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

4,746 篇 会议
12 篇 期刊文献

馆藏范围

4,758 篇 电子文献
0 种 纸本馆藏

日期分布

学科分类号

3,155 篇 工学
- 2,813 篇 计算机科学与技术...
- 2,227 篇 软件工程
- 1,264 篇 信息与通信工程
- 759 篇 控制科学与工程
- 691 篇 生物工程
- 668 篇 光学工程
- 530 篇 电气工程
- 454 篇 生物医学工程（可授...
- 419 篇 电子科学与技术（可...
- 299 篇 网络空间安全
- 182 篇 安全科学与工程
- 163 篇 机械工程
- 160 篇 仪器科学与技术
- 159 篇 交通运输工程
- 152 篇 动力工程及工程热...
- 152 篇 化学工程与技术
- 142 篇 石油与天然气工程
1,643 篇 理学
- 709 篇 生物学
- 637 篇 物理学
- 604 篇 数学
- 242 篇 化学
- 180 篇 统计学（可授理学、...
827 篇 管理学
- 463 篇 图书情报与档案管...
- 443 篇 管理科学与工程(可...
- 119 篇 工商管理
434 篇 医学
- 364 篇 临床医学
- 247 篇 基础医学(可授医学...
- 214 篇 药学(可授医学、理...
- 106 篇 公共卫生与预防医...
125 篇 法学
- 109 篇 社会学
95 篇 农学
45 篇 经济学
44 篇 文学
33 篇 教育学
12 篇 军事学

主题

320 篇 image processing
312 篇 deep learning
231 篇 image segmentati...
191 篇 signal processin...
172 篇 image classifica...
167 篇 image enhancemen...
162 篇 computer vision
140 篇 image recognitio...
138 篇 convolutional ne...
136 篇 feature extracti...
125 篇 training
108 篇 machine learning
83 篇 neural networks
83 篇 computational mo...
79 篇 visualization
78 篇 object detection
71 篇 natural language...
69 篇 semantics
66 篇 accuracy
65 篇 acoustics

机构

24 篇 chitkara univers...
17 篇 maharishi school...
15 篇 lovely professio...
15 篇 tianjin universi...
13 篇 university of ch...
12 篇 the islamic univ...
11 篇 school of comput...
11 篇 centre of interd...
10 篇 peng cheng labor...
10 篇 graphic era hill...
9 篇 national univers...
9 篇 school of comput...
9 篇 vivekananda glob...
9 篇 college of compu...
8 篇 school of comput...
8 篇 maharishi school...
8 篇 gla university d...
8 篇 college of infor...
8 篇 school of comput...
7 篇 college of compu...

作者

13 篇 chauhan rahul
11 篇 yang yang
10 篇 anand vatsala
8 篇 kukreja vinay
8 篇 gupta rupesh
7 篇 luo xiaonan
7 篇 zhao yang
6 篇 pei jihong
6 篇 kumar ankit
6 篇 choudhury tanupr...
6 篇 zhu ce
6 篇 ce zhu
6 篇 kumar gaurav
6 篇 li wei
6 篇 yu li
5 篇 gill kanwarparta...
5 篇 zhiguo cao
5 篇 nagaraj p.
5 篇 singh kamred udh...
5 篇 li qiang

语言

4,706 篇 英文
51 篇 其他
17 篇 中文
1 篇 土耳其文

检索条件"任意字段=2023 IEEE International Conference on Image Processing and Computer Applications, ICIPCA 2023"

共 4758 条记录，以下是511-520 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：

An Area-Efficient, Analog Integrated image Edge Detector based on the Robert's Cross Operator 12

An Area-Efficient, Analog Integrated Image Edge Detector bas...

引用

12th international conference on Modern Circuits and Systems Technologies, MOCAST 2023

作者： Gennis, Georgios Kamperi, Argyro Alimisis, Vassilis Dimas, Christos Sotiriadis, Paul P. National Technical University of Athens Department of Electrical and Computer Engineering Greece

ISBN: (纸本)9798350321074

Edge detection is an useful tool utilized by various computer Vision applications. A prime application example for locating the spatial edges of an image is to then separate and identify the included objects. Similarly to most computer Vision tools, edge detection is computation hungry, but the whole procedure can be highly parallelized. Therefore hardware application specific implementations present multiple benefits compared to traditional central processing unit approaches. To this end, in this work an implementation of a hardware friendly variation of the Robert's Cross operator is presented, that along with the utilized building blocks achieves a high area and power efficiency. The edge detector was evaluated on 3 images involving various different applications, achieving a mean Structural Similarity Index Metric of 0.75 while requiring 956μm2 per pixel. The presented edge detector was designed and simulated in a TSMC 90nm CMOS process, using the Cadence IC Suite. © 2023 ieee.

关键词： Edge detection

来源：评论

学校读者我要写书评

暂无评论

ICCL: SELF-SUPERVISED INTRA- AND CROSS-MODAL CONTRASTIVE LEARNING WITH 2D-3D PAIRS FOR 3D SCENE UNDERSTANDING 30

ICCL: SELF-SUPERVISED INTRA- AND CROSS-MODAL CONTRASTIVE LEA...

引用

30th ieee international conference on image processing (ICIP)

作者： Higa, Kyota Yamaguchi, Masahiro Hosoi, Toshinori NEC Corp Ltd Visual Intelligence Res Labs Shimonumabe 1753Nakahara Ku Kawasaki Kanagawa Japan

ISBN: (纸本)9781728198354

This paper proposes self-supervised intra- and cross-modal contrastive learning (ICCL) with 2D-3D pairs for 3D scene understanding. Learning from different modalities has produced substantial results in self-supervised learning. Our method learns a model with high transferability by minimizing contrastive losses based on 2D, 3D, and 2D-3D features. Compared with a conventional approach minimizing 3D and 2D-3D contrastive losses, our method minimizes a 2D contrastive loss in addition to them. It leads to learning a better feature representation. We evaluate the transferability by conducting three downstream tasks, including object classification and part segmentation. The results of the 3D object classification show that our approach achieves an accuracy of 91.7 and 85.4 (0.5 and 3.7 points higher than the conventional method). The results of the few-shot object classification and the part segmentation show that our accuracy is equal to or higher than conventional methods. With better feature representation for 2D images and 3D point clouds, transfer learning can be more accessible, enabling the implementation of various applications in many fields.

关键词： contrastive learning image point cloud multi-modality

来源：评论

学校读者我要写书评

暂无评论

Research on Detection of Moldy Corn Kernels Based on Machine Vision 7

Research on Detection of Moldy Corn Kernels Based on Machine...

引用

7th international conference on Electrical, Mechanical and computer Engineering, ICEMCE 2023

作者： Chen, Yuanqi Zhang, Ning Liu, Ziyang Ye, Xinwei Xijing University Xi'an China

ISBN: (纸本)9798350382877

Corn plays an important role in many fields, but the level of intelligent detection for moldy corn is low. This article proposes a method for identifying moldy corn kernels based on machine vision. First, the image is processed, and then the MSR method with color restoration in the Retinex image enhancement algorithm is used to enhance the image. The threshold is set in the HSV space, and the moldy corn kernels are segmented through morphological processing. The two processing results are combined through logical AND operation to obtain the result. The final detection result shows that the probability of effectively recognizing moldy corn kernels can reach around 95%. This proves that the algorithm proposed in the article can efficiently and quickly detect moldy individuals in corn kernels, providing technical support and theoretical basis for the future development of intelligent detection of moldy individuals in corn. © 2023 ieee.

关键词： image segmentation

来源：评论

学校读者我要写书评

暂无评论

Research and Implementation of Multi-Objective Optimization Algorithm in Dietary Collocation

Research and Implementation of Multi-Objective Optimization ...

引用

image processing and computer applications (icipca), ieee international conference on

作者： Xiaoli Zhu School of Computing and Software Dalian Neusoft University of Information Dalian China

ISBN: (数字)9798350360240

ISBN: (纸本)9798350384161

In this paper, the dietary collocation method based on multi-objective evolutionary algorithm will be introduced. Firstly, the dietary collocation problem based on multi-objective evolution is described, the recipe structure and food database are defined, the cost evaluation model is given, and the solution space of the recipe recommendation problem is established; then new domination strategies are defined for the food collocation problem in order to find the non-dominated solutions in the evolutionary process; the methods used for the dietary collocation updating strategy are defined based on gene mutation and crossover; finally, the algorithm used in this paper is compared with two mainstream multi-objective evolutionary algorithms to prove the effectiveness of the algorithm in this paper.

关键词： Costs Databases image processing Evaluation models Evolutionary computation computer applications Optimization Sorting Convergence

来源：评论

学校读者我要写书评

暂无评论

Exploration of Deep Methods for Cross-Domain Aerial image Matching 12

Exploration of Deep Methods for Cross-Domain Aerial Image Ma...

引用

12th international conference on image processing Theory, Tools and applications, IPTA 2023

作者： Shahid, Md. Vk, Prajwal Haq, Inzamam-Ul Faisal, Md. Bangalore India Drdo Ade Bangalore India

ISBN: (纸本)9798350325416

image matching is an attractive area for researchers. This field has been propelled recently due to the advancement of imaging devices with multi-spectral capabilities, compute power, and the evolution of the deep learning era. Cross-domain or cross-platform matching remains challenging due to the multiple type modalities associated and the need for relevant datasets. Learning or training in one domain (e.g., spectral band) and matching across domains are the real challenges for the imaging community today. The wide availability of Google Earth imagery, the development of cross-domain matching algorithms, and high-speed devices encourage addressing this issue. This paper explored deep learning methods for a cross-domain image-matching perspective. We have exploited latent and feature space, particularly for standard deep methods with several preprocessing steps, optimizer settings, and post-processing steps. We evaluated performance over standard cross-platform dataset using metrics available in the literature. © 2023 ieee.

关键词： Antennas

来源：评论

学校读者我要写书评

暂无评论

Multi-scale Feature Modification Network for FewShot image Classification 2

Multi-scale Feature Modification Network for FewShot Image C...

引用

2nd international conference on image processing, computer Vision and Machine Learning, ICICML 2023

作者： Chen, Yuxiang Lu, Zongqing Tsinghua University Shenzhen International Graduate School Shenzhen China

ISBN: (纸本)9798350331417

Few-shot image classification aims to learn a model that can adopt to unseen classes with few labeled data. This challenging problem requires to overcome the distribution shift of features due to differences between the novel classes and the base classes. Inspired by transformer style self-attention mechanism and feature pyramid, we propose a multi-scale cross-attention module. This module enables the correction of features by interacting with feature information at different scales and obtains the feature set of the sample. In addition, from the perspective of metric learning, we further propose a distance metric module to measure the distance between sets of features, thus better characterizing the similarity between samples. Extensive experiments on two public benchmarks in both 1-shot and 5-shot setting demonstrate the effectiveness of our method, which is a significant performance improvement over most methods. © 2023 ieee.

关键词： cross-attention Few-shot image classification metric learning multi-sacle

来源：评论

学校读者我要写书评

暂无评论

LEARNABLE SNAKE R-CNN FOR INSTANCE-LEVEL BIOMEDICAL image SEGMENTATION 30

LEARNABLE SNAKE R-CNN FOR INSTANCE-LEVEL BIOMEDICAL IMAGE SE...

引用

30th ieee international conference on image processing (ICIP)

作者： Song, Jie Cai, Ziyun Song, Yurong Jiang, Guoping Lian, Zhichao Xiao, Liang Nanjing Univ Posts & Telecommun Coll Automat Coll Artificial Intelligence Nanjing Peoples R China Nanjing Univ Sci & Technol Sch Comp Sci & Engn Nanjing Peoples R China

ISBN: (纸本)9781728198354

Precisely knowing each instance's position and extents is a critical first step in many biological applications. State-of-the-art techniques rely either on deep learning models designed to predict segmentation masks on each Region of Interest (RoI) or on classic active contour methods. The former struggles to precisely delineating boundaries and tends to output masks at low resolutions when the cells/nuclei are very irregular while the latter often needs good initialization and manual setting of parameters, thus limiting their usefulness. To bridge this gap, we introduce Snake R-CNN, a new level of the learnable active contour model that predict boundary on each RoI in a sequent way. To do so, for each RoI, we reformulate the contour deformation task in terms of a hidden state evolution problem and update the evolution process using energy minimization. We learn snake parameterizations per instance in an end-to-end manner, and demonstrate its effectiveness for contour inferences of various cell/nucleus types where consistently higher performances were obtained for comparison against state-of-the-arts.

关键词： Biomedical segmentation Deep learning Active contour Recurrent neural network Instance segmentation

来源：评论

学校读者我要写书评

暂无评论

Anomaly Detection in image processing using Artificial Intelligence

Anomaly Detection in Image Processing using Artificial Intel...

引用

2023 ieee international conference on Device Intelligence, Computing and Communication Technologies, DICCT 2023

作者： Jain, Swati Choudhary, Naveen College of Technology and Engineering Department of Computer Science and Engineering Udaipur India College of Technology and Engineering The Department of Computer Science and Engineering Udaipur India

ISBN: (纸本)9781665474924

Any method that looks for samples that deviate from anticipated patterns is sometimes referred to as anomaly detection. Many outlier finding methods are established on the types of irregularities, various types of data labels that are available, and the applications. The aim of this paper is to give an overview and systematic evaluation of outlier finding research. We believe that the paper contributes to a better understanding of the numerous fields in various types of research done on this subject. The approaches for anomaly detection have been separated into many groups. We discuss the pros and cons of each category and look at how computationally complex the various methods are in terms of real-world application domains. We concluded the paper by providing research gaps and constraints we faced while applying artificial intelligence algorithms in practical applications. This review paper examines several outlier detection and treatment techniques in images, as well as gives better performance of various AI approaches. © 2023 ieee.

关键词： Anomaly detection

来源：评论

学校读者我要写书评

暂无评论

Optimized NLP Models for Digital Twins in Metaverse 47

Optimized NLP Models for Digital Twins in Metaverse

引用

47th ieee-computer-Society Annual international conference on computers, Software, and applications (COMPSAC)

作者： Lukaj, Valeria Catalfamo, Alessio Fazio, Maria Celest, Antonio, V Vinare, Massimo Univ Messina Messina Italy

ISBN: (纸本)9798350326970

Digital Twins (DTs) in Metaverse face many challenges such as the lack of optimized AI models to allow the interaction between the user and the virtual environment. In this paper, we propose an optimized model for human language processing based on Convolutional Neural Networks (CCNs) and we present an input processing strategy to meet the realtime requirements of smart applications that integrate DTs oriented to speech-based functionalities for user interaction and Metaverse. In our solution, CNNs are applied for the processing and classification of the human voice, while structured data and MFCC coefficients are used to train the neural networks and generate interference in the models. Similarly, the MFCC algorithm is provided to extract the unique characteristics that specify each generated audio file and to reduce the complexity of the neural network model in order to obtain better performance. Starting from an approach to the problem available in the literature, we have optimized a specific CNN model for Natural Language processing (NLP) in order to increase effective results. The proposed model has demonstrated excellent performance and can be used as a basis for the implementation of software that allows the interaction of DTs with voice commands issued by a user.

关键词： Digital Twins Metaverse Virtual Reality Natural Language processing Automated Speech Recognition Convolutional Neural Networks MFCCs

来源：评论

学校读者我要写书评

暂无评论

CT- MRI image Fusion Using Multi-Measure Enhancement 10

CT- MRI Image Fusion Using Multi-Measure Enhancement

引用

10th ieee Uttar Pradesh Section international conference on Electrical, Electronics and computer Engineering, UPCON 2023

作者： Aishwarya, N. Sai Keerthi, R.V. Amrita School of Engineering Department of ECE Amrita Vishwa Vidyapeetham Chennai India

ISBN: (纸本)9798350382471

Fusion of medical data from different modalities has attracted the heath care applications due to its improved image quality and increased accuracy in clinical diagnosis. In this work, patch-based fusion using optimum focus measures are performed based on the analysis of each image patch in the respective source images. Firstly, the images are divided into optimal-sized patches. Secondly, the information depth in each patch is assessed using image variance, leading to the establishment of three categories: patches with high structural information, those with good texture content, and patches with slow variation. Next, each group of corresponding patches from the source images is integrated using multiple focus measures to create synthesized image patches. Finally, all the fused image patches are combined together to form the final fused output. To evaluate the effectiveness of this approach, both visual examination and statistical analysis are conducted, ensuring a comprehensive assessment of the fused images. By employing this strategy, the proposed technique aims to enhance the quality of medical image fusion, providing better insights for medical professionals in diagnosis and treatment planning. © 2023 ieee.

关键词： focus measure image fusion image variance multi-modal

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476页 << < 48 49 50 51 52 53 54 55 56 57 > >>

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：