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

25,302 篇 会议
282 篇 期刊文献
21 册 图书
3 篇 学位论文

馆藏范围

25,608 篇 电子文献
0 种 纸本馆藏

日期分布

学科分类号

15,842 篇 工学
- 9,892 篇 计算机科学与技术...
- 6,083 篇 电气工程
- 5,779 篇 信息与通信工程
- 5,627 篇 软件工程
- 2,035 篇 光学工程
- 1,458 篇 控制科学与工程
- 1,281 篇 机械工程
- 1,157 篇 电子科学与技术（可...
- 877 篇 生物医学工程（可授...
- 834 篇 生物工程
- 799 篇 仪器科学与技术
- 268 篇 网络空间安全
- 253 篇 化学工程与技术
- 248 篇 安全科学与工程
- 243 篇 交通运输工程
- 183 篇 材料科学与工程（可...
- 167 篇 土木工程
- 164 篇 建筑学
5,731 篇 理学
- 3,491 篇 物理学
- 2,208 篇 数学
- 886 篇 生物学
- 566 篇 统计学（可授理学、...
- 419 篇 系统科学
- 317 篇 化学
3,025 篇 医学
- 2,900 篇 临床医学
- 313 篇 基础医学(可授医学...
- 229 篇 药学(可授医学、理...
1,401 篇 管理学
- 856 篇 管理科学与工程(可...
- 618 篇 图书情报与档案管...
- 169 篇 工商管理
181 篇 法学
134 篇 农学
58 篇 教育学
52 篇 文学
51 篇 经济学
51 篇 军事学
22 篇 艺术学

主题

3,123 篇 image processing
2,084 篇 image coding
2,027 篇 visualization
1,754 篇 image segmentati...
1,490 篇 feature extracti...
1,083 篇 image reconstruc...
908 篇 cameras
885 篇 signal processin...
833 篇 image color anal...
756 篇 humans
717 篇 image edge detec...
692 篇 image enhancemen...
667 篇 computer vision
651 篇 training
584 篇 image analysis
575 篇 deep learning
536 篇 image quality
481 篇 conferences
473 篇 object detection
470 篇 robustness

机构

51 篇 school of electr...
49 篇 shanghai jiao to...
39 篇 ieee
38 篇 university of sc...
36 篇 shanghai jiao to...
36 篇 school of comput...
34 篇 shanghai jiao to...
33 篇 university of ch...
32 篇 microsoft resear...
26 篇 national institu...
25 篇 department of el...
24 篇 hendisli&#x011f
23 篇 institute for in...
23 篇 institute of ima...
23 篇 istanbul teknik ...
23 篇 institute of dig...
22 篇 peking univ inst...
21 篇 institute of inf...
21 篇 univ chinese aca...
21 篇 univ sci & techn...

作者

62 篇 guangtao zhai
46 篇 song li
45 篇 zhai guangtao
32 篇 jie yang
27 篇 li li
25 篇 m. vetterli
25 篇 bovik alan c.
25 篇 li sumei
25 篇 li song
25 篇 sarp ertürk
24 篇 jing zhang
24 篇 b. macq
23 篇 zhang lei
23 篇 li zhuo
23 篇 d.r. bull
22 篇 jürgen seiler
21 篇 shi guangming
20 篇 liu yang
20 篇 zhang wenjun
18 篇 mohamed-chaker l...

语言

24,610 篇 英文
489 篇 土耳其文
394 篇 其他
137 篇 中文
2 篇 西班牙文
2 篇 葡萄牙文

检索条件"任意字段=IEEE Visual Communications and Image Processing Conference"

共 25608 条记录，以下是4401-4410 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：

image to Text Synthesis with VGG-16 CNN and LSTM

Image to Text Synthesis with VGG-16 CNN and LSTM

引用

Technology & Engineering Management conference - Asia Pacific (TEMSCON-ASPAC), ieee

作者： Edward Kevin Winata Jude Joseph Lamug Martinez Computer Science Department Faculty of Computing and Media Bina Nusantara International University Central Jakarta Indonesia

ISBN: (数字)9798331515881

ISBN: (纸本)9798331515898

One of the more difficult tasks at the nexus of computer vision and natural language processing(NLP) is image decomposition into natural language, also referred to as prompts. This study presents a novel method for tackling this job by combining Long Short - Term Memory(LSTM) networks for text synthesis with Convolutional Neural Networks(CNNs) for image feature extraction. After high - level visual features from input photos are extracted using the VGG-16 CNN architecture, the information is then fed into LSTM encoder networks to produce descriptive texts. Using common evaluation measures like BLEU(Bilingual Evaluation Understudy), METEOR(Metric for Evaluation of Translation with Explicit Ordering), and CIDEr(Consensus - based image Description Evaluation), the efficacy of the suggested method is assessed on benchmark datasets, such as other Flickr datasets with larger scales. The suggested strategy outperforms baseline techniques, as shown by experimental findings, obtaining exceptional performance indexes. Furthermore, the model's capacity to generate seman-tically coherent and contextually appropriate descriptions is demonstrated by quantitative examination of generated texts. The suggested methodology advances the field of multimodal artificial intelligence and establishes the groundwork for future developments in content creation, picture comprehension and human - computer interaction.

关键词： visualization Translation Tensors Benchmark testing Feature extraction Performance analysis Convolutional neural networks Web sites Multimedia communication Long short term memory

来源：评论

学校读者我要写书评

暂无评论

Enhancing Autonomous Driving through Dual-Process Learning with Behavior and Reflection Integration

Enhancing Autonomous Driving through Dual-Process Learning w...

引用

International conference on Acoustics, Speech, and Signal processing (ICASSP)

作者： Xiao Zhang Kangsheng Wang Tianyu Hu Huimin Ma School of Computer and Communication Engineering University of Science and Technology Beijing Beijing China

ISBN: (数字)9798350368741

ISBN: (纸本)9798350368758

Contemporary autonomous driving (AD) methodologies, which predominantly convert visual features into control directives, face long-tail challenges due to constraints imposed by limited data distribution. Conversely, human drivers exhibit proficiency in such conditions, underscoring the significance of emulating human cognition in AD systems. Therefore, we introduce Dual-Process Learning (D-PL) approach for cognitive-enhanced decision-making. Inspired by dual-process theory, the D-PL method combines Behavior Pattern Learning (BPL) and Self-Reflective Learning (SRL) to integrate quick, intuitive decisions with deliberate, analytical reasoning, constructing a hierarchical decision model for sophisticated trajectory planning. Our approach improves decision-making, enhances adaptability, and tackles the crucial open-world generalization challenge encountered by current AD methods. Comprehensive evaluations on the nuScenes dataset validate the robustness of our method, demonstrating its superior performance in navigating the intricacies of real-world contrasting with conventional models.

关键词： Adaptation models visualization Heavily-tailed distribution Trajectory planning Decision making Power line communications Cognition Robustness Speech processing Autonomous vehicles

来源：评论

学校读者我要写书评

暂无评论

AI-based Diabetic Retinopathy Grading Using Raspberry Pi

AI-based Diabetic Retinopathy Grading Using Raspberry Pi

引用

ieee International conference on Signal processing, Informatics, Communication and Energy Systems (SPICES)

作者： Aparna S Madhurema V J Nandana Nair Parvathi Mohan Rajeev Rajan Govt Engineering College Bartonhill Thiruvananthapuram Translational Research and Professional Leadership Centre (TPLC) APJ Abdul Kalam Technological University Kerala India

ISBN: (数字)9798350376135

ISBN: (纸本)9798350376142

Diabetic retinopathy is a progressive eye condition caused by prolonged high blood sugar levels in individuals with diabetes, leading to damage in the blood vessels of the retina. It can result in vision impairment or blindness if left untreated, making early detection and management crucial for preserving eyesight. Employing neural networks for image classification can help overcome these challenges. Convolutional neural networks (CNNs) can automatically extract relevant features and classify images into different categories, aiding in early diagnosis and intervention. It also offers a promising avenue for improving DR screening, particularly in areas with limited access to ophthalmologists. This paper aims to enhance DR grading performance by implementing a hardware solution using Raspberry Pi. One significant advantage of this approach is the potential for costeffective and portable screening in resource-limited settings. By leveraging the Raspberry Pi’s affordability and compact form factor, healthcare providers can deploy screening systems in remote areas where access to traditional medical infrastructure is limited

关键词： Diabetic retinopathy visual impairment Neural networks Medical services Signal processing Feature extraction SPICE Retina Convolutional neural networks Medical diagnostic imaging

来源：评论

学校读者我要写书评

暂无评论

Liver Tumor Segmentation Based on Three-Channel Cascaded SEU-Nets and C-LSTM 13

Liver Tumor Segmentation Based on Three-Channel Cascaded SEU...

引用

13th International conference on Wireless communications and Signal processing, WCSP 2021

作者： Li, Yarong Hu, Dong Nanjing University of Posts and Telecommunications Jiangsu Province's Key Lab of Image Processing and Image Communications Nanjing China

ISBN: (纸本)9781665407854

An abdominal CT liver tumor segmentation algorithm based on three-channel cascade SEU-Nets and C-LSTM is proposed in this paper. Concerning the accuracy of most known algorithms is limited by using single-phase CT images, the proposed method takes advantage of the different characteristics of the lesion area in the venous phase, arterial phase and delayed phase, and the correlation between slices in enhanced CT images. It uses three-channel SEU-Nets as the encoder to extract image features of slices in three phases, and uses 3D convolution to extract the relationship between slices for the same location at different phases. And then it uses C-LSTM to extract the inter-slice sequence feature relationship. Finally, the decoder outputs fine segmentation of liver tumor output. 40 sets of high-quality abdominal-enhanced CT images of the liver and liver tumors used in the experiment were collected in the provincial central hospital and annotated by experts. Comparisons are carried out with well-known methods, such as improved CFCNs, H-DenseUNet network and DBAs-based multi-scale DC-CUNets segmentation network. Experimental results show that the average segmentation accuracy of proposed algorithm is 7.04% higher than that of the multi-scale DC-CUNets segmentation network based on DBAs, and the DICE coefficient is improved by 4.89%. © 2021 ieee.

关键词： Long short-term memory

来源：评论

学校读者我要写书评

暂无评论

Multi-Access Edge Computing performance into Non-Public 5G Networks: A robot-based experiment

Multi-Access Edge Computing performance into Non-Public 5G N...

引用

ieee International Workshop on Factory Communication Systems (WFCS)

作者： Andrés Meseguer Valenzuela Javier Silvestre-Blanes Victor M. Sempere-Paya Luis M. Bartolín-Arnau Instituto Tecnológico de Informática (ITI) Valencia Spain Dept. Comp. Eng. (DISCA)(ITI) Universitat Politècnica de Valencia (UPV) Valencia Spain Dept. Comms (DCOM)(ITI) Universitat Politècnica de Valencia (UPV) Valencia Spain

ISBN: (数字)9798350319347

ISBN: (纸本)9798350319354

The fifth generation of cellular communications (5G) provides enough performance to carry on scenarios that require low latency such as robot control remote computing. In this work, it is presented an experiment focused on the trajectory management of a 5G connected arm robot end-effector with image processing in the Edge. This use case, which is integrated into a Non-Public 5G network (NPN), provides several improvements in terms of network configuration to enable the development of Multi-Access Edge Computing (MEC) use cases by enhancing uplink throughput.

关键词： Multi-access edge computing 5G mobile communication image processing Robot control Throughput Production facilities Trajectory

来源：评论

学校读者我要写书评

暂无评论

Center-free intuitionistic fuzzy c-means clustering algorithm based on similarity of hybrid spatial membership for image segmentation

Center-free intuitionistic fuzzy c-means clustering algorith...

引用

Natural Language processing (ICNLP), International conference on

作者： Lan Rong Wang Shumin He Hu Zhao Feng Yu Haiyan Zhang Lu School of Communications and Information Engineering Xi’an University of Posts and Telecommunications Xi’an China

In order to address the issue that the center-free fuzzy c-means (CFFCM) clustering algorithm does not consider the texture features and spatial information of pixels, and the time complexity is too high, a center-free intuitionistic fuzzy c-means clustering algorithm based on similarity of hybrid spatial membership for image segmentation is proposed. In the proposed algorithm, the voting model is used to generate intuitionistic fuzzy sets (IFS), and the generated hesitation degree and membership degree are combined with spatial information to design a spatial intuitionistic membership degree similarity model. This model can deal with the similarity between pixels and classes in gray information, so the segmentation efficiency is improved. At the same time, the intuitionistic fuzzy local binary pattern (IFLBP) operator is used to extract the image texture information and introduce it into the objective function. Spatial membership similarity model is used to process texture information and improve the segmentation accuracy of the algorithm. The results of simulation experiment show that the proposed has advantages in both visual effect and evaluation index.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Subjective Quality Assessment of HDR Stereoscopic Omnidirectional Videos

Subjective Quality Assessment of HDR Stereoscopic Omnidirect...

引用

International conference on Communication Technology (ICCT)

作者： Manman Liu Jihao You Ruitao Chen Ziwei Ye Gangyi Jiang Faculty of Information Science and Engineering Ningbo University Ningbo China

High dynamic range stereoscopic omnidirectional video (HSOV) can bring wide field of view and high contrast visual experience to viewers. However, the generation, transmission and display of HSOV will inevitably cause distortions in the video. Therefore, it is important to quantify the impact of the processing of coding and tone mapping on the quality of HSOV. To this end, the subjective quality of HSOV after HEVC coding and tone mapping is evaluated in this paper. Firstly, an HSOV database namely NBU-HSOVD is constructed, which consists of 450 distorted HSOVs. Then, 34 subjects are invited to evaluate the quality of the distorted videos with absolute category rating method so that the MOS value of each video can be provided. Finally, the performance of six existing objective image or video quality assessment methods are tested on NBU-HSOVD. The constructed NBU-HSOVD database can provide reference and basis for the research of objective quality assessment of HSOV in the future.

关键词： visualization image analysis Databases Stereo image processing Distortion Encoding communications technology

来源：评论

学校读者我要写书评

暂无评论

A Deep Texture Metric for PET image Quantification and image Synthesis

A Deep Texture Metric for PET Image Quantification and Image...

引用

ieee Symposium on Nuclear Science (NSS/MIC)

作者： R. L. Smith R. R. John I. Ackerley K. Al-Battat E. Alsyed E. Spezi K. Wells N. Morley C. Marshall Wales Research and Diagnostic PET Imaging Centre (PETIC) Cardiff University Cardiff United Kingdom University of Surrey Centre for Vision Speech & Signal Processing University of Surrey Guildford Guildford United Kingdom Department of Nuclear Engineering Faculty of Engineering King Abdulaziz University Jeddah Saudi Arabia School of Engineering Cardiff University Cardiff United Kingdom

Fluorodeoxyglucose (FDG) Positron Emission Tomography (PET) serves as a cornerstone in functional imaging. PET imaging reveals metabolic abnormalities before morphological alterations occur. The standardized uptake value is a common metric to semi-quantify PET images. visual scoring of PET image heterogeneity has demonstrated correlations with tumour characteristics. Quantification of this spatial variation in FDG distribution via its shape and texture has proven to be a fertile area of research under the umbrella term "Radiomics." Deep learning with convolutional neural networks (CNN) serves as large feature extractors with proven ability in tumour type classification in PET imaging. Deep learning in PET imaging has also been utilized for image enhancement, reconstruction, segmentation and image synthesis. In this work, we quantify the feature distribution of neural activations of each layer in a CNN following propagation through the network of a PET image. The Gramian matrix of the activation functions quantifies the neural representation of the CNN and thus serves as a measure of visual perception. image synthesis using gradient descent on the target PET image Gramian matrix allows visualization of the texture. This metric is tested in PET imaging data of a recently developed texture phantom and a single primary tumour from a non-small-cell lung cancer (NSCLC) patient. It is demonstrated that the summation of the Gramian decreases with decreasing homogeneity. The visual appearance of the synthesized PET images closely resembles that ground truth PET images, both in the texture phantom and clinical image.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Optimal Frame Rate Selection of Screen Content Video and Its Application in Perceptual Versatile Video Coding 4

Optimal Frame Rate Selection of Screen Content Video and Its...

引用

4th International conference on Natural Language processing, ICNLP 2022

作者： Gong, Yanchao Yu, Xiaoxin Yang, Kaifang Xi'an University of Posts and Telecommunications Intl. Jt. Res. Ctr. for Wireless Commun. and Information Processing Technology of Shaanxi Province Center for Image and Information Processing Xi'an China Xi'an University of Posts and Telecommunications School of Communications and Information Engineering Xi'an China Shaanxi Normal University School of Computer Science Xi'an China

ISBN: (数字)9781665495448

ISBN: (纸本)9781665495448

Screen content videos (SCV) containing text, graphics, icons, and charts are widely used in distance education, screen sharing, and other fields. In these fields, SCV coding plays a critical role which pursues higher reconstructed video quality with lower coding bitrate. And, the selection of frame rate significantly affects the SCV coding efficiency. In addition to motion intensity, smoothness of motion change is also an important factor affecting the selection of frame rate, but it is ignored by current researches. In this paper, targeting at SCV, metrics that effectively quantify smoothness of motion change and motion intensity are first constructed. Then, the impacts of smoothness of motion change and motion intensity on frame rate selection are further explored and modeled. Finally, an optimal frame rate selection method is proposed and is further applied to the state-of-the-art versatile video coding (VVC) standard to significantly improves the SCV coding efficiency. Compared with the traditional method adopted in the VVC test model (i.e., VTM), the proposed method can achieve the average BD-rate reductions of 27.14%. © 2022 ieee.

关键词： Video signal processing

来源：评论

学校读者我要写书评

暂无评论

Artificial Neural Network for processing Fingerprint image Noise 23

Artificial Neural Network for Processing Fingerprint Image N...

引用

23rd ACIS International Summer Virtual conference on Software Engineering, Artificial Intelligence, Networking and Parallel/Distributed Computing, SNPD-Summer 2022

作者： Han, Ke Institute of Forensic Science Ministry of Public Security China Department of Fingerprint Technology Beijing China

ISBN: (纸本)9798350396379

Fingerprint images from crime scenes can be used to find and identify suspects in the field of forensic science. Fingerprint images are usually polluted by noise, which affects the visual effect of fingerprint images. It is important to process the noise of fingerprint images. A supervised learning 9-layer artificial neural network besides the input layer and the output layer is designed to remove the noise of fingerprint images in this paper. The first three layers of the neural network are convolutional layers. The purpose of designing convolutional layers is to extract the feature information of the images layer by layer and gradually generate the feature maps. The fourth layer to the sixth layer are fully connected layers. The number of neurons in the fourth layer is the same as that of the sixth layer. The number of neurons in the fourth layer is the number of elements in the vector flattened by the feature maps outputted from the last convolutional layer. The seventh layer to the ninth layer in the neural network are deconvolutional layers. These deconvolutional layers gradually restore the feature maps to the fingerprint image. Finally, the enhanced fingerprint image is outputted from the output layer. As the training samples of fingerprint images is inadequate, this paper provides a way to make training samples. The clear fingerprint image is blurred as the corresponding blurred fingerprint image, which solves the problem of lack of the training samples. The blurred fingerprint image and the corresponding clear fingerprint image are used to establish the training sample set and train the artificial neural network. The mean square error function is used as the loss function to adjust and optimize the parameters of the neural network. The neural network in this paper is evaluated on test fingerprint images. The neural network method is compared with the Gaussian low-pass filtering method and the Wiener filtering method. Experimental results show that the neura

关键词： image enhancement

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 << < 437 438 439 440 441 442 443 444 445 446 > >>

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：