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

5,196 篇 期刊文献
4,316 篇 会议
28 册 图书

馆藏范围

9,540 篇 电子文献
0 种 纸本馆藏

日期分布

学科分类号

6,137 篇 工学
- 3,753 篇 计算机科学与技术...
- 3,066 篇 软件工程
- 1,397 篇 信息与通信工程
- 839 篇 控制科学与工程
- 744 篇 电子科学与技术（可...
- 741 篇 电气工程
- 564 篇 生物工程
- 537 篇 光学工程
- 511 篇 机械工程
- 408 篇 仪器科学与技术
- 346 篇 化学工程与技术
- 334 篇 生物医学工程（可授...
- 248 篇 动力工程及工程热...
- 201 篇 交通运输工程
- 194 篇 核科学与技术
- 170 篇 材料科学与工程（可...
- 154 篇 网络空间安全
- 150 篇 安全科学与工程
4,071 篇 理学
- 1,892 篇 物理学
- 1,664 篇 数学
- 630 篇 生物学
- 583 篇 统计学（可授理学、...
- 433 篇 化学
- 289 篇 系统科学
- 181 篇 地球物理学
1,407 篇 管理学
- 884 篇 管理科学与工程(可...
- 579 篇 图书情报与档案管...
- 319 篇 工商管理
294 篇 医学
- 249 篇 临床医学
- 201 篇 基础医学(可授医学...
183 篇 法学
105 篇 经济学
89 篇 农学
61 篇 教育学
31 篇 文学
24 篇 艺术学
16 篇 军事学
2 篇 历史学

主题

232 篇 feature extracti...
179 篇 deep learning
168 篇 training
167 篇 semantics
141 篇 computational mo...
122 篇 image segmentati...
113 篇 optimization
110 篇 accuracy
106 篇 hadron colliders
106 篇 machine learning
96 篇 hadrons
94 篇 face recognition
93 篇 object detection
89 篇 computer science
89 篇 predictive model...
83 篇 cloud computing
83 篇 bosons
82 篇 neural networks
82 篇 convolution
82 篇 data models

机构

1,431 篇 school of comput...
1,025 篇 cavendish labora...
845 篇 department of ph...
764 篇 oliver lodge lab...
763 篇 physikalisches i...
535 篇 fakultät physik ...
522 篇 department for p...
493 篇 infn sezione di ...
488 篇 university of ch...
479 篇 infn laboratori ...
474 篇 institute of phy...
469 篇 infn sezione di ...
467 篇 iccub universita...
450 篇 infn sezione di ...
444 篇 institute of phy...
441 篇 infn sezione di ...
441 篇 infn sezione di ...
432 篇 department of ph...
385 篇 department of ph...
385 篇 h.h. wills physi...

作者

276 篇 barter w.
269 篇 c. alexa
269 篇 c. amelung
267 篇 g. bella
267 篇 j. strandberg
267 篇 d. calvet
266 篇 j. m. izen
263 篇 brundu d.
261 篇 g. spigo
260 篇 f. siegert
249 篇 beiter a.
243 篇 blake t.
239 篇 y. tayalati
239 篇 bellee v.
239 篇 betancourt c.
238 篇 r. ströhmer
232 篇 m. rijssenbeek
232 篇 borsato m.
229 篇 s. jin
228 篇 g. gaudio

语言

7,747 篇 英文
1,650 篇 其他
158 篇 中文
1 篇 德文
1 篇 法文
1 篇 日文
1 篇 朝鲜文

检索条件"机构=School of Computer Science and Engineering Nanjing Univ. of Science and Technology"

共 9540 条记录，以下是221-230 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：

Spatial-Temporal Hierarchical Graph Convolutional Networks for Traffic Forecasting

Spatial-Temporal Hierarchical Graph Convolutional Networks f...

引用

2023 IEEE International Conference on Systems, Man, and Cybernetics, SMC 2023

作者： Qingyuan, Shao Hui, Yan Yuxin, Chen School of Computer Science and Engineering Nanjing University of Science and Technology Nanjing China

ISBN: (纸本)9798350337020

Traffic forecasting is a critical task in transportation planning and management, which requires modeling the complex spatial and temporal dependencies in traffic data. Most current methods employ Graph Convolutional Networks (GCN) to model spatial dependencies, and Recurrent Neural Networks (RNN) or Temporal Convolutional Networks (TCN) to model temporal dependencies. However, the representation ability of such methods is limited due to: 1) the conventional temporal extract models, such as RNN and TCN, suffer from limited flexibility, specifically, RNN can only capture temporal dependencies sequentially, while TCN is constrained by its multi-layer dilated convolution structure;2) spatial and temporal dependencies are intricately intertwined in the real world, but most methods fail to capture this spatial-temporal correlation resulting in sub-optimal performance. To this end, we propose the Spatial-Temporal Hierarchical Graph Convolutional Networks (STHGCN), in which we design Spatial-Temporal Hierarchical Graph (STHG) to simultaneously model spatial and temporal dependencies. Specifically, to model temporal dependencies more flexibly, we introduce two crucial components: the Local Temporal Transmission Matrix (LTTM) and the Multi-hop Temporal Similarity Matrix (MTSM). The LTTM captures adjacent temporal dependencies, while the MTSM captures multi-hop temporal dependencies. We further propose a Temporal Neighbor Fusion model that combines the LTTM and MTSM to obtain the adjacency matrix of STHG. Additionally, accounting for spatial-temporal correlation, we exploit the spatial GCN results as the STHG nodes which allows us to learn spatial and temporal dependencies simultaneously via the temporal GCN. Our experiments on four real-world datasets demonstrate that STHGCN outperforms the state-of-the-art methods for traffic forecasting. The code is available at https://***/sqy123qwer/STHGCN © 2023 IEEE.

关键词： graph convolutional network spatial-temporal data traffic forecasting

来源：评论

学校读者我要写书评

暂无评论

FedFC: An Efficient Personalized Federated Learning Method on Non-iid Data 29

FedFC: An Efficient Personalized Federated Learning Method o...

引用

29th IEEE International Conference on Parallel and Distributed Systems, ICPADS 2023

作者： Yang, Yuxin Wang, Yifei Huang, Chanying Li, Qianmu Xiao, Shan Nanjing University of Science and Technology School of Cyber Science and Engineering Nanjing China Nanjing University of Science & Technology School of Computer Science & Engineering Nanjing China Nanjing Univ. of Science & Technology School of Cyber Science & Engineering Nanjing China Fiberhome Communication Tech. Co. Fiberhome R & D Center Wuhan China

ISBN: (纸本)9798350330717

Federated Learning has been widely used due to its ability to train models while ensuring data privacy and security. However, the presence of non-i.i.d. (independent and identically distributed) data among different participating entities leads to significant performance disparities in Federated Learning. In addition, as the essence of Federated Learning involves model training on local devices without centralized data storage, it poses certain challenges in personalized tasks. Traditional centralized machine learning methods can perform deep learning and personalized model training on centralized data, while distributed data in Federated Learning may not provide enough information to support personalized requirements. In this paper, we propose a personalized Federated Learning method called FedFC, which adopts parameter decoupling to address the data domain shift issue in Federated Learning. We experimentally validate our proposed solutions on the OrganCMNIST and COVID-19 datasets. The experimental results show that compared to existing methods, FedFC achieves average accuracy improvements of 4.93% and 6.31% on the two datasets, respectively. Additionally, by employing partial gradient uploading, we successfully reduce the communication overhead by 22.67% and 26.91% for each dataset. © 2023 IEEE.

关键词： Efficiency Federated Learning Parameter Decoupling Personalization

来源：评论

学校读者我要写书评

暂无评论

Say No to the Poisonous Fungi: An Effective Strategy for Reducing 0-1 Cost in FungiCLEF2024 25

Say No to the Poisonous Fungi: An Effective Strategy for Red...

引用

25th Working Notes of the Conference and Labs of the Evaluation Forum, CLEF 2024

作者： Tan, Bao-Feng Li, Yang-Yang Wang, Peng Zhao, Lin Wei, Xiu-Shen School of Computer Science and Engineering Nanjing University of Science and Technology Nanjing China School of Computer Science and Engineering Key Laboratory of New Generation Artificial Intelligence Technology and Its Interdisciplinary Applications Southeast University Nanjing China

The FungiCLEF2024 competition endeavors to precisely identify fungi species leveraging both metadata and image analysis. Pivotal to the success of this competition are two crucial evaluation metrics: minimizing the error rate and the 0-1 cost loss resulting from misclassification. To reduce the identification error rate, we introduce a Dynamic MLP framework, drawing inspiration from [1]. This approach effectively integrates image and metadata embeddings through recursive blocks, utilizing matrix multiplication for deep fusion of information. To further address the issue of 0-1 cost, we devise a novel probability-based screening strategy, which initially consolidates poisonous fungi categories into a single class, then employs marginal expected loss and a threshold parameter α to optimize the recall rate for poisonous species. These approaches significantly reduce the error rate and 0-1 cost associated with misclassification and achieve a score of 0.5548 on the private leaderboard, securing the third-place ranking. The code is available at https://***/bftan1949/FungiCLEF2024. © 2024 Copyright for this paper by its authors.

关键词： 0-1 cost loss Fine-grained image recognition Fungi Species Identification Open-Set

来源：评论

学校读者我要写书评

暂无评论

Multibranch Co-training to Mine Venomous Feature Representation: A Solution to SnakeCLEF2024 25

Multibranch Co-training to Mine Venomous Feature Representat...

引用

25th Working Notes of the Conference and Labs of the Evaluation Forum, CLEF 2024

作者： Wang, Peng Li, Yangyang Tan, Bao-Feng Zhou, Yi-Chao Li, Yong Wei, Xiu-Shen School of Computer Science and Engineering Nanjing University of Science and Technology Nanjing China School of Computer Science and Engineering Key Laboratory of New Generation Artificial Intelligence Technology and Its Interdisciplinary Applications Southeast University Nanjing China

The SnakeCLEF2024 competition aims to develop an advanced algorithm capable of automatically identifying snake species from images. Accurate identification of snake species in snakebite cases can assist doctors in administering targeted antivenom, which is crucial for effective treatment. In this paper, we propose a multibranch co-training strategy based on Convolutional Neural Networks (CNNs) as the solution. During the training phase, our method consists of three branches which can be trained end-to-end. The first branch is used for the classification of all species and generates a gating coefficient. The second branch specifically focuses on venomous snakes, while the third branch concentrates on harmless species. The gating coefficient determines which of these branches will be utilized. During the inference phase, we only retain the first branch. Our solution significantly enhances the model's ability to distinguish between venomous and harmless snake species and achieve an accuracy of 69.83% and scored 83.57% on the track1 on the private leaderboard, which is the 1st place among all participants. The code is available at https://***/pengdadaaa/SnakeCLEF2024. © 2024 Copyright for this paper by its authors.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

A Deep Learning based Solution to FungiCLEF2023 24

A Deep Learning based Solution to FungiCLEF2023

引用

24th Working Notes of the Conference and Labs of the Evaluation Forum, CLEF-WN 2023

作者： Hu, Feiran Wang, Peng Li, Yangyang Duan, Chenlong Zhu, Zijian Li, Yong Wei, Xiu-Shen School of Computer Science and Engineering Nanjing University of Science and Technology Nanjing China

The FungiCLEF2023 competition intends to foster the development of advanced algorithms for fungi species identification through the analysis of images and metadata, thereby making notable contributions to biodiversity conservation and human health. To overcome the inherent challenges posed by this competition, this paper introduces a deep learning based approach to solving this problem, which is based on the VOLO [1] backbone architecture with rich data augmentation and the loss function addressing data imbalance issues. We also discuss methods for utilizing metadata to address the issue of open-set recognition under limited model capacity. Our method achieves 54.34% on private leaderboard, which is the third place among the participators. The code is available at https://***/xiaoxsparraw/ CLEF2023. © 2023 Copyright for this paper by its authors.

关键词： Metadata

来源：评论

学校读者我要写书评

暂无评论

EF2Net: Better Extracting, Fusing and Focusing Text Features for Scene Text Detection 4

EF2Net: Better Extracting, Fusing and Focusing Text Features...

引用

4th International Seminar on Artificial Intelligence, Networking and Information technology, AINIT 2023

作者： Qu, Xiangyang Zhang, Chongyang School of Computer Science and Engineering Nanjing University of Science and Technology Nanjing China

ISBN: (纸本)9798350314526

Text detection in natural scene images is a chal-lenging task that requires localization and fitting of text regions. Currently, existing natural scene methods use fixed-size convolutional kernels to extract text instance features and have achieved good results. However, due to the extremely large aspect ratio of text regions in natural scenes, extracting features using fixed-size convolutional kernels introduces background noise, which affects the accuracy of text detection. In addition, complex backgrounds in natural scenes may cause text features in existing methods to be incorrectly detected as text, while small and ambiguous text may be missed in the detection. To address these challenges, first, we use a new backbone with multi-branch depth band convolution to better capture text features in large aspect ratios and multi-scale backgrounds. Then, we propose a novel FPN that can obtain detailed information and scale sequence features to enhance the feature information of small texts. Finally, we design a dynamic text detection head that combines a text detection head with three attention mechanisms. We perceive from three dimensions: scale, space, and channel, enhance multi-scale text region features, focus on foreground targets, and accurately locate text regions, finally achieving the effect of reducing false and missed detections. In conclusion, the method proposed in this paper achieves good performance in text detection tasks in natural scenes and solves some problems in existing methods. Experimental results show that our proposed model achieves a comprehensive surpass compared with the text detection baseline. © 2023 IEEE.

关键词： Convolution

来源：评论

学校读者我要写书评

暂无评论

MM-ABR: an Enhanced ABR Algorithm with Multi-Metric Information for QUIC-based Video Streaming 29

MM-ABR: an Enhanced ABR Algorithm with Multi-Metric Informat...

引用

29th IEEE International Conference on Parallel and Distributed Systems, ICPADS 2023

作者： Cui, Changjiang Lu, Yifei Wang, Zhen Ruan, Zeqi Wang, Hongxiang Nanjing University of Science and Technology School of Computer Science and Engineering Nanjing China

ISBN: (纸本)9798350330717

DASH is becoming the unified adaptive bitrate (ABR) streaming open-source standard in video streaming. However, existing ABR algorithms lack accuracy and real-time performance in bandwidth estimation. Incorporating a wider range of information can enhance ABR algorithm performance. Positioned at the application layer, QUIC offers high scalability and can provide richer decision-making information for ABR algorithms. In this paper, we introduce an enhanced ABR algorithm enriched with multi-metric information, referred to as MM-ABR. MM-ABR surpasses the capabilities of existing ABR algorithms by additionally predicting network congestion, thereby improving the smoothness of video playback. To obtain the multi-metric information required for MM-ABR, we extend the implementation of the QUIC protocol, which allows us to integrate not only more accurate bandwidth data but also RTT and packet loss information into the DASH client application. We conduct simulations using NS-3 and compare MM-ABR with traditional ABR algorithms. The results demonstrate that MM-ABR offers higher video quality and Quality of Experience (QoE). © 2023 IEEE.

关键词： ABR DASH multi-metric QUIC video streaming

来源：评论

学校读者我要写书评

暂无评论

Progressive Neural Networks for Continuous Classification of Retinal Optical Coherence Tomography Images 11

Progressive Neural Networks for Continuous Classification of...

引用

11th International Conference on Advanced Cloud and Big Data, CBD 2023

作者： Wang, Di Huang, Kun Chen, Qiang Nanjing University of Science and Technology School of Computer Science and Engineering NanJing China

ISBN: (纸本)9798350345346

Deep learning models have demonstrated a great effectiveness on the classification of retinal lesions in optical coherence tomography images. However, the performance of these models deteriorates significantly when classifying images from different devices compared to the training data, which greatly limits their practicality. To address the issue of poor performance of the model in real-world applications, we propose a method of multi-granularity feature space constraint by studying samples from different devices as domain incremental tasks, to maintain the stability and plasticity of the model, thereby making the model having good generalization performance. Experimental results demonstrate that the proposed method effectively maintains performance on both new and old datasets. Compared to some state-of-the-art baselines focusing on natural images, the proposed method in this paper achieves higher average accuracy and lower forgetting rate on publicly available medical image datasets. © 2023 IEEE.

关键词： Image classification

来源：评论

学校读者我要写书评

暂无评论

Power and Latency Collaborative Optimizations of Object Detection CNN on Edge Devices under Limited Energy Budget 11

Power and Latency Collaborative Optimizations of Object Dete...

引用

11th International Conference on Advanced Cloud and Big Data, CBD 2023

作者： Huang, Zhiyi Wu, Zebin Zhou, Junlong Sun, Jin Nanjing University of Science and Technology School of Computer Science and Engineering Nanjing China

ISBN: (纸本)9798350345346

Real-time object detection with remote sensing technologies often requires drones and other battery-driven edge devices in situ to take images at high altitudes. In some cases, tasks are carried out where there exists no Internet access that is stable or reliable enough, making it impractical to transfer obtained data to a cloud server and have them processed there, especially during tasks that require real-time detection results. But processing remote sensing data on an edge device comes with many obstacles, with limited energy budget arguably being the biggest one of them. In this paper, we propose a method to adjust computational load on GPU and CPU on the fly when executing CNN inference, specifically that of YOLOX, on three common Nvidia MPSoC models, by making use of genetic algorithm to find an optimized deployment. We conducted extensive experiments to gather essential data and carried out simulations on the said device and observed uptime increase of up to over 158% compared to GPU-only deployment, with acceptable to no performance degradation and accurate detection results in line with the original implementation. In future work, we expect that it can be applied to more CNN-based models and algorithms, and with more adjustable variables to meet more various demands on diverse scenarios in the field of remote sensing. © 2023 IEEE.

关键词： Object detection

来源：评论

学校读者我要写书评

暂无评论

Automatic Check-out within Generalized Zero-shot Learning Setting 4

Automatic Check-out within Generalized Zero-shot Learning Se...

引用

4th International Symposium on computer engineering and Intelligent Communications, ISCEIC 2023

作者： Han, Yue Fu, Zhenyong Nanjing University of Science and Technology School of Computer Science and Engineering Nanjing China

ISBN: (纸本)9798350306323

Automatic Check-Out (ACO) aims to accurately forecast the presence and counts of each product in any given product combination. This paper concentrates on the ACO problem within generalized zero-shot Learning (GZSL) setting. Many recent GZSL studies have adopted a feature generation approach. However, these methods treat each class synthesis process independently, ignoring the rich dependency structure of different classes and their compositions. We propose a generative model that captures the common structure between classes and a classifier which optimizes classification boundaries by imposing a multi-class Deep SVDD constraint on seen classes. The evaluations are performed on the large-scale RPC dataset during the experiments. © 2023 IEEE.

关键词： Zero-shot 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 << < 19 20 21 22 23 24 25 26 27 28 > >>

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：