered increasing attention. The core idea of multimodal recommendation is to effectively utilize the multimodal information of items to enhance the performance of recommendation systems. Previous work has primarily focused on integrating item ID embeddings and multimodal representations. However, there are two main drawbacks: first, a lack of interaction between multimodal features, which neglects the inherent semantic relationships within these features. Second, the distribution gap between ID embeddings and multimodal representations adversely affects recommendation performance. In this paper, we propose a novel Multi-stage Interactive Network for multimodal recommendation, named MIN. Specifically, we first discarded the ID embeddings, retaining only the multimodal features to represent the items. Then, we designed a three-stage interaction network to model the multimodal representations and the latent structural semantics between users and items. Additionally, to obtain more general and robust representations, we applied graph enhancement techniques in the final stage to enhance the representations of users and items. Finally, contrastive learning techniques were employed to address the inconsistency in user and item representations. A series of comprehensive experiments on three publicly available datasets have validated the efficacy of our method. © 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

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 << < 46 47 48 49 50 51 52 53 54 55 > >>

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：