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

20,242 篇 会议
164 篇 期刊文献
80 册 图书
3 篇 学位论文

馆藏范围

20,489 篇 电子文献
0 种 纸本馆藏

日期分布

学科分类号

12,755 篇 工学
- 8,298 篇 计算机科学与技术...
- 5,001 篇 软件工程
- 4,985 篇 信息与通信工程
- 4,638 篇 电气工程
- 1,447 篇 控制科学与工程
- 1,321 篇 电子科学与技术（可...
- 1,224 篇 光学工程
- 899 篇 生物医学工程（可授...
- 868 篇 机械工程
- 830 篇 仪器科学与技术
- 811 篇 生物工程
- 326 篇 网络空间安全
- 291 篇 交通运输工程
- 284 篇 安全科学与工程
- 278 篇 化学工程与技术
- 247 篇 动力工程及工程热...
- 189 篇 建筑学
- 179 篇 土木工程
4,662 篇 理学
- 2,149 篇 数学
- 2,072 篇 物理学
- 874 篇 生物学
- 668 篇 统计学（可授理学、...
- 522 篇 系统科学
- 330 篇 化学
1,523 篇 医学
- 1,405 篇 临床医学
- 383 篇 基础医学(可授医学...
- 269 篇 药学(可授医学、理...
1,368 篇 管理学
- 824 篇 管理科学与工程(可...
- 615 篇 图书情报与档案管...
- 208 篇 工商管理
204 篇 法学
136 篇 农学
78 篇 经济学
69 篇 军事学
64 篇 教育学
40 篇 文学
24 篇 艺术学
1 篇 哲学
1 篇 历史学

主题

1,120 篇 image segmentati...
1,067 篇 image coding
1,059 篇 signal processin...
1,010 篇 image processing
987 篇 internet of thin...
952 篇 feature extracti...
830 篇 image reconstruc...
631 篇 internet
553 篇 signal processin...
495 篇 signal to noise ...
476 篇 image edge detec...
475 篇 deep learning
456 篇 training
423 篇 image color anal...
400 篇 cameras
397 篇 robustness
395 篇 image enhancemen...
306 篇 image resolution
292 篇 image recognitio...
287 篇 visualization

机构

58 篇 school of inform...
39 篇 university of sc...
37 篇 signal processin...
29 篇 microsoft resear...
27 篇 university of ch...
26 篇 institute of sig...
26 篇 signal processin...
25 篇 center for signa...
24 篇 university of el...
23 篇 school of electr...
21 篇 ieee
21 篇 college of big d...
20 篇 school of cyber ...
20 篇 department of si...
20 篇 school of inform...
20 篇 signal and infor...
20 篇 school of electr...
19 篇 hsch darmstadt d...
19 篇 peng cheng labor...
19 篇 harbin institute...

作者

31 篇 li zhuo
27 篇 zhuo li
25 篇 sridharan sridha
23 篇 yang yang
23 篇 r.m. mersereau
20 篇 jing zhang
20 篇 wei li
20 篇 gabbouj moncef
19 篇 mansouri majdi
18 篇 zhang lei
18 篇 busch christoph
18 篇 m. gabbouj
17 篇 m.j.t. smith
17 篇 bouzrara kais
17 篇 clinton fookes
17 篇 wang wei
17 篇 zhang yan
16 篇 wang lei
16 篇 takahiro ogawa
16 篇 ghassan alregib

语言

19,942 篇 英文
461 篇 其他
75 篇 中文
7 篇 俄文
6 篇 土耳其文
1 篇 西班牙文

检索条件"任意字段=IEEE International Conference on Signal Image Technology and Internet Based Systems"

共 20489 条记录，以下是4611-4620 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：

Facial Recognition with Deblurring Component (RL Deconvolution) Utilizing MATLAB and OpenCV for Household Surveillance

Facial Recognition with Deblurring Component (RL Deconvoluti...

引用

ieee international conference on Artificial Intelligence in Engineering and technology (IICAIET)

作者： Kyle Mikael Pacudan Charmaine C. Paglinawan School of Electrical Electronics and Computer Engineering Mapúa University Manila Philippines

ISBN: (数字)9798350389692

ISBN: (纸本)9798350389708

The study tackles the challenge of developing a facial recognition in household surveillance systems through the integration of image deblurring techniques. Particularly, it examines the use of Richardson-Lucy (RL) deconvolution, coupled with Speeded-Up Robust Features (SURF) for feature matching, to enhance the clarity of images blurred by motion. The research was conducted using a system developed in MATLAB GUI with OpenCV, focusing on the dual objectives of improving facial recognition accuracy and image quality under motion blur conditions. Various testing was conducted to measure the system's performance, demonstrating that RL deconvolution significantly enhances both the image clarity and the effectiveness of facial recognition, with marked improvements in detection accuracy and Peak signal-to-Noise Ratios (PSNR) in which it achieved an average value of 29.43dB. Uncontrolled deblurring tests using real-life blurred images demonstrated average success, reflecting the inherent challenges of deblurring images with complex and unpredictable blur patterns. The facial recognition system achieved an accuracy of 96.7% in optimal feature matching threshold which is set at 30. However, performance declined with increased facial occlusion and varying angles, emphasizing the need for further refinement. Lowering the thresholds generally resulted in higher sensitivity, capturing more true positives but at the cost of increasing false positives. While increasing the thresholds enhanced precision by effectively reducing false positives but also increased the risk of false negatives, missing some true matches.

关键词： image quality PSNR Deconvolution Accuracy Sensitivity Face recognition Surveillance MATLAB Testing Graphical user interfaces

来源：评论

学校读者我要写书评

暂无评论

Radar signal recognition based on deep residual network with attention mechanism 4

Radar signal recognition based on deep residual network with...

引用

4th ieee international conference on Electronic Information and Communication technology, ICEICT 2021

作者： Jin, Xiaolin Ma, Jing Ye, Fang College of Infomation and Communication Engineering Harbin Engineering University Harbin150001 China Key Laboratory of Advanced Marine Communication and Information Technology Ministry of Industry and Information Technology Beijing100854 China Science and Technology on Special System Simulation Laboratory Beijing100854 China

ISBN: (纸本)9781665432030

To address the problem of poor recognition success rate (RSR) of low probability of intercept (LPI) radar signals such as polyphase codes at low signal-to-noise ratio (SNR), In this paper, we propose a method of deep neural network with attention mechanism for modulation recognition of radar signals. The method first transforms the received radar signal into a two-dimensional time-frequency image(TFI), and then we obtain a binary time-frequency image by threshold segmentation，and resize TFIs through bicubic interpolation. While a deep residual network with Convolutional Block Attention Module (CBAM) is designed to recognize the radar signals. We take advantage of the attention mechanism to find the effective feature information in the noise and increase the effective information weight to further improve the recognition success rate of radar signals under low SNR. Finally, the average RSR of the method is nearly 96% for 7 signals at -6dB. © 2021 ieee

关键词： Deep neural networks

来源：评论

学校读者我要写书评

暂无评论

T-Pixel2Mesh: Combining Global and Local Transformer for 3D Mesh Generation from a Single image

T-Pixel2Mesh: Combining Global and Local Transformer for 3D ...

引用

international conference on Acoustics, Speech, and signal Processing (ICASSP)

作者： Shijie Zhang Boyan Jiang Keke He Junwei Zhu Ying Tai Chengjie Wang Yinda Zhang Yanwei Fu School of Data Science Fudan University Shanghai China Youtu Lab Tencent Shanghai China School of Intelligence Science and Technology Nanjing University Suzhou China Google USA

Pixel2Mesh (P2M) is a classical approach for reconstructing 3D shapes from a single color image through coarse-to-fine mesh deformation. Although P2M is capable of generating plausible global shapes, its Graph Convolution Network (GCN) often produces overly smooth results, causing the loss of fine-grained geometry details. Moreover, P2M generates non-credible features for occluded regions and struggles with the domain gap from synthetic data to real-world images, which is a common challenge for single-view 3D reconstruction methods. To address these challenges, we propose a novel Transformer-boosted architecture, named T-Pixel2Mesh, inspired by the coarse-to-fine approach of P2M. Specifically, we use a global Transformer to control the holistic shape and a local Transformer to progressively refine the local geometry details with graph-based point upsampling. To enhance real-world reconstruction, we present the simple yet effective Linear Scale Search (LSS), which serves as prompt tuning during the input preprocessing. Our experiments on ShapeNet demonstrate state-of-the-art performance, while results on real-world data show the generalization capability.

关键词：

来源：评论

学校读者我要写书评

暂无评论

SiQA: A Large Multi-Modal Question Answering Model for Structured images based on RAG

SiQA: A Large Multi-Modal Question Answering Model for Struc...

引用

international conference on Acoustics, Speech, and signal Processing (ICASSP)

作者： Jiawang Liu Ye Tao Fei Wang Hui Li Xiugong Qin School of Information Science and Technology Qingdao University of Science and Technology Qingdao China Beijing Research Institute of Automation for Machinery Industry Co. Ltd. Beijing China

ISBN: (数字)9798350368741

ISBN: (纸本)9798350368758

Existing Large Multimodal Models (LMMs) demonstrate excellent performance in handling visual tasks in everyday scenarios. However, they still face challenges in understanding structured images, such as flowcharts and organizational charts, which are characterized by text-rich and complex hierarchical components. In this paper, we propose SiQA, a knowledge construction and Retrieval-Augmented Generation(RAG)-based multimodal Question-Answering model designed for Structured images. SiQA operates in three stages: Knowledge Graph (KG) generation, retrieval-augmented, and answer generation. First, a KG representing the semantics of the structured images is generated through component analysis. We then performed similarity retrieval between the KG and queries, using a node-first algorithm to construct the most relevant subgraph. Finally, after performing an encoding alignment on the multimodal information, it is fed into the LLM to generate the answer. Additionally, we introduce a new dataset, OCQA 1 , which includes 5,112 questions derived from 1,000 Organizational Charts. We evaluated SiQA’s structured image detection and question-answering capabilities on the FD-DETR (a flowchart dataset) and SCQA, and verified its effectiveness and strong generalization ability through comparisons with existing state-of-the-art (SOTA) methods.

关键词： Flowcharts Visualization Semantics signal processing algorithms Knowledge graphs signal processing Question answering (information retrieval) Encoding Speech processing Faces

来源：评论

学校读者我要写书评

暂无评论

A Survey of Watermarking Technique using Deep Neural Network Architecture

A Survey of Watermarking Technique using Deep Neural Network...

引用

international conference on Computing, Communication, and Intelligent systems (ICCCIS)

作者： Gupta, Megha Kishore, R. Rama Guru Gobind Singh Indraprastha Univ USICT Delhi India NIET Greater Noida UP India

ISBN: (纸本)9781728185293

A computerized watermark is a sort of marker secretly introduced in a noise accepting signals, let us say, video, audio or image. It is normally accustomed to recognize proprietorship for the copyright of such signals. "Watermarking" is the way toward covering computerized bits in a conveyor signal. The shrouded data need not have to contain a connection to the transporter signal. Computerized watermarks might be applied to verify the genuineness or uprightness of the conveyor signal or to demonstrate the uniqueness of its proprietors. This paper explores a new family of transformation dependent on Deep Learning systems. We survey and present a relative investigation of the different profound learning procedures that target installing watermark that can be worked upon to accomplish substantial security level for the data being transmitted, and robustness over a few attacks particularly when transmitted over the loud medium. Our paper centers on how deep learning-based watermarking approaches show their prevalence because of the level of imperceptibility and robustness presented by adjustments in recurrence coefficients. We likewise feature the parts of the current methodologies that can be worked upon to accomplish images that are exceptionally indistinct from one another in the future.

关键词： Artificial neural network (ANN) Generative Adversarial neutral network (GAN) Convolutional neural network (CNN) Probabilistic neural network (PNN) Deep learning Deep neural network (DNN) Digital image watermarking Blind Robust Fragile Semi-fragile Watermarking

来源：评论

学校读者我要写书评

暂无评论

Large Array DOA Estimation Method based on VMD-NGOELM

Large Array DOA Estimation Method Based on VMD-NGOELM

引用

international conference on Vision, image and signal Processing (ICVISP)

作者： Runan Wang Yingchun Li Zhaolin Zhang Yan Song Hongbu Wang School of Information Science and Engineering Harbin Institute of Technology Weihai Weihai China State Grid Shandong Electric Power Company Yantai Muping Power Supply Company Yantai China

ISBN: (数字)9798331541460

ISBN: (纸本)9798331541477

In addressing the severe interference caused by noise issues in complex environments and the high-dimensional covariance matrix problem arising from large arrays during target azimuth estimation, this research introduces an innovative approach for Direction of Arrival (DOA) estimation in large-scale arrays, which integrates Variational Mode Decomposition with an optimized Extreme Learning Machine framework enhanced by the Northern Goshawk algorithm (VMD-NGOELM). This method leverages VMD to decompose the local features of each array signal, employing regularization and constraints to reduce the noise components in the signal, thereby mitigating the impact of noise information on covariance matrix construction. Subsequently, by harnessing the bio-inspired nature and local search capabilities of the NGO method, the algorithm of Extreme Learning Machine (ELM) undergoes a comprehensive optimization process in this study, enhancing the DOA estimation performance of the ELM model. The rapid training of ELM facilitates the swift acquisition of output weights between the covariance matrix and DOA, thereby accelerating the DOA estimation process for large arrays. Extensive numerical experiments reveal that the proposed methodology maintains superior accuracy in direction of arrival estimation, particularly in challenging low SNR environments.

关键词： Support vector machines Direction-of-arrival estimation Array signal processing Extreme learning machines Estimation signal processing algorithms Multiple signal classification Covariance matrices Optimization signal to noise ratio

来源：评论

学校读者我要写书评

暂无评论

A Fully-integrated Analog Front-end for Carbon-based Short-wave Infrared image Sensor

A Fully-integrated Analog Front-end for Carbon-based Short-w...

引用

international conference on ASIC

作者： Weirong Xi Jianhua Jiang Chengying Chen School of Opto-Electronic and Communication Engineering Xiamen University of Technology Xiamen China Research Center for Carbon-Based Electronics School of Electronics Peking University Beijing China

Carbon Nanotube Field Effect Transistor (CNT-FET) have many advantages in electronics materials such as high mobility and ultra-thin body, which are promising for the fabrication of high performance, low power consumption and low cost shortwave infrared image sensors. In this paper, a column-level Analog Front-end (AFE) circuit is designed as a processing circuit for a carbon-based short-wave infrared image sensor, which includes Capacitor TransImpedance Amplifier (CTIA) integrator, Correlated Double Sampling (CDS), and 10bit/125KHz Successive AppRoximation Analog-to-Digital Converter (SAR ADC). The proposed AFE is designed using SMIC 0.18µm CMOS 1P6M process with area of 1.9mm 2 and an power supply voltage of 1.8V. The post-simulation results show that the signal-to-Noise Ratio (SNR) is 56.84dB and signal-to-Noise and Distortion Ratio (SNDR) is 55.885dB. Meanwhile the Effective Number of Bits (ENOB) achieves 8.99bit. The range of detection current is 500p-100nA, and the power consumption is 7.01mW.

关键词：

来源：评论

学校读者我要写书评

暂无评论

A wide-spectrum 550-1600 nm, 16k VIS + 8 NIR pixels, high-dynamic range image-sensor for biomedical applications

A wide-spectrum 550-1600 nm, 16k VIS + 8 NIR pixels, high-dy...

引用

ieee international conference on Electronics, Circuits and systems (ICECS)

作者： Laurent Alacoque David Coriat Jean-Michel Tualle Valentin Espinas Xavier Alacoque Anabela Da Silva DOPT Department Univ. Grenoble Alpes CEA Leti Grenoble France DSCIN Department Univ. Grenoble Alpes CEA List Grenoble France LPL UMR 7538 Université Sorbonne Paris-Nord Villetaneuse France Aix Marseille Univ CNRS Centrale Marseille Institut Fresnel Aix Marseille University CERIMED Marseille France Anesthesia intensive care Oncopole Claudius Regaud Toulouse France

This paper presents an Application-Specific Integrated Circuit (ASIC) wide-spectrum image sensor and its sensing-module and system. It is made of an integrated visible image sensor, an external NIR-SWIR photodiodes acquisition system and on-chip Analogue to Digital conversion and provides a digital interface to a portable, fully integrated host system based on a raspberry-pi with a dedicated “hat” board. The system is capable of real-time Diffuse Optical Imaging in a wide spectrum with a resolution of 3x16k visible images and 3x8 NIR photodiodes. A signal-to-noise ratio of 66dB in the NIR domain was attained at a total power of 18.4 mW.

关键词：

来源：评论

学校读者我要写书评

暂无评论

A Deep Residual-based Model on Multi-Branch Aggregation for Stress and Emotion Recognition through Biosignals 19

A Deep Residual-based Model on Multi-Branch Aggregation for ...

引用

19th international conference on Electrical Engineering/Electronics, Computer, Telecommunications and Information technology, ECTI-CON 2022

作者： Mekruksavanich, Sakorn Hnoohom, Narit Jitpattanakul, Anuchit University of Phayao School of Information and Communication Technology Department of Computer Engineering Phayao Thailand Mahidol University Image Information and Intelligence Laboratory Department of Computer Engineering Faculty of Engineering Nakhon Pathom Thailand King Mongkut's University of Technology North Bangkok Intelligent and Nonlinear Dynamic Innovations Research Center Department of Mathematics Faculty of Applied Science Bangkok Thailand

ISBN: (纸本)9781665485845

Stress and emotion recognition (SER) is a rapidly growing field of study that has applications in various areas, including psychological wellbeing, rehabilitative services, athletic training, and human-computer interaction. Biological information such as the electrocardiogram (ECG), electromyography (EMG), and electrodermal activity (EDA) has been frequently utilized for the SER for learning-based approaches. This study introduces a convolutional neural network motivated by ResNeXt to facilitate multimodal awareness. The proposed model, named StressNeXt, can extract high-level insights from raw bio-signal signals and classify emotional expressions effectively. We undertake a series of investigations using a publicly released standard dataset (WESAD) to determine the optimal implementation of the proposed solution for recognizing stress and emotion. After incorporating preliminary fusion events, we examined deep learning models using 5-fold cross-validation. Our study demonstrates that the suggested technique can comprehend robust multimodal representations with an accuracy of 87.73% utilizing EDA. Additionally, the identification was designed to provide better to 99.92% by fusing with accelerometer sensor data. © 2022 ieee.

关键词： Emotion Recognition

来源：评论

学校读者我要写书评

暂无评论

New Generative image Model for Variational Autoencoders based on Counts Partition 7

New Generative Image Model for Variational Autoencoders Base...

引用

7th ieee international conference on Information technology and Nanotechnology, ITNT 2021

作者： Antsiperov, Viacheslav Kotelnikov Institute of Radioengineering and Electronics of Russian Academy of Sciences Signal Processing and Telecommunication Lab Moscow Russia

ISBN: (纸本)9781665432177

The article substantiates a generative image model based on a sample of random counts and its representation using compressed (coded) lattice partitioning. The basics of the model proposed is a concept of the ideal image. To avoid the problems with cumbersome descriptions, the ideal image is reduced to a sample of counts of a fixed (controlled) size. It is shown that the corresponding statistical description can be factorized into the product of the distributions of individual counts, which fits well with naive Bayesian algorithms and other machine learning approaches. Guided by this association in the image and likeness of the well-known K-means algorithm, the method of iterative partitioning - maximization of counts was synthesized. The main goal of the method is to calculate the maximum likelihood parameters of sample probability distribution and to use these parameters as a code for some intermediate representation of the input data. The method specific feature is the use of lattice neighbourhood trick for partitioning counts, that allows to control both the computation time and some characteristics of the resulting code. The final of the article is devoted to the algorithmic details of the proposed partition-maximization method are considered and several iterations related characteristics, including the convergence property, convergence criterion and asymptotic efficiency of the resulting estimates are discussed. Most of those characteristics are illustrated by the results of numerical simulations. © 2021 ieee.

关键词： K-means clustering

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 << < 458 459 460 461 462 463 464 465 466 467 > >>

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：