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

15,854 篇 会议
360 篇 期刊文献
193 册 图书

馆藏范围

16,407 篇 电子文献
0 种 纸本馆藏

日期分布

学科分类号

8,314 篇 工学
- 5,413 篇 计算机科学与技术...
- 2,985 篇 软件工程
- 2,163 篇 电气工程
- 1,860 篇 信息与通信工程
- 1,123 篇 控制科学与工程
- 880 篇 光学工程
- 644 篇 机械工程
- 637 篇 电子科学与技术（可...
- 539 篇 生物医学工程（可授...
- 538 篇 仪器科学与技术
- 477 篇 生物工程
- 225 篇 测绘科学与技术
- 217 篇 交通运输工程
- 201 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
- 159 篇 网络空间安全
- 140 篇 安全科学与工程
4,005 篇 理学
- 2,390 篇 物理学
- 1,355 篇 数学
- 527 篇 生物学
- 367 篇 统计学（可授理学、...
- 341 篇 系统科学
- 205 篇 化学
1,521 篇 医学
- 1,348 篇 临床医学
- 200 篇 特种医学
- 197 篇 基础医学(可授医学...
1,054 篇 管理学
- 612 篇 管理科学与工程(可...
- 481 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

2,779 篇 image processing
1,551 篇 image segmentati...
1,513 篇 signal processin...
867 篇 feature extracti...
656 篇 image edge detec...
634 篇 cameras
633 篇 signal processin...
609 篇 real-time system...
575 篇 image reconstruc...
517 篇 image coding
498 篇 algorithm design...
399 篇 clustering algor...
398 篇 deep learning
398 篇 image color anal...
381 篇 object detection
369 篇 image enhancemen...
354 篇 accuracy
334 篇 hardware
323 篇 image analysis
312 篇 computer vision

机构

39 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 ...
23 篇 national laborat...
22 篇 xi an jiao tong ...
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 department of el...
15 篇 school of automa...
15 篇 national key lab...
15 篇 school of comput...
14 篇 tsinghua univers...
14 篇 school of electr...

作者

39 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
14 篇 xi li
13 篇 de-shuang huang
13 篇 yanning zhang
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

16,103 篇 英文
159 篇 其他
132 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 16407 条记录，以下是661-670 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：

VLATTACK: Multimodal Adversarial Attacks on Vision-Language Tasks via Pre-trained Models 37

VLATTACK: Multimodal Adversarial Attacks on Vision-Language ...

引用

37th conference on Neural Information processing systems (NeurIPS)

作者： Yin, Ziyi Ye, Muchao Zhang, Tianrong Du, Tianyu Zhu, Jinguo Liu, Han Chen, Jinghui Wang, Ting Ma, Fenglong Penn State Univ University Pk PA 16802 USA Zhejiang Univ Hangzhou Peoples R China Xi An Jiao Tong Univ Xian Peoples R China Dalian Univ Technol Dalian Peoples R China SUNY Stony Brook Stony Brook NY USA

ISBN: (纸本)9781713899921

Vision-Language (VL) pre-trained models have shown their superiority on many multimodal tasks. However, the adversarial robustness of such models has not been fully explored. Existing approaches mainly focus on exploring the adversarial robustness under the white-box setting, which is unrealistic. In this paper, we aim to investigate a new yet practical task to craft image and text perturbations using pre-trained VL models to attack black-box fine-tuned models on different downstream tasks. Towards this end, we propose VLATTACK(2) to generate adversarial samples by fusing perturbations of images and texts from both single-modal and multimodal levels. At the single-modal level, we propose a new blockwise similarity attack (BSA) strategy to learn image perturbations for disrupting universal representations. Besides, we adopt an existing text attack strategy to generate text perturbations independent of the image-modal attack. At the multimodal level, we design a novel iterative cross-search attack (ICSA) method to update adversarial image-text pairs periodically, starting with the outputs from the single-modal level. We conduct extensive experiments to attack five widely-used VL pre-trained models for six tasks. Experimental results show that VLATTACK achieves the highest attack success rates on all tasks compared with state-of-the-art baselines, which reveals a blind spot in the deployment of pre-trained VL models.

关键词： Visual languages

来源：评论

学校读者我要写书评

暂无评论

Classification of pothole pavement based on pseudo-sample generation augmentation 12

Classification of pothole pavement based on pseudo-sample ge...

引用

12th International conference on Information systems and Computing Technology

作者： Zhang, Renye Wang, Huihan Xu, Sihang Yang, Bin Yang, Mengyun Hunan First Normal Univ Sch Comp Sci Changsha Hunan Peoples R China Shaoyang Univ Sch Mech & Energy Engn Shaoyang Hunan Peoples R China

ISBN: (纸本)9798350379860;9798350379877

Potholes can be a nuisance to the vehicle and can affect the decision-making of the intelligent driving system. However, most autonomous driving algorithms are currently trained using datasets collected from normal road conditions, as datasets containing pothole roads are scarce. This limitation reduces the robustness and sensitivity of autonomous driving algorithms in recognizing pothole pavement. To address the aforementioned limitation, we propose an Pseudo-Samples Generation strategy based on Improved Cycle Generative Adversarial Network (PSG-ICGAN) to enhance the model's accuracy in recognizing pothole pavement. In PSG-ICGAN, we enhance the adversarial sample generation algorithm of CycleGAN to produce pseudo-samples with highly similar semantic information to the original images, yet indistinguishable by the classification model. Adding these challenging pseudo-samples to the training dataset significantly enhances the model's robustness in recognizing pothole road images. In addition, we introduce a channel attention mechanism into the pothole classification model, which helps the model to capture subtle pothole features. Experiments show that our model achieves superior performance in the pothole road dataset.

关键词： Pothole image classification Sample generation Channel attention

来源：评论

学校读者我要写书评

暂无评论

Smart Painting Software and Cross-Border Fusion based on Digital image processing algorithms 3

Smart Painting Software and Cross-Border Fusion based on Dig...

引用

3rd International conference on Smart Electronics and Communication, ICOSEC 2022

作者： xi, Kang The School of Digital Media and Design Neusoft Institute Guangdong Foshan528000 China

ISBN: (数字)9781665497640

ISBN: (纸本)9781665497640

Smart painting software and cross-border fusion based on digital image processing algorithms is studied in this paper. Early non-deep methods use shallow network model architectures, which are difficult to effectively mine complex nonlinear semantic correlation information between multimodal data. Hence, the deep structure is considered as the basis of model design. Therefore, the traditional CG concept has entered the profession of art creation and design. CG illustration is the product of the combination of advanced technology and art, with its own timeliness and shocking visual impact. Further, the novel digital image processing algorithms are integrated to achieve a smart platform. The efficiency of the model is demonstrated by performing a performance analysis. © 2022 IEEE.

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

Detection of defects on the end face of small motor bearings based on machine vision 3

Detection of defects on the end face of small motor bearings...

引用

3rd International conference on Machine Vision, Automatic Identification, and Detection, MVAID 2024

作者： xie, xiaobo xi, Haixu Guo, Dan Jiangsu University of Science and Technology 1801 Zhongwu Avenue Jiangsu Province Changzhou213001 China

ISBN: (纸本)9781510681880

This paper focuses on the detection and identification of defects on the end faces of small motor bearings. Bearing defects significantly impact the performance and lifespan of motors, and traditional manual inspection methods suffer from low efficiency and high miss rates. This paper proposes the use of machine vision and image processing techniques to enhance the speed, efficiency, and reliability of detection. The study includes the analysis of common defect types on bearing end faces, the selection of industrial cameras and vision lighting, as well as image preprocessing and edge detection. By improving the YOLOv5 algorithm, the detection performance for small and medium-sized targets on bearing end faces is optimized. Moreover, a supervisory software for bearing defect detection has been designed to achieve more effective processing and statistical analysis of detection results. The primary goal of the research is to enhance the accuracy and automation level of detection, reduce the risk of omissions in manual inspections, and improve detection efficiency through the advancement of deep learning-based target detection algorithms. This research holds significant importance for the technological progress and production efficiency improvement in the small motor bearing industry. © 2024 SPIE.

关键词： Inspection

来源：评论

学校读者我要写书评

暂无评论

Real-time image Edge Detection System Design and algorithms for Artificial Intelligence FPGAs 2

Real-time Image Edge Detection System Design and Algorithms ...

引用

2nd IEEE International conference on Artificial Intelligence of Things and Crowdsensing, AIoTCs 2022

作者： Ye, Caizeng Shandong Institute of Commerce and Technology Jinan250103 China

ISBN: (纸本)9798350334104

Extraction of image edges is the basis of image processing class algorithms, for image edge extraction is of great significance. Nowadays, video image data is greatly increases the amount of image data and the processing difficulty. FPGA technology stands out for its parallel processing method and pipeline structure, which enables high-speed processing of large amounts of image data, and its high processing speed ensures real-time image data processing. The application of FPGA technology in the field of image data processing will be unstoppable. The main objective of this paper is to investigate the design and algorithms of a real-time image edge detection system using artificial intelligence and FPGAs. Median filtering and edge detection algorithms in video acquisition and pre-processing systems are an important part of complex algorithms in the field of target recognition and tracking, and the quality of image pre-processing plays an important role in the high accuracy of subsequent algorithms. This paper presents an in-depth study and analysis of the hardware implementation of the HD video capture and pre-processing system, combining the characteristics of FPGA parallel high-speed and pipeline structure, and completes the system design and verification on the hardware platform, fully proving the feasibility and correctness of the system. © 2022 IEEE.

关键词： Field programmable gate arrays (FPGA)

来源：评论

学校读者我要写书评

暂无评论

Intelligent Detection of Insulator Defects on Transmission Lines in Complex Backgrounds based on Improved DETR Visual Perception Model

Intelligent Detection of Insulator Defects on Transmission L...

引用

2024 International conference on Artificial Intelligence and Power systems, AIPS 2024

作者： Tang, Songping Zhu, Ruifeng Ji, Chao Li, Chong Dong, Yuxi Zhang, Yun Liu, Junpeng Huizhou PowerSupply Bureau of Guangdong Power Grid Co. Ltd. Huizhou516000 China Xi'An Polytechnic University Xi'an710048 China

ISBN: (纸本)9798350392210

The problem of insulator defects in transmission lines caused by adverse environmental conditions poses a significant risk to the safe and stable operation of the power system. In order to improve upon traditional methods of inspecting transmission lines in real-time, this article proposes an optimized detection method based on the Detection Transformer (DETR) algorithm. With the aim of achieving a more intelligent detection of transmission lines, unmanned aerial vehicles (UAVs) are employed for line inspections. Firstly, the insulator images captured by UAV inspections are processed to remove fog and noise, enhancing their clarity. Subsequently, a hybrid attention mechanism module is introduced into the backbone network ResNet50 of the DETR algorithm to reduce data processing errors. Insulator defect data is annotated using LabelImg software and saved according to the Pascal VOC standard dataset. Finally, the annotated data is input into the improved DETR algorithm for feature data training, generating an optimal image neural network detection model capable of intelligently detecting insulators in transmission lines amidst complex backgrounds. © 2024 IEEE.

关键词： Unmanned aerial vehicles (UAV)

来源：评论

学校读者我要写书评

暂无评论

A Novel image Captioning Approach Using CNN and MLP 1

引用

5th International conference on Data and Information Sciences, ICDIS 2023

作者： Sharma, Swati Tomar, Vivek Yadav, Neha Aggarwal, Mukul KIET Group of Institutions Ghaziabad India Dehradun India

ISBN: (数字)9789819969067

ISBN: (纸本)9789819969050

Computer vision and natural language processing researchers have dedicated significant time and energy to the problem of automatically creating image descriptions. In this work, we propose an artificially intelligent picture captioner built on a hybrid architecture of convolutional neural networks (CNNs) and multilayer perceptron (MLPs). This system will take photographs as input and generate captions based on those images using algorithms from convolutional neural networks (CNN), multilayer perception (MLP), recurrent neural networks (RNN). To generate a natural language caption, CNN first extracts feature from the input image, and then the MLP analyses these features. The proposed model is trained on a dataset of photos with captions by optimizing the parameters of a convolutional neural network (CNN) and a multilayer perceptron (MLP) via a hybrid of supervised learning and reinforcement learning. Our results demonstrate that the suggested model may produce captions that are on par with the best methods currently available in terms of accuracy and variety. The artificially intelligent picture captioner has potential uses in many areas, such as social networking, e-commerce, and image retrieval systems. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd 2024.

关键词： Recurrent neural networks

来源：评论

学校读者我要写书评

暂无评论

Super-resolution computational ghost imaging for long-range active detection 18

Super-resolution computational ghost imaging for long-range ...

引用

18th IEEE conference on Industrial Electronics and Applications, ICIEA 2023

作者： Wei, Shiyang Li, Qing xiong, Zijun Liu, Lei Northwestern Polytechnical University Shaanxi Aerospace Flight Vehicle Design Key Laboratory School of Astronautics Xi'an China

ISBN: (纸本)9798350312201

Long-range active detection is widely demanded in various fields. Currently, it is still difficult to obtain high-resolution images in long-range while ensuring miniaturization of the detection system, because the resolution of photodetector-based detection systems is limited by the aperture of the optic system and the sampling frequency of the photodetector. Furthermore, the existing super-resolution algorithms are limited by the Nyquist sampling theorem. Alternatively, super-resolution computational ghost imaging is utilized to overcome the above problems and to meet the requirements of imaging resolution in the long-range active detection system. This paper aims to verify the feasibility of super-resolution computational ghost imaging applied to long-range active detection. First, we establish the light transmission model based on scalar diffraction theory. Then, we investigate the resolution of the imaging system and finally verify the proposed computational ghost imaging method by simulation and equivalent experiments. It is concluded from the above study that super-resolution computational ghost imaging can be applied to long-range active detection. It provides a feasible technical means for the miniaturization of long-range active detection systems. Furthermore, in the image processing of the equivalence experiment, it was found that the image reconstructed by the ghost imaging (GI) algorithm can suppress the background noise of the image reconstructed by the compressive sensing ghost imaging (CSGI) algorithm. © 2023 IEEE.

关键词： Photodetectors

来源：评论

学校读者我要写书评

暂无评论

Enhanced Text-to-image Synthesis Using Generative Adversarial Networks and Skip-Thought Vectors for Improved Visual and Semantic Accuracy

Enhanced Text-to-Image Synthesis Using Generative Adversaria...

引用

2024 International conference on Intelligent algorithms for Computational Intelligence systems, IACIS 2024

作者： Monisha, D. Keerthana, D.R. Manoj Kumar, M.V. Prashanth, B.S. Sneha, H.R. Puneeth, B.H. Nitte Meenakshi Institute of Technology Department of Information Science & Engineering Karnataka Bangalore560064 India Bapuji Institute of Engineering and Technology Department of Computer Science and Business Systems Karnataka Davanagere577004 India

ISBN: (数字)9798350360660

ISBN: (纸本)9798350360660

Creating realistic images from textual descriptions is a major challenge in computer vision and natural language processing. Traditional methods often fail to accurately translate text into visual representations, resulting in images that lack detail and context. This study addresses this issue by combining Generative Adversarial Networks (GANs) with Skip-Thought *** proposed approach involves three key stages. First, textual descriptions are embedded using Skip-Thought Vectors, which utilize a Recurrent Neural Network (RNN) encoder with Gated Recurrent Unit (GRU) activation to capture semantic nuances. Next, low-resolution images are generated using GANs, providing a basic visual structure. Finally, these images are refined to high resolution to ensure they are detailed and contextually *** method was validated using the Caltech-UCSD Birds 200 (CUB-200) dataset, showing notable improvements in both visual quality and semantic accuracy over previous methods. This approach enables the generation of detailed and contextually relevant images from text, with potential applications in design, storytelling, e-commerce, and *** automating the generation of high-quality images from text, this research enhances user experience and opens new possibilities for creative and practical uses, marking a significant advancement in the integration of computer vision and natural language processing. © 2024 IEEE.

关键词： Generative adversarial networks

来源：评论

学校读者我要写书评

暂无评论

image Super-Resolution Based on Frequency Division Generative Adversarial Network 4

Image Super-Resolution Based on Frequency Division Generativ...

引用

4th International conference on Natural Language processing, ICNLP 2022

作者： Xu, Jian Gao, Qiannan Xi'an China

ISBN: (数字)9781665495448

ISBN: (纸本)9781665495448

Most supervised super-resolution (SR) algorithms require paired high-resolution (HR) and low-resolution (LR) images as training samples. However, the network structures trained by supervised algorithms don't adapt to different image degradations and it is difficult to find paired HR and LR images in real world. In this paper, a new unsupervised image SR algorithm based on generative adversarial network (GAN) is proposed. (1) A new network that can be trained with unpaired HR and LR images is proposed. (2) An intermediate process is proposed so that network contains two GANs, the first learns LR degradation, and the second performs SR procedure. (3) The idea of frequency division training is adopted in LR degradation and SR procedures: low frequency of image is preserved and only high frequency is learned. Experimental results on different datasets show that proposed algorithm provide a better balance between visual quality of SR reconstructed images and computational cost when compared with the state-of-the-art SR algorithms. © 2022 IEEE.

关键词： Generative adversarial networks

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 << < 63 64 65 66 67 68 69 70 71 72 > >>

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：