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

15,887 篇 会议
363 篇 期刊文献
193 册 图书

馆藏范围

16,443 篇 电子文献
0 种 纸本馆藏

日期分布

学科分类号

8,341 篇 工学
- 5,433 篇 计算机科学与技术...
- 2,997 篇 软件工程
- 2,169 篇 电气工程
- 1,867 篇 信息与通信工程
- 1,130 篇 控制科学与工程
- 890 篇 光学工程
- 646 篇 机械工程
- 644 篇 电子科学与技术（可...
- 539 篇 仪器科学与技术
- 539 篇 生物医学工程（可授...
- 477 篇 生物工程
- 226 篇 测绘科学与技术
- 219 篇 交通运输工程
- 205 篇 材料科学与工程（可...
- 199 篇 航空宇航科学与技...
- 163 篇 化学工程与技术
- 160 篇 网络空间安全
- 141 篇 安全科学与工程
4,017 篇 理学
- 2,399 篇 物理学
- 1,363 篇 数学
- 527 篇 生物学
- 368 篇 统计学（可授理学、...
- 341 篇 系统科学
- 207 篇 化学
1,522 篇 医学
- 1,349 篇 临床医学
- 201 篇 特种医学
- 197 篇 基础医学(可授医学...
1,056 篇 管理学
- 614 篇 管理科学与工程(可...
- 482 篇 图书情报与档案管...
- 139 篇 工商管理
84 篇 法学
66 篇 农学
45 篇 经济学
43 篇 教育学
37 篇 军事学
32 篇 文学
26 篇 艺术学
1 篇 哲学

主题

2,783 篇 image processing
1,552 篇 image segmentati...
1,512 篇 signal processin...
867 篇 feature extracti...
658 篇 image edge detec...
635 篇 cameras
633 篇 signal processin...
612 篇 real-time system...
577 篇 image reconstruc...
517 篇 image coding
498 篇 algorithm design...
402 篇 deep learning
399 篇 clustering algor...
398 篇 image color anal...
384 篇 object detection
370 篇 image enhancemen...
362 篇 accuracy
334 篇 hardware
323 篇 image analysis
313 篇 computer vision

机构

40 篇 xi'an jiaotong u...
32 篇 northwestern pol...
31 篇 xi an jiao tong ...
31 篇 school of electr...
29 篇 school of electr...
26 篇 university of ch...
24 篇 xi an jiao tong ...
22 篇 xi an jiao tong ...
22 篇 national laborat...
21 篇 signal and image...
19 篇 samara national ...
18 篇 xidian universit...
16 篇 school of inform...
16 篇 institute of art...
15 篇 tsinghua univers...
15 篇 department of el...
15 篇 school of automa...
15 篇 national key lab...
15 篇 school of comput...
14 篇 school of electr...

作者

38 篇 chen xi
29 篇 xi chen
24 篇 nanning zheng
24 篇 licheng jiao
20 篇 li xi
20 篇 liu ying
18 篇 xuelong li
17 篇 anon
14 篇 xi ning
14 篇 wei li
14 篇 yuan yuan
13 篇 de-shuang huang
13 篇 yanning zhang
13 篇 xi li
12 篇 jie yang
12 篇 yang xi
12 篇 ying liu
11 篇 p. pirsch
11 篇 liu yang
11 篇 mingyi he

语言

16,016 篇 英文
282 篇 其他
135 篇 中文
20 篇 土耳其文
3 篇 葡萄牙文
2 篇 法文
2 篇 俄文
1 篇 西班牙文

检索条件"任意字段=Conference on Image Processing - Algorithms and Systems XI"

共 16443 条记录，以下是1231-1240 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：

Cross-modal Active Complementary Learning with Self-refining Correspondence 37

Cross-modal Active Complementary Learning with Self-refining...

引用

37th conference on Neural Information processing systems (NeurIPS)

作者： Qin, Yang Sun, Yuan Peng, Dezhong Zhou, Joey Tianyi Peng, xi Hu, Peng Sichuan Univ Coll Comp Sci Chengdu Peoples R China ASTAR Ctr Frontier AI Res CFAR Singapore Singapore ASTAR IHPC Singapore Singapore Chengdu Ruibei Yingte Informat Technol Co Ltd Chengdu Peoples R China Sichuan Zhiqian Technol Co Ltd Chengdu Peoples R China

ISBN: (纸本)9781713899921

Recently, image-text matching has attracted more and more attention from academia and industry, which is fundamental to understanding the latent correspondence across visual and textual modalities. However, most existing methods implicitly assume the training pairs are well-aligned while ignoring the ubiquitous annotation noise, a.k.a noisy correspondence (NC), thereby inevitably leading to a performance drop. Although some methods attempt to address such noise, they still face two challenging problems: excessive memorizing/overfitting and unreliable correction for NC, especially under high noise. To address the two problems, we propose a generalized Cross-modal Robust Complementary Learning framework (CRCL), which benefits from a novel Active Complementary Loss (ACL) and an efficient Self-refining Correspondence Correction (SCC) to improve the robustness of existing methods. Specifically, ACL exploits active and complementary learning losses to reduce the risk of providing erroneous supervision, leading to theoretically and experimentally demonstrated robustness against NC. SCC utilizes multiple self-refining processes with momentum correction to enlarge the receptive field for correcting correspondences, thereby alleviating error accumulation and achieving accurate and stable corrections. We carry out extensive experiments on three image-text benchmarks, i.e., Flickr30K, MS-COCO, and CC152K, to verify the superior robustness of our CRCL against synthetic and real-world noisy correspondences. Code is available at https://***/QinYang79/CRCL.

关键词： Refining

来源：评论

学校读者我要写书评

暂无评论

A Web-based Dicom image and Plane Viewer 5

A Web-based Dicom Image and Plane Viewer

引用

5th IEEE International conference on Electrical, Computer and Communication Technologies, ICECCT 2023

作者： Priya Darshini, B. Deepan Chakkaravarthy, N. Gokul, B. Sabari Maharaja, B. KPR Institute of Engineering and Technology Department of Biomedical Engineering Tamil Nadu Coimbatore India

ISBN: (纸本)9781665493604

Preclinical research, clinical diagnosis, and treatment can all benefit from the information that a medical image can offer. Due to the increased usage of digital medical imaging, numerous researchers are actively creating medical image processing algorithms and systems to provide the clinical community with improved results, such as accurate clinical parameters or processed images from the original images. We describe a Web-based DICOM reader in this work that was created solely using web technology, specifically Python, Streamlit, and Docker. When it comes to programming languages, Python has established itself as a competitor to MATLAB and Julia, two prominent scientific programming languages. In this work, we examine the potential of Python and Docker as co-implementers of the DICOM viewer. A demonstration field is available to new users, for learning purposes. Three different types of image planes namely axial, coronal, and sagittal are also available, which helps doctors readily detect cancers. Additionally, we can adjust the image plane's threshold levels to suit our needs. We also provide a JSON version of the website for use in forthcoming research initiatives. © 2023 IEEE.

关键词： Python

来源：评论

学校读者我要写书评

暂无评论

Employing Tensor Decomposition and Contextual Inference for Reducing the Semantic Discrepancy in image processing 2

Employing Tensor Decomposition and Contextual Inference for ...

引用

2nd IEEE International conference on Communication, Security and Artificial Intelligence, ICCSAI 2023

作者： Suneetha, K. Gupta, Namit University Karnataka Bangalore India College of Computing Science and Information Technology Teerthanker Mahaveer University Uttar Pradesh Moradabad India

ISBN: (纸本)9798350369960

Despite the growing need for effective image tagging in both commercial and research domains, the inconsistency between image content and text annotations remains a significant issue. We propose an innovative approach that leverages deep learning and tensor decomposition to enhance the quality of image labelling and eliminate the reliance on labor-intensive manual tagging. Our methodology transforms images into tensors, facilitating the formation of a standardized feature space. We employ a sophisticated five-layer neural network architecture that integrates three-level tensor decomposition to match images with their context groups accurately. This structure is adept at capturing the nuanced patterns in data, which is crucial for reducing the semantic discrepancy between visual and textual information. We have rigorously evaluated our algorithm using the Corel-10K dataset, focusing on the specific case of penguin images, to demonstrate the efficacy of our model. The results showcase a marked improvement in the relevance of generated tags, thereby enhancing the retrieval accuracy and mitigating the issue of inappropriate tag assignment. This work not only contributes to the fields of Machine Learning and Data Mining by refining feature extraction and context estimation techniques but also has significant implications for the development of NLP algorithms that can better interpret and generate descriptive tags for visual content. Moreover, our approach sets the stage for future explorations into the integration of AI-driven image tagging systems with robotic systems for autonomous data handling and organization. © 2023 IEEE.

关键词： Contextual Estimation image Understanding Techniques Semantic Gap Minimization Tensor-Based image Analysis Visual Data Interpretation

来源：评论

学校读者我要写书评

暂无评论

3D Positioning and Robot Assembly Method for Multi-plane Workpiece

3D Positioning and Robot Assembly Method for Multi-plane Wor...

引用

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

作者： Jia, Ruoyu Zhong, Kai Huang, Jintao Li, xi Li, Ruifeng Luo, Hua Li, Zhongwei Huazhong University of Science and Technology State Key Lab. of Materials Processing and Die and Mould School of Materials Science and Engineering Wuhan430074 China Xi'an Saineng Aerospace Automation Technology Co. Ltd. Xi'an710100 China

ISBN: (纸本)9798350327182

Aiming at the assembly of workpieces with multiple plane structures, this paper proposes a 3D visual positioning and robot assembly method. First, several planes are extracted by plane detection and outlier removal algorithms;then the poses of the plane point clouds are calculated by the oriented bounding box algorithm;finally, the target plane is found through the length and width constraints. Based on proper hand-eye calibration and motion planning, the method can achieve the workpieces' recognizing, positioning and assembly accurately, meanwhile has high computational efficiency and strong robustness. As shown in the experiment results, for the recognition and positioning accuracy, the translation error of the proposed method is less than 0.2mm, and the rotation error is less than 0.2°;for the robot assembly accuracy, the translation error of the proposed method is less than 0.8mm and the rotation error is less than 0.4°. Therefore, the proposed method can successfully satisfy the requirement of robot assembly tasks. © 2023 IEEE.

关键词： Robots

来源：评论

学校读者我要写书评

暂无评论

CIFAR-10 Dataset image Classification Using CNN 8th

CIFAR-10 Dataset Image Classification Using CNN

引用

8th International conference on Information System Design and Intelligent Applications, ISDIA 2024

作者： Sucharitha, M. Sesha Talpa Sai, P.H.V. Vijayagovindan, Sanjith Razmin, Fabina Ravindran, Byju Kiran Babu, Vadapalli V. S. Naveen Kumar, G.S. Bhaumik, Amiya School of Electronics Engineering VIT-AP University Amaravati India Malla Reddy College of Engineering and Technology Hyderabad India School of Information Technology Lincoln University College Petaling Jaya Malaysia Malla Reddy University Hyderabad India Lincoln University College Petaling Jaya Malaysia

ISBN: (纸本)9789819786657

image classification is an essential technology that is widely used in all aspects of human life. This work combined multiple image feature sources using deep learning algorithms to identify photos from the publicly available CIFAR10 image dataset. The same architecture, which consists of convolution modification and max-pooling of layers connected with several completely linked layers, is used to build most conventional convolutional neural networks (CNNs). This system consists of two steps: Pre-processing and Classification. The modified bilateral filtering method was employed in this study’s preprocessing steps. This study used convolutional neural network (CNN) architectures as suggested by the VGG-19 model to classify the CIFAR10 image dataset. The accuracy, precision, recall, and F1-score of the results are evaluated after simulating the suggested model. The testing results demonstrate that the proposed method reach a recall value of 96.4%, F1-score of 94.1%, accuracy of 97.3%, and maximum precision of 96.1%. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2024.

关键词： Wiener filtering

来源：评论

学校读者我要写书评

暂无评论

Neural Gas Counter Propagation Neural Network (NG CPNN): A Novel Model for Face Recognition

Neural Gas Counter Propagation Neural Network (NG CPNN): A N...

引用

2024 International conference on Science, Engineering and Business for Driving Sustainable Development Goals, SEB4SDG 2024

作者： Olagunju, Kazeem Michael Samuel Falohun, Adeleye Oke, Alice Oluwafunke Adebiyi, Marion O. Landmark University Directorate of Centre for Systems and Information Services Omu-Aran Nigeria LAUTECH Department of Computer Engineering Ogbomoso Nigeria Landmark University Department of Computer Science Omu-Aran Nigeria

ISBN: (纸本)9798350358155

The advent of biometric technology has enhanced security in various ways, especially by lowering the propensity for circumvention which was obtainable in traditional recognition measures such as the use of passwords, tokens, smart cards, PIN etc. Particularly facial recognition is currently a hot topic, which has evolved over time. A face recognition system is supposed to automatically recognize faces in pictures and videos by receiving a two-dimensional face image as input and comparing it to a predefined database of faces to outputs a discernible face image in the end. Despite the various algorithms used in face recognition, the problems of occlusion, light conditions and facial variation still persist. However, this study has implemented and presented Neural Gas Counter Propagation Neural Network (NG CPNN) as a novel model for face recognition *** implementation of model was carried out using 600 face images, pre-processed by histogram equalization, while face features were extracted by Principal Component Analysis. The novelty of NG CPNN was established by utilizing computational time, sensitivity, and accuracy as performance assessment measures at four distinct threshold values. The result shows computation time of 72.36s, accuracy of 96.25%, sensitivity of 98.33% at 0.8, 0.8, and 0.2 thresholds respectively. Finally, it was concluded based on empirical result and statistical evidence that NG-CPN is a novel model for face recognition. NG CPNN can be employed in access control systems, international borders, smartphone technology, and many more. © 2024 IEEE.

关键词： artificial intelligence biometrics face recognition image processing NG- CPNN pattern recognition

来源：评论

学校读者我要写书评

暂无评论

End-to-end Multi-source image Phase Retrieval 3

End-to-end Multi-source Image Phase Retrieval

引用

3rd IEEE International conference on Computer systems, ICCS 2023

作者： Zhao, Nan Song, Tianyang Guo, Yina Taiyuan University of Science and Technology Shanxi China

ISBN: (纸本)9798350313666

The phase information of multi-source hybrid images is prone to confusion during image propagation. Since traditional phase retrieval algorithms require a large number of assumptions that cannot be executed by obtaining amplitude, which makes phase retrieval of multi-source mixed images with phase distortion challenging. To address these phase retrieval problems, inspired by dual learning, we propose an end-to-end phase retrieval algorithm based on Multi-source image Phase Retrieval via dual Generative Adversarial Networks (MPRDGAN). By introducing the Least Square Error in the loss function of the network, the algorithm improves the performance of the model to prevent overfitting and ensures the phase retrieval of multi-source mixed images. Experimental results show that the MPRDGAN algorithm reduces the image restoration error, so that the correlation of restored images can reach more than 94.5%, which is widely used in various images such as face and remote sensing. © 2023 IEEE.

关键词： Generative adversarial networks

来源：评论

学校读者我要写书评

暂无评论

Target tracking algorithm based on multi-target features

Target tracking algorithm based on multi-target features

引用

Computer Vision, image and Deep Learning (CVIDL), International conference on

作者： Jiaxin Wang Wei Zhang Dan Wang xiangwei Kong Chinese Flight Test Establishment Institute of Measurement and Testing Technology Xi’an China

ISBN: (数字)9798350373820

ISBN: (纸本)9798350373837

Accurately tracking dynamic objects in video sequences is an ongoing challenge in target tracking tasks, especially in the face of occlusion, fast motion, and drastic changes in target scale and appearance. Although significant progress has been made in deep learning-based target tracking algorithms, these approaches often overlook the potential value of target history feature information in enhancing tracking stability and accuracy. To this end, we propose a novel target tracking framework that enhances the performance of the tracking algorithms by integrating both long-term and short-term historical feature information of the target into the tracking algorithms. This structure not only simplifies the processing flow, but also dramatically improves the operational efficiency through parallel processing mechanisms, enabling the algorithm to achieve fast and accurate target tracking in complex dynamic environments. Experimental results on several publicly available target tracking datasets show that our approach provides significant improvements in improving the accuracy and robustness of tracking compared to existing algorithms.

关键词： Computer vision Visualization Target tracking Accuracy Heuristic algorithms Video sequences Parallel processing

来源：评论

学校读者我要写书评

暂无评论

Application of Deep Learning Methods for Forest Fire Intelligent image processing 2nd

Application of Deep Learning Methods for Forest Fire Intelli...

引用

2nd International conference on Advances in Information and Communication Technology, ICTA 2023

作者： Long, Nguyen The Huong, Nguyen Thu G, Shmeleva Anna. Lien, Pham Thi Department of Informatics Institute of Cybersecurity and Digital Technologies MIREA – Russian Technological University Moscow119454 Russia Laboratory of Artificial Intelligence and Machine Learning Institute of Information Technology and Data Science Irkutsk National Research Technical University Irkutsk664074 Russia University of Information and Communication Technology Thai Nguyen University Thai Nguyen70000 Viet Nam

ISBN: (纸本)9783031495281

There are many challenges for a Deep Learning application project. Many problems need to be solved in an optimal way to improve the performance of the system. We can focus on a specific step or on the whole process. The aim of the work is to show a new way of using convolutional neural networks is proposed to image intelligent process. Due to the influence of climate change, natural disasters are becoming more complicated and have serious consequences. In particular, the phenomenon of forest fires is affected by factors such as humidity, temperature and vegetation characteristics, etc., so the detection and prediction of forest fires face many challenges. In this study, we focus on using image processing techniques and visual algorithms to preprocess data and filter noise, in order to create a complete database for training and testing model. Natural elements are also used in combination with object features (forest fire images) to build feature vectors. This study will allow to develop the technology and open up new opportunities for its subsequent application. © 2023, The Author(s), under exclusive license to Springer Nature Switzerland AG.

关键词： image processing

来源：评论

学校读者我要写书评

暂无评论

Research on garment image classification and detection algorithm based on improved deep learning 7

Research on garment image classification and detection algor...

引用

7th International conference on Intelligent Computing and Signal processing, ICSP 2022

作者： Ren, Fei Liu, Ye Gao, Pengfei Devaraj, Madhavi Zhang, Jiahui Li, Hongsheng Mapua University School of Information Technology Manila Philippines Nanjing Institute of Technology School of Automation Nanjing China

ISBN: (纸本)9781665478571

With the development of e-commerce economy, online shopping has become an indispensable part of people's life. Therefore, the study of clothing image classification is of great significance to realize the effective operation of online clothing change and clothing recommendation system. This paper uses two classical deep learning algorithms: LeNet and ResNet to construct the clothing image classification model and realize the classification and detection of. At the same time, on the basis of Yolov5, combined with ResNet to improve its backbone network and further improve the accuracy of clothing image classification and detection. Experiments show that on the FashionMnist dataset, the accuracy and precision of LeNet and ResNet are about 93%, the accuracy and precision of improved Yolov5 are more than 98%, which is much higher than the former. © 2022 IEEE.

关键词： Electronic commerce

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 << < 120 121 122 123 124 125 126 127 128 129 > >>

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：