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

6,791 篇 会议
95 篇 期刊文献
35 册 图书

馆藏范围

6,921 篇 电子文献
0 种 纸本馆藏

日期分布

学科分类号

3,682 篇 工学
- 2,607 篇 计算机科学与技术...
- 1,542 篇 信息与通信工程
- 1,363 篇 软件工程
- 935 篇 电气工程
- 464 篇 光学工程
- 345 篇 控制科学与工程
- 244 篇 生物工程
- 222 篇 电子科学与技术（可...
- 203 篇 生物医学工程（可授...
- 174 篇 网络空间安全
- 133 篇 机械工程
- 106 篇 仪器科学与技术
- 93 篇 安全科学与工程
- 89 篇 材料科学与工程（可...
- 84 篇 化学工程与技术
- 84 篇 交通运输工程
- 70 篇 建筑学
- 70 篇 土木工程
- 67 篇 动力工程及工程热...
1,359 篇 理学
- 860 篇 物理学
- 410 篇 数学
- 263 篇 生物学
- 101 篇 统计学（可授理学、...
- 76 篇 化学
1,145 篇 医学
- 1,116 篇 临床医学
- 83 篇 基础医学(可授医学...
493 篇 管理学
- 266 篇 图书情报与档案管...
- 252 篇 管理科学与工程(可...
- 59 篇 工商管理
70 篇 法学
- 65 篇 社会学
29 篇 农学
25 篇 经济学
23 篇 教育学
23 篇 文学
17 篇 军事学
1 篇 艺术学

主题

1,009 篇 visualization
573 篇 image processing
517 篇 image coding
485 篇 feature extracti...
421 篇 deep learning
403 篇 image segmentati...
380 篇 accuracy
364 篇 visual communica...
343 篇 training
247 篇 computational mo...
229 篇 image enhancemen...
224 篇 signal processin...
187 篇 image color anal...
184 篇 image edge detec...
175 篇 image reconstruc...
169 篇 convolutional ne...
160 篇 three-dimensiona...
159 篇 real-time system...
159 篇 semantics
157 篇 object detection

机构

43 篇 shanghai jiao to...
35 篇 institute of ima...
29 篇 shanghai jiao to...
28 篇 university of sc...
28 篇 beijing universi...
26 篇 school of electr...
17 篇 university of el...
16 篇 shanghai jiao to...
16 篇 tianjin univ sch...
15 篇 university of ch...
14 篇 shanghai jiao to...
13 篇 zhejiang univers...
13 篇 peng cheng labor...
13 篇 moscow technical...
13 篇 school of commun...
12 篇 univ sci & techn...
12 篇 tsinghua univ de...
11 篇 school of remote...
11 篇 school of electr...
11 篇 peking universit...

作者

42 篇 zhai guangtao
27 篇 song li
27 篇 sumei li
26 篇 guangtao zhai
25 篇 andré kaup
22 篇 li sumei
20 篇 li li
18 篇 li song
18 篇 min xiongkuo
17 篇 xiongkuo min
17 篇 dong liu
14 篇 chen zhibo
14 篇 xie rong
12 篇 yang yang
12 篇 yang xiaokang
12 篇 shan liu
11 篇 liu dong
11 篇 jürgen seiler
11 篇 heming sun
11 篇 chen chen

语言

6,662 篇 英文
195 篇 其他
114 篇 中文
50 篇 土耳其文

检索条件"任意字段=2024 Conference on Visual Communications and Image Processing"

共 6921 条记录，以下是41-50 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：

Learning Multi-semantic Based on Cross-Attention for image-Text Retrieval 7th

Learning Multi-semantic Based on Cross-Attention for Image-T...

引用

8th Asia Pacific Web and Web-Age Information Management Joint International conference on Web and Big Data

作者： Lu, Bo Gao, Ying Zhao, Tianbao Yuan, Xia Zhu, Haibin Gan, Lin Duan, Xiaodong Dalian Minzu Univ Dalian 116650 Peoples R China

ISBN: (纸本)9789819600540;9789819600557

Cross-modal retrieval is a challenging problem for processing multi-modal information, primarily addressing the semantic gap between different modalities. However, current research mainly focuses on aligning image and text regions, which often ignore the importance of contextual background information. Specially, there are uncertainties among heterogeneous modalities which persist in understanding semantic information of cross-modal retrieval. In this paper, we propose a novel MultiSemantic Based on Cross-Attention Network (MSCA) for cross-modal retrieval tasks. Specifically, a cross-extraction of contextual semantic feature encoder module and a graph structure enhancement module are firstly designed to more effectively address the issue of neglecting contextual background information and to further enhance the fusion of information and features, respectively. Secondly, we effectively solve the cross-modal alignment problem by employing a probability distribution encoder, simultaneously, we integrate three pre-training models, which include image-text contrastive learning, image-text matching loss and masked language model loss for reducing uncertainties among different modalities. We conducted extensive experiments on two large datasets, MS-COCO and Flickr30K. The experimental results show that the MSCA model outperforms other existing methods on both datasets, demonstrating its effectiveness and significant performance advantages.

关键词： image-Text Retrieval Feature Fusion Coarse-Grained Alignment Fine-Grained Alignment

来源：评论

学校读者我要写书评

暂无评论

Joint Dehazing and Low-light image Enhancement with Complete Atmospheric Model 16

Joint Dehazing and Low-light Image Enhancement with Complete...

引用

16th International conference on Signal processing Systems, ICSPS 2024

作者： Wu, Yong Xia, Kexiang Ge, Liyong Ye, Jiongkai Zhejiang Institute of Communications Hangzhou311112 China The School of Automation Hangzhou Dianzi University Hangzhou310000 China

ISBN: (纸本)9781510689251

Current image dehazing algorithms often encounter issues of contrast reduction and color distortion in the shadow regions of images. To address this challenge, this paper proposes a comprehensive atmospheric model that simultaneously considers haze and low-light conditions. This model incorporates a global darkness factor as a disturbance variable alongside the atmospheric scattering model, enabling adaptive luminance balancing without the need to estimate the global atmospheric light or the global darkness factor. Building on the principle of object color rendition, This paper justifies the use of the dark channel prior for haze removal and extends the bright channel prior for low-light image enhancement. Furthermore, we explore the mapping relationship between normal and inverted images based on the complete atmospheric model. By solving for the transmission rates of the global atmospheric light and global darkness factor, we propose an image enhancement algorithm capable of concurrently processing haze and low-light images. The proposed algorithm effectively mitigates issues of contrast reduction and color distortion. Experimental results demonstrate the efficacy of our approach, showing that the visual outcomes of simultaneous haze removal and low-light enhancement surpass those achieved through single-task haze removal. © 2025 SPIE.

关键词： Demulsification

来源：评论

学校读者我要写书评

暂无评论

WGID: wavelet-guided iterative detail enhancement diffusion models for zero-shot image super-resolution 16

WGID: wavelet-guided iterative detail enhancement diffusion ...

引用

2024 16th International conference on Graphics and image processing, ICGIP 2024

作者： Lu, Junjie Liu, Hongyi Wei, Zhihui Nanjing University of Science and Technology Nanjing210094 China

ISBN: (数字)9781510688780

ISBN: (纸本)9781510688773

Zero-shot image super-resolution methods have attracted considerable attention due to their high potential for applications with few additional training data. However, these methods often encounter challenges such as inconsistent results and blurred details. To mitigate these issues, we propose WGID: Wavelet-Guided Iterative Detail Enhancement Diffusion Models for single-image super-resolution. In this method, diffusion iteration is guided by wavelet transform to enhance details across different scales while maintaining the similarity between the reference and diffusion-generated images. In addition, the reference images are dynamically updated to provide a suitable guidance during the diffusion process. Meanwhile, the diffusion model progressively refines details, suppresses noise and preserves the natural appearance of the generated image. By integrating these two techniques, the proposed method produces reconstructed super-resolution image with enhanced visual quality, clear details, and more realistic results, accompanied by improved assessment metrics. © 2025 SPIE.

关键词： Wavelet transforms

来源：评论

学校读者我要写书评

暂无评论

Computer System of Evaluation of the Mass Exam Results Based on Recognition of Handprinted Azerbaijani Characters 2nd

Computer System of Evaluation of the Mass Exam Results Based...

引用

2nd International conference on Information Technologies and Their Applications

作者： Mustafayev, Elshan Azimov, Rustam Inst Control Syst Lab Recognit Identificat & Methods Optimal Solut Baku Azerbaijan

ISBN: (纸本)9783031734199;9783031734205

The utilization of pattern recognition is on the rise extensively in information systems. The convergence of progress in image processing and the accessibility of open-source libraries enables the implementation of innovative solutions for diverse practical problems. One notable challenge pertains to automatically processing responses in mass large-scale exams. This paper introduces a developed system tailored for recognizing such exam results, showcasing its capacity to deliver dependable, effective, and impartial assessments. This system can be configured on almost any type of form. Its use also allows you to abandon the expensive and difficult to use OMR scanners. To increase productivity of system we propose to use the multicore/multithreading property of modern processors to parallelize processes within a single workstation. As a result of experiments, itwas found that the transition to multi-threaded recognition can increase productivity up to 3.5 times in comparison with single-threaded. To reduce the physical size of exam cards, it is proposed to fill in the answers with handwritten symbols instead of filling in the circles. Multilayer and convolutional neural networks were used as a recognition module. A comparative evaluation of the dependence of recognition results on the architecture of neural networks and the feature extraction algorithm was carried out.

关键词： Evaluation of Exam Results Intelligent System Information processing Multithreading Recognition image processing OCR

来源：评论

学校读者我要写书评

暂无评论

ReVisE: Emulated visual Outfit Generation from User Reviews Using Generative-AI 33rd

ReVisE: Emulated Visual Outfit Generation from User Reviews ...

引用

33rd International conference on Software and Data Engineering

作者： Rosas, Samar Rahimi Neupane, Subash Mitra, Shaswata Mittal, Sudip Mississippi Sch Math & Sci Columbus MS 39701 USA Mississippi State Univ Dept Comp Sci & Engn Starkville MS USA

ISBN: (纸本)9783031752001;9783031752018

The fashion industry faces significant challenges due to overproduction and waste, often driven by uncertainty about consumer preferences. This paper presents ReVisE, a novel framework leveraging generative AI to address this issue by emulating outfit generation from user reviews. ReVisE combines a text-to-text Large Language Model (LLM) and a text-to-image Stable Diffusion (SD) model to create virtual outfits based on customer feedback. The LLM consolidates user reviews to extract desired improvements and feedback, and the SD model utilizes these insights to produce realistic visual representations of the improved product. Our framework allows designers to evaluate potential designs and identify areas for improvement without physically producing multiple prototypes, thereby reducing waste and accelerating the design process. Experimental results conducted on the Amazon fashion item reviews demonstrate the effectiveness of ReVisE, showing promising results with both multimodal and human evaluations.

关键词： Outfit generation Generative AI LLM Text-to-Text Text-to-image Stable diffusion

来源：评论

学校读者我要写书评

暂无评论

Bibliometric Analysis of Road Distress Detection Based on Citespace 24

Bibliometric Analysis of Road Distress Detection Based on Ci...

引用

5th International conference on Computer Science and Management Technology, ICCSMT 2024

作者： Li, Yaoye Zhang, Yinbo He, Rong Ma, Lianxia Chen, Fang Xinjiang communications Construction Group Co. Ltd. Xinjiang Urumqi China Xinjiang Key Laboratory of Transportation Prefabricated Construction and Maintenance Xinjiang Urumqi China Xinjiang University Xinjiang Urumqi China

ISBN: (纸本)9798400709999

To analyze the research progress in the field of road disease detection, this article searched the Web of Science Core Collection database for papers related to road disease detection from 2000 to *** CiteSpace software, a visual analysis was conducted on the 247 retrieved documents, focusing on annual publication numbers, publishing countries, core institutions and authors, keywords, burst words, and timeline mapping to explore the current status and trends in this *** findings indicate that since 2004, the overall research trend in road disease detection has been on an upward trajectory, with a notable increase in the number of research papers published in 2021, reflecting a significant surge in research ***, China, the United States, and Italy have been the most prolific in research *** leading research institutions are primarily scientific and technological academies, with Chang'an University taking a dominant position in the field of road disease *** keyword co-occurrence analysis, burst detection, and keyword clustering analysis, it was determined that disease detection technology, deep learning and machine learning, image processing and intelligent analysis, and system integration and development have been the research hotspots in the road disease detection field from 2000 to *** is anticipated that future research will evolve towards the directions of performance evaluation, multimodal data fusion, and real-time monitoring and analysis. © 2024 Copyright held by the owner/author(s). Publication rights licensed to ACM.

关键词： Data fusion

来源：评论

学校读者我要写书评

暂无评论

Application of image Recognition Algorithm in Positioning and Emergency Call Function of Smart Safety Helmets 24

Application of Image Recognition Algorithm in Positioning an...

引用

3rd International conference on Signal processing, Computer Networks and communications, SPCNC 2024

作者： Zhang, Dongdong Zhang, Kan Li, Yong Cui, Yichen Zheng, Ke Liu, Yafei Marketing Service Center of State Grid Henan Electric Power Company Henan Zhengzhou China

ISBN: (纸本)9798400710834

In terms of ensuring the safety of construction workers and cyclists, traditional positioning methods often rely on GPS signals, but the accuracy of GPS positioning is limited indoors or in signal-blocked areas. At the same time, the traditional way of asking for help may delay the rescue time due to cumbersome operation, noisy environment or psychological pressure in emergency situations. To address these problems, this paper first integrates high-definition cameras, sensors and wireless communication modules on the smart safety helmet (SSH). The captured image is then preprocessed by noise reduction, enhancement, cropping, etc., and key features such as facial features are identified through CNN. The extracted features are then matched and analyzed, and compared with pre-stored map data, landmark databases, etc. At the same time, CNN is used to identify safety signs in the image to determine whether the wearer is in a dangerous environment. The research results found that the average error of CNN-based positioning technology is 1.32 meters, which is significantly lower than the 3.56 meters of traditional GPS technology. In terms of the response time of the rescue function, the average response time of CNN-based technology is 500.5 milliseconds, and the rescue success rate is also significant. improve. Therefore, this study concludes that CNN can improve the positioning accuracy and rescue response speed of SSHs, improve rescue efficiency and safety, and show great potential in the field of safety. © 2024 Copyright held by the owner/author(s).

关键词： Noise abatement

来源：评论

学校读者我要写书评

暂无评论

Research on surface defect detection technology of power equipment based on image processing

Research on surface defect detection technology of power equ...

引用

2024 International conference on Physics, Photonics, and Optical Engineering, ICPPOE 2024

作者： Yuan, Jiayi Dong, Lili Zhu, Hui Wang, Ji Wang, QiMin Shandong University of Technology Zibo Shandong255000 China State Grid Liaocheng Power Supply Company Liaocheng Shandong252000 China

ISBN: (数字)9781510689121

ISBN: (纸本)9781510689114

In power equipment operations, ensuring reliable and safe functioning depends heavily on effective surface defect detection. This paper presents an image-processing-based solution that enhances surface defect detection for electrical equipment by refining the Simple Linear Iterative Clustering (SLIC) algorithm. First, a guided filter is applied to infrared images to improve contrast and clarity while preserving edge information. This preprocessing step facilitates better feature extraction by reducing noise and maintaining important image details. Next, the improved SLIC algorithm segments the filtered images into superpixel blocks with similar characteristics, which helps isolate and precisely mark defect areas on electrical equipment surfaces. By accurately partitioning the image, the method enables clear identification of fault regions, making it more straightforward to diagnose and address defects. This enhanced segmentation approach thus contributes significantly to maintaining the safety and reliability of power equipment under a wide range of operational conditions. On the test set, the method improves the boundary recall rate, and effectively improves the visual effect of generating super pixel shape size, and verifies the effectiveness and feasibility of the method in the surface defect detection of electrical equipment. In summary, the image processing-based surface defect detection technology of power equipment proposed in this study has important application prospects. Through the pretreatment of infrared image and the improved algorithm segmentation, the fault area of electrical equipment can be accurately located and marked, which provides strong support for equipment maintenance and repair. In the future, we will further explore and optimize this method, improve its application effect in the field of power equipment, and promote the development of intelligence and automation of power equipment. © 2025 SPIE.

关键词： image segmentation

来源：评论

学校读者我要写书评

暂无评论

Efficient LED image reflection removal via mixture-of-experts

Efficient LED image reflection removal via mixture-of-expert...

引用

2024 International conference on Computer Vision and image processing, CVIP 2024

作者： Yao, Ziyu Sun, Xinzhong Wang, Liqiang Zhao, Lihong Zhang, Kai Lin, Junjie Wang, Yong Zou, Yuexian School of Electronic and Computer Engineering Peking University Beijing China Shenzhen AOTO Electronics Co. Ltd. Shenzhen China

ISBN: (纸本)9781510688384

Recently, XR virtual shooting has developed rapidly, with LED displays playing a pivotal role in promoting the prosperity of the film and television industry. However, the necessity for additional lighting to achieve fill light often results in specular or diffuse reflections from the LED displays, which can be prominently visible in the video data, thus affecting the overall visual quality. Meanwhile, given the strict time constraints in most XR scenes, lightweight approaches are indispensable. To benchmark single reflection removal of LED image, we collect and introduce a new dataset named AOTO Denoising Dataset, comprising 5500 LED images with white reflection areas. Furthermore, we propose a novel lightweight denoising model called MoE-LED-light for efficient LED image reflection removal. Specifically, we innovatively adopt the proposed mixture-of-experts strategy to enhance the performance of reflection removal without compromising inference efficiency. Experimental results on our AOTO denoising dataset and four public datasets have demonstrated that our MoE-LED-light model not only effectively eliminates white reflection areas in images but also achieves efficient performance, operating at over 50 frames per second. © 2025 SPIE.

关键词： Light emitting diodes

来源：评论

学校读者我要写书评

暂无评论

9th International conference on image processing and communications, IP and C 2017

9th International Conference on Image Processing and Communi...

引用

9th International conference on image processing and communications, IP and C 2017

ISBN: (纸本)9783319687193

The proceedings contain 22 papers. The special focus in this conference is on image processing and communications. The topics include: Binary line oriented histogram;image search enhanced by using external data sources and reasoning;linguistic description of images based on fuzzy histograms;using toboggan segmentation in detection of centers and radius of cell nuclei;evaluation of the pre-processing methods in image-based palmprint biometrics;on the way to perfect steganography;PET waste classification method and plastic waste database – wadaba;estimation of geometrical deformations of 3D prints using local cross-correlation and monte carlo sampling;quality assessment of 3D printed surfaces in fourier domain;the adaboost algorithm with linear modification of the weights;evaluation of hashing methods performance on binary feature descriptors;efficient parallelization methods of labeling algorithm;modeling telecommunication networks with the use of reference graphs;QoS concept for protecting network resources - a case study;acceleration of genome sequencing with intelligent cloud brokers;learning management systems on blended learning courses;technology and software for calculating correct normalization of correlation functions;running sports decision aid tool based on reinforcement learning approach;framework for evaluating QoE for remote control of autonomous cars in mobile wireless networks;practical advices for university teachers and comparison of visual descriptors for 3D reconstruction of non-rigid planar surfaces.

关键词：

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 << < 1 2 3 4 5 6 7 8 9 10 > >>

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：