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

1,330 篇 会议
743 篇 期刊文献

馆藏范围

2,073 篇 电子文献
0 种 纸本馆藏

日期分布

学科分类号

1,329 篇 工学
- 784 篇 计算机科学与技术...
- 676 篇 软件工程
- 305 篇 控制科学与工程
- 265 篇 信息与通信工程
- 208 篇 生物工程
- 198 篇 生物医学工程（可授...
- 174 篇 电气工程
- 154 篇 机械工程
- 154 篇 光学工程
- 138 篇 电子科学与技术（可...
- 75 篇 化学工程与技术
- 66 篇 仪器科学与技术
- 54 篇 材料科学与工程（可...
- 39 篇 力学（可授工学、理...
- 32 篇 动力工程及工程热...
- 30 篇 土木工程
- 30 篇 交通运输工程
- 27 篇 航空宇航科学与技...
789 篇 理学
- 442 篇 数学
- 230 篇 生物学
- 207 篇 物理学
- 123 篇 统计学（可授理学、...
- 119 篇 系统科学
- 72 篇 化学
324 篇 管理学
- 195 篇 管理科学与工程(可...
- 137 篇 图书情报与档案管...
- 62 篇 工商管理
129 篇 医学
- 108 篇 临床医学
- 87 篇 基础医学(可授医学...
- 70 篇 药学(可授医学、理...
33 篇 法学
27 篇 农学
20 篇 经济学
19 篇 教育学
9 篇 艺术学
8 篇 文学
5 篇 军事学

主题

76 篇 feature extracti...
59 篇 training
51 篇 semantics
44 篇 image segmentati...
39 篇 computational mo...
37 篇 deep learning
37 篇 accuracy
33 篇 convolution
33 篇 machine learning
29 篇 object detection
29 篇 neural networks
29 篇 image processing
27 篇 support vector m...
26 篇 neurons
24 篇 intelligent cont...
23 篇 magnetic resonan...
23 篇 electroencephalo...
23 篇 mathematical mod...
23 篇 robustness
22 篇 laboratories

机构

79 篇 school of artifi...
69 篇 key laboratory o...
57 篇 guangxi key labo...
57 篇 school of automa...
52 篇 key laboratory o...
48 篇 key laboratory o...
48 篇 school of comput...
40 篇 key laboratory o...
40 篇 key laboratory o...
35 篇 key laboratory o...
33 篇 shaanxi key labo...
32 篇 shenzhen huazhon...
27 篇 shaanxi key labo...
26 篇 department of co...
25 篇 key laboratory o...
24 篇 alibaba group
24 篇 school of comput...
23 篇 school of comput...
23 篇 key laboratory o...
23 篇 guangxi key labo...

作者

64 篇 wu dongrui
61 篇 sang nong
50 篇 zeng zhigang
50 篇 gao changxin
46 篇 jiao licheng
44 篇 zhigang zeng
41 篇 jian huang
36 篇 pan linqiang
34 篇 huang jian
32 篇 yongji wang
32 篇 cao zhiguo
31 篇 licheng jiao
30 篇 hai-tao zhang
29 篇 wang yongji
28 篇 hamid soltanian-...
26 篇 housheng su
26 篇 wang zhongmin
25 篇 luo xiaonan
24 篇 su housheng
24 篇 wang xiang

语言

1,821 篇 英文
202 篇 其他
57 篇 中文

检索条件"机构=Key Laboratory of Intelligent Image Processing and Analysis"

共 2073 条记录，以下是11-20 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：

Attitude Detection Model Based on Improved High Resolution Network 13

Attitude Detection Model Based on Improved High Resolution N...

引用

13th International Conference on intelligent Control and Information processing, ICICIP 2025

作者： Shi, Dongliang Li, Yuhan Luo, Xiaonan Guangxi Key Laboratory of Image and Graphic Intelligent Processing Guilin University of Electronic Technology Guilin China

ISBN: (纸本)9798331516147

2D human posture detection, a challenging task in computer vision, aims to identify human body key points and is widely used. The HRNet model performs well in human key point detection. To enhance its effect in human posture detection and address suboptimal prediction accuracy in interactive occlusion, this paper combines HRNet and Transformer. The Transformer's attention mechanism handles complex image dependencies, and HRNet obtains image features. By embedding the Transformer's attention mechanism module into HRNet's backbone network and integrating a self-designed double-branch structure and convolutional attention module, an improved HRNet model is constructed. The DConvAttention module processes extracted features, and the convolutional attention mechanism balances image frequencies, enhancing processing and discrimination of complex backgrounds and occlusions and improving detection performance. In tests of complex and occluded images, the improved HRNet Local model has a 4.2M parameter increase, 0.5G FLOPs increase, and 1% mAP increase compared to HRNet, with the same recall rate. The improved HRNet Global model has 11M more parameters, 1.1G more FLOPs, a similar or slightly higher recall rate, and a 2% higher mAP value. © 2025 IEEE.

关键词： Face recognition

来源：评论

学校读者我要写书评

暂无评论

A Novel Self-Learning Network Integrating Contrastive Learning, Perceptual Learning and Masked image Modelling 15

A Novel Self-Learning Network Integrating Contrastive Learni...

引用

15th International Conference on Graphics and image processing, ICGIP 2023

作者： Chen, Yingxian Yang, Rui Lan, Rushi Guangxi Key Laboratory Image and Graphic Intelligent Processing Guilin University of Electronic Technology China

ISBN: (纸本)9781510675018

Unsupervised learning methods in computer vision have achieved remarkable success, exceeding the performance of supervised learning methods. It is noteworthy that current unsupervised learning methods share certain similarities, particularly in their data augmentation techniques. Masking, a type of data augmentation, can be utilized for both contrastive learning and masked image modelling. This paper presents a novel deep learning approach on visual unsupervised learning. It integrates previous methods such as contrastive learning, perceptual learning, self-distillation and masked image modelling. In our method, we treat the network that handles the original images as the teacher network, and the network that handles the masked images as the student network. The student network employs the representations extracted by the projection head for contrastive learning, while the features generated by the decoder are employed for masked image modeling. The process of self-knowledge distillation is facilitated by perceptual learning between the teacher and student networks. This model aligns with the main idea of contrastive learning, which aims to pull similar images closer while pushing dissimilar images further apart. Simultaneously, it reflects the main idea of masked image modelling, which enables the extraction of semantic information from large scale masked pixel reconstruction tasks. Additionally, we compare the effect of self-supervised methods to the performance of the model. Our results show that with only 75 epochs of fine-tuning, our 29M-parameter model achieves 78.5% top-1 accuracy on the imageNet-1k dataset. © 2024 SPIE. All rights reserved.

关键词： Unsupervised learning

来源：评论

学校读者我要写书评

暂无评论

Design of Dual-mode DPE Receiver Based on GPS L1/BDS B1C Signals

Design of Dual-mode DPE Receiver Based on GPS L1/BDS B1C Sig...

引用

2025 International Technical Meeting of The Institute of Navigation, ITM 2025

作者： Jia, Qiongqiong Guo, Qiqi Tianjin Key Laboratory of Intelligent Signal and Image Processing Civil Aviation University of China Tianjin300000 China

ISBN: (纸本)9780936406404

With the expanding applications of the Global Navigation Satellite System (GNSS), its operating environment has become increasingly complex, with challenges such as multipath effects, non-line-of-sight (NLOS) propagation, and signal attenuation caused by tall urban buildings and trees. This complexity poses additional challenges for traditional GNSS receivers. Direct Position Estimation (DPE) addresses some of the limitations of traditional receivers by accumulating signals from all visible satellites directly in the navigation domain. However, when severe obstructions result in a reduced number of visible satellites, DPE may fail to function properly. The introduction of multiconstellation satellite signals can help mitigate the issue of insufficient visible satellites in complex environments. Based on this, this paper designs a dual-mode DPE receiver utilizing Global Positioning System (GPS) L1 signals and BeiDou Navigation Satellite System (BDS) B1C signals. © 2025 Proceedings of the International Technical Meeting of The Institute of Navigation, ITM. All rights reserved.

关键词： Global positioning system

来源：评论

学校读者我要写书评

暂无评论

Improved LYT-Net image Enhancement Model for Underwater Robotics Vision 13

Improved LYT-Net Image Enhancement Model for Underwater Robo...

引用

13th International Conference on intelligent Control and Information processing, ICICIP 2025

作者： Li, Wenjie Luo, Xiaonan Guangxi Key Laboratory of Image and Graphic Intelligent Processing Güttin University of Electronic Technology Guilin China

ISBN: (纸本)9798331516147

—Although underwater robots can replace humans to explore the ocean which is rich in resources but fraught with unknown risks, there are phenomena such as monotonous colors, complex backgrounds and uneven illumination in the underwater environment, which makes it difficult for underwater robots relying on the optical vision system to obtain clear images and is not conducive to subsequent recognition and grasping tasks. In this paper, relevant preparatory work was carried out for underwater image processing applicable to underwater robots, and the underwater imaging model as well as other underwater image processing models were analyzed. Subsequently, a method combining the underwater physical model and the dark channel image was proposed to improve LYT-Net, enabling it to be applicable to mobile embedded devices such as underwater robots. After training and testing on the real datasets LSUI and UIEB, our model achieved good results on important indicators such as PSNR and SSIM. Meanwhile, it met the theoretical requirements of mobile devices in terms of FLOPs, Params and single-frame processing time, which verified its robustness and real-time processing ability in various underwater environments. © 2025 IEEE.

关键词： Underwater imaging

来源：评论

学校读者我要写书评

暂无评论

A High-Efficiency Doppler Frequency Parallel Acquisition Method Based on A-GPS

A High-Efficiency Doppler Frequency Parallel Acquisition Met...

引用

2025 International Technical Meeting of The Institute of Navigation, ITM 2025

作者： Jia, Qiongqiong Zhao, Yuchen China Civil Aviation University Tianjin Key Laboratory of Intelligent Signal and Image Processing Tianjin300000 China

ISBN: (纸本)9780936406404

Acquisition is a key step for Global Navigation Satellite System (GNSS) receivers to achieve positioning and other functions, and the acquisition speed directly affects the Time To First Fix (TTFF) of the receiver. The acquisition process typically involves generating local reference signals for all satellite signals and matching them with the received signals. For each satellite signal, this matching involves searching in the unknown Doppler frequency and code phase space. Traditional parallel acquisition methods can only perform parallel processing in either the Doppler frequency dimension or the code phase dimension, and still require linear search in the other dimension. To reduce the computational load and improve the acquisition efficiency, this paper proposes a high-efficiency parallel acquisition method based on A-GPS. This method utilizes the auxiliary information provided by the A-GPS base station to convert the linear search of visible star signals in Doppler frequency into a single parallel search in the Doppler search space, thereby reducing the computational load required for acquisition to 1/N of the conventional method, where N is the total number of frequency bands searched. The paper verifies through theoretical analysis and experimental results that the proposed method can significantly improve acquisition efficiency while ensuring acquisition performance. © 2025 Proceedings of the International Technical Meeting of The Institute of Navigation, ITM. All rights reserved.

关键词： Global positioning system

来源：评论

学校读者我要写书评

暂无评论

Geometric Algebra Based Kalman Filter Trajectory Prediction 3

Geometric Algebra Based Kalman Filter Trajectory Prediction

引用

3rd International Symposium on Aerospace Engineering and Systems, ISAES 2024

作者： Li, Taiyu Jiao, Weidong Civil Aviation University of China Tianjin Key Laboratory of Intelligent Signal and Image Processing Tianjin China

ISBN: (纸本)9798350350418

To improve the safety and efficiency of aviation operation, a Kalman filtered trajectory prediction algorithm based on geometric algebra is proposed in this space. Firstly, the Kalman filter equations for trajectory prediction in geometric algebraic space are given by taking position, velocity and acceleration as state variables and position, velocity and acceleration in a typical trajectory as observations. Secondly, the matrix operation in the geometric algebraic space is simplified to the matrix operation by establishing a composite geometric algebraic space. Then, the versor operator in the conformal geometric algebraic space is introduced into the Kalman filter, and the steps of geometric algebra-based Kalman filter trajectory prediction are given to improve the prediction rate and accuracy. The experimental results show that the proposed trajectory prediction algorithm has the highest accuracy and the operation efficiency is improved by 27.66% compared with the Kalman filter algorithm in Euclidean space and the DBSCAN clustering algorithm. © 2024 IEEE.

关键词： Trajectories

来源：评论

学校读者我要写书评

暂无评论

Facial Recognition-Based Classroom Attendance System Utilizing Deep Learning 1

Facial Recognition-Based Classroom Attendance System Utilizi...

引用

1st IEEE International Conference on Data Intelligence and Innovative Application, DIIA 2024

作者： Zhou, Cong Luo, Xiaonan Guilin University of Electronic Technology Guangxi Key Laboratory of Image and Graphic Intelligent Processing Guilin China

ISBN: (纸本)9798331504434

In recent years, artificial intelligence technologies, especially facial recognition, have made significant strides. With its high precision and efficiency, facial recognition has shown great potential and advantages in areas such as identity verification and behavior analysis. Classroom learning is the main channel through which students acquire knowledge, develop skills, and improve their competencies. A well-organized classroom attendance system is essential for ensuring the effective implementation and smooth execution of teaching plans. This system is based on an OpenCV and PyQt5 facial recognition client, utilizing the LBPH algorithm to achieve efficient facial recognition. In addition to providing a simple check-in function, the system offers a complete registration process and data management features. In practical use, students simply need to check in by facing the camera, allowing the system to automatically recognize the student's face and record the attendance data. This significantly simplifies the check-in process for both teachers and students, thereby improving classroom management efficiency. © 2024 IEEE.

关键词： Information management

来源：评论

学校读者我要写书评

暂无评论

Application of intelligent Schedule Management in Volunteer Service System 1

Application of Intelligent Schedule Management in Volunteer ...

引用

1st IEEE International Conference on Data Intelligence and Innovative Application, DIIA 2024

作者： Li, Yongxin Luo, Xiaonan Guilin University of Electronic Technology Guangxi Key Laboratory of Image and Graphic Intelligent Processing Guilin China

ISBN: (纸本)9798331504434

As the demand for volunteer services grows, enhancing the efficiency and management of these services has become a key issue. This paper explores methods of integrating intelligent scheduling management functions with volunteer service systems to optimize volunteer time management and task allocation. By analyzing existing volunteer service systems, we propose a novel system framework that integrates intelligent scheduling management. This framework updates volunteer schedules in real- time, automatically matches tasks with volunteers' time windows, and optimizes task distribution using smart algorithms. Experimental results show that volunteer service systems with integrated intelligent scheduling management significantly improve task allocation accuracy and volunteer satisfaction. This research provides new ideas and practical basis for the intelligent development of volunteer services. © 2024 IEEE.

关键词： Digital family digital platform volunteer service

来源：评论

学校读者我要写书评

暂无评论

Research on YOLOv8-Based Household Item Detection for Indoor Scenes 1

Research on YOLOv8-Based Household Item Detection for Indoor...

引用

1st IEEE International Conference on Data Intelligence and Innovative Application, DIIA 2024

作者： Wu, Jingwen Luo, Xiaonan Guilin University of Electronic Technology Guangxi Key Laboratory of Image and Graphic Intelligent Processing Guilin China

ISBN: (纸本)9798331504434

This research is driven by the growing need for efficient, scalable object detection in smart home applications with real-time performance and resource constraints. In this study, we utilize the YOLOv8 deep learning model for household item detection, focusing on its performance in real-time scenarios. We compare different versions of YOLOv8 - specifically, YOLOv8n, YOLOv8s, and YOLOv8m - using a preprocessed custom dataset. The results indicate that YOLOv8n stands out due to its lower parameter count and faster inference speed, making it ideal for real-time applications, even though it has slightly lower precision and recall. In contrast, while YOLOv8s and YOLOv8m show improvements in certain metrics, their higher computational demands limit their effectiveness in resource-constrained settings. Overall, YOLOv8n effectively balances speed and accuracy, offering a viable solution for household item detection. © 2024 IEEE.

关键词： Smart homes

来源：评论

学校读者我要写书评

暂无评论

An English Pronunciation Evaluation Model Based on Acoustic Phonetics Features 4

An English Pronunciation Evaluation Model Based on Acoustic ...

引用

4th International Conference on Computer Science and Blockchain, CCSB 2024

作者： Wang, Hongkang Guo, Qingkai Huang, Guimin Zhou, Ya Guilin University of Electronic Technology Guangxi Key Laboratory of Image and Graphic Intelligent Processing Guilin China

ISBN: (纸本)9798350356502

Oral English practice constitutes a crucial component of English language acquisition for non-native speakers;however, traditional classroom teaching methods are increasingly insufficient to address the diverse needs of learners. This paper enhances the evaluation of pronunciation quality within Computer-Assisted Language Learning (CALL) system. To assess the fluency of English learners' pronunciation, this paper introduces the innovative feature known as wordDurationRatio. Additionally, an intonation evaluation method utilizing dynamic time warping (DTW) algorithms is explored. Finally, this study incorporates support vector regression (SVR) algorithms to effectively fuse features, enhancing the assessment result of pronunciation quality. © 2024 IEEE.

关键词： Support vector regression

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208页 << < 1 2 3 4 5 6 7 8 9 10 > >>

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：