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

4,884 篇 会议
91 篇 期刊文献
21 册 图书

馆藏范围

4,996 篇 电子文献
0 种 纸本馆藏

日期分布

学科分类号

2,835 篇 工学
- 1,763 篇 计算机科学与技术...
- 1,191 篇 信息与通信工程
- 935 篇 软件工程
- 878 篇 电气工程
- 274 篇 光学工程
- 139 篇 控制科学与工程
- 129 篇 电子科学与技术（可...
- 124 篇 生物工程
- 103 篇 生物医学工程（可授...
- 99 篇 仪器科学与技术
- 85 篇 机械工程
- 68 篇 网络空间安全
- 45 篇 化学工程与技术
- 30 篇 安全科学与工程
- 27 篇 动力工程及工程热...
- 26 篇 测绘科学与技术
1,207 篇 医学
- 1,186 篇 临床医学
- 34 篇 基础医学(可授医学...
- 31 篇 药学(可授医学、理...
- 28 篇 特种医学
1,056 篇 理学
- 755 篇 物理学
- 299 篇 数学
- 138 篇 生物学
- 84 篇 统计学（可授理学、...
- 53 篇 系统科学
- 50 篇 化学
254 篇 管理学
- 161 篇 管理科学与工程(可...
- 100 篇 图书情报与档案管...
47 篇 军事学
- 45 篇 军队指挥学
38 篇 法学
- 34 篇 社会学
14 篇 农学
10 篇 文学
8 篇 经济学
7 篇 教育学
2 篇 艺术学

主题

562 篇 image coding
549 篇 image processing
354 篇 visual communica...
326 篇 visualization
308 篇 feature extracti...
298 篇 image segmentati...
189 篇 image reconstruc...
181 篇 cameras
178 篇 image compressio...
175 篇 humans
161 篇 video coding
161 篇 signal processin...
131 篇 image enhancemen...
131 篇 image quality
127 篇 image analysis
127 篇 image color anal...
125 篇 image edge detec...
122 篇 training
119 篇 image retrieval
107 篇 decoding

机构

36 篇 shanghai jiao to...
29 篇 institute of ima...
25 篇 school of electr...
22 篇 school of electr...
20 篇 university of sc...
18 篇 shanghai jiao to...
16 篇 shanghai jiao to...
16 篇 tianjin univ sch...
16 篇 beijing universi...
13 篇 institute of ima...
12 篇 cas key laborato...
11 篇 university of el...
11 篇 tsinghua univ de...
10 篇 univ sci & techn...
10 篇 school of comput...
10 篇 peking univ inst...
10 篇 tsinghua univ de...
10 篇 xidian univ sch ...
9 篇 zhejiang univers...
9 篇 microsoft res as...

作者

34 篇 zhai guangtao
26 篇 sumei li
25 篇 song li
22 篇 guangtao zhai
22 篇 li sumei
19 篇 li song
18 篇 li li
18 篇 min xiongkuo
16 篇 andré kaup
16 篇 dong liu
16 篇 shan liu
15 篇 yang xiaokang
14 篇 chen zhibo
14 篇 gao wen
13 篇 xie rong
13 篇 xiongkuo min
12 篇 kaup andre
11 篇 heming sun
11 篇 zhibo chen
11 篇 zhenzhong chen

语言

4,898 篇 英文
64 篇 土耳其文
31 篇 中文
20 篇 其他

检索条件"任意字段=Conference on Visual Communications and Image Processing 2007"

共 4996 条记录，以下是651-660 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 Denoising Using a Deep Auto-encoder Approach Based on Beetle Antennae Search Algorithm 1

引用

2nd International conference on Computer and Communication Engineering, CCCE 2022

作者： Xiang, Qian Zhu, Peng College of Information Science and Engineering Wuchang Shouyi University Wuhan China

ISBN: (数字)9783031174223

ISBN: (纸本)9783031174216

image will be polluted by different kinds of noise in the process of acquisition, compression, and transmission, resulting in interference to subsequent image segmentation, feature extraction and other processing. With the development of deep convolutional neural network (DCNN), quite a few effective DCNNs have been designed and have made remarkable progress in image denoising. Gradient descent algorithm is generally used for DCNN training. However, due to the complex mathematical properties of the high-dimensional and non-convex loss optimization surface, there are often many local optimal points, saddle points or large range of gradient gentle regions, which affects training effect of the gradient descent algorithm. Although intelligent algorithms such as evolutionary algorithm have global optimization capability, they often have large computing resource requirements and slow convergence speed, which limit its application in DCNN training which is a high-dimensional optimization problem. Beetle antennae search (BAS) algorithm is a simple and efficient bionic intelligent optimization algorithm, which has global search ability. In this paper, the gradient descent method and BAS method are combined as a hybrid method for deep auto-encoder (DAE) denoising network training. Experimental results show that the proposed method accelerates the training speed of the DAE denoising network, reduces the blurring of edge details and improves the visual effect of the restored image. © 2022, The Author(s), under exclusive license to Springer Nature Switzerland AG.

关键词： image enhancement

来源：评论

学校读者我要写书评

暂无评论

Adaptive Multi-Feature Extraction Graph Convolutional Networks for Multimodal Target Sentiment Analysis

Adaptive Multi-Feature Extraction Graph Convolutional Networ...

引用

2022 IEEE International conference on Multimedia and Expo, ICME 2022

作者： Xiao, Luwei Zhou, Ejian Wu, Xingjiao Yang, Shuwen Ma, Tianlong He, Liang School of Computer Science and Technology East China Normal University Shanghai China East China Normal University Shanghai Key Laboratory of Multidimensional Information Processing Shanghai China

ISBN: (数字)9781665485630

ISBN: (纸本)9781665485630

The multi-modal target-oriented sentiment analysis aims at predicting the sentiment polarities for target entities in a sentence by combining vision and language information. However, most existing deep learning approaches fail to extract valuable information from the visual modality and ignore the usability of syntactic dependency information embedded in the text modality. In this paper, we propose a two-stream adaptive multi-feature extraction graph convolutional networks (AME-GCN), which translates the image into a textual caption and dynamically fuses the semantic and syntactic feature from the given sentence and generated caption to model the inter/intra-modality dynamics. Extensive experiments on two multi-modal Twitter datasets show the effectiveness of the proposed model against popular textual and multi-modal approaches, demonstrating that AME-GCN is a best alternative for this task. © 2022 IEEE.

关键词： Sentiment analysis

来源：评论

学校读者我要写书评

暂无评论

3D image visual Communication Optimization System on Account of image processing Technology

3D Image Visual Communication Optimization System on Account...

引用

Mobile Networks and Wireless communications (ICMNWC), IEEE International conference on

作者： Hongbo Sun Changchun Humanities and Sciences College Changchun Jilin China

ISBN: (纸本)9781665491129

As an efficient tool in the new era, computer plays a great role in image processing, video production and development. In the 21st century, the application field of image technology is more extensive, and image technology has also become an important direction of intelligent development. The research on image technology no longer stays in the laboratory. More and more enterprises have also joined the research and application of image technology, and achieved certain results in the fields of object recognition, target tracking, work piece detection and so on. This paper studies the content and knowledge of the design of 3D image visual communication optimization system based on image processing technology, explains the process and technology of film and television image processing and optimization, and expounds the process of system optimization and data analysis in detail. Through the effect analysis of data samples, the test effect shows that with the help of image processing technology, this system has good processing effect in the field of video and image, and has professional processing effect in many aspects of image and video.

关键词： Wireless communication Three-dimensional displays visual communication image processing Symbols Input devices Blockchains

来源：评论

学校读者我要写书评

暂无评论

Design and Implementation of image Recognition System Based on AI Intelligent Video Technology

Design and Implementation of Image Recognition System Based ...

引用

Data Analytics, Computing and Artificial Intelligence (ICDACAI), International conference on

作者： Qingrong Huang China Mobile Communications Group Fujian Co. Ltd. Fuzhou Fujian China

Based on the research of AI (Artificial Intelligence) technology and image recognition technology, this article designed a monitoring and recognition system around the principle of universality. image data collection is achieved by using external devices such as scanners to digitize and store data; image preprocessing is the enhancement processing of scanned images to achieve a certain degree of visual change to meet certain requirements. The main work includes: image gray correction (histogram equalization, linear and nonlinear transformation of histogram), image noise reduction, and image tilt correction; the image segmentation and recognition part can achieve dynamic cutting of images, and extract images of specific regions, thus analyzing and processing them to obtain accurate information. In image recognition rate monitoring, the recognition rate of personnel leaving the monitoring range without permission was 94%. The system used in this article met the predetermined requirements of the design.

关键词：

来源：评论

学校读者我要写书评

暂无评论

visual Analysis Motivated Super-Resolution Model for image Reconstruction

Visual Analysis Motivated Super-Resolution Model for Image R...

引用

IEEE visual communications and image processing (VCIP)

作者： Huifen Wang Junda Xue Mingchuan Yang Yuan Zhang College of Big Data and Artificial Intelligence China Telecom Research Institute Shanghai China College of Big Data and Artificial Intelligence China Telecom Research Institute Beijing China College of Information Science and Electronic Engineering Zhejiang University College of Big Data and Artificial Intelligence China Telecom Research Institute Hangzhou China

ISBN: (纸本)9781665475938

This paper presents a concise end-to-end visual analysis motivated super-resolution model VASR for image reconstruction. Compatible with the existing machine vision feature coding framework, the features extracted from the machine vision task model are super-resolution amplified to reconstruct the original image for human vision. The experimental results show that without additional bit-streams, VASR can well complete the task of image reconstruction based on the extracted machine features, and has achieved good results on COCO, Openimages, TVD, and DIV2K datasets.

关键词： Training visualization Analytical models image coding visual communication Machine vision Superresolution

来源：评论

学校读者我要写书评

暂无评论

Leveraging visual Language Information for Enhanced Person Re-Identification: A Robust Framework for Real-World Applications

Leveraging Visual Language Information for Enhanced Person R...

引用

2025 IEEE International conference on Consumer Electronics, ICCE 2025

作者： Han, Seunghee Jeong, Dasol Park, Hasil Park, Jiwon Lee, Hyebean Paik, Joonki Department of Image Chung-Ang University Seoul Korea Republic of Department of Artificial Intelligence Chung-Ang University Seoul Korea Republic of

ISBN: (纸本)9798331521165

Recently, performance improvements through vision-language learning have gained significant attention in the field of image re-identification (ReID). In particular, the CLIP-ReID [1] achieved enhanced visual representations by introducing learnable text token sets for each identity. However, existing approaches have not fully exploited fine-grained part-specific features of the human body, which are crucial when applying person re-identification technology in real-world scenarios where partial occlusions or other factors might affect accuracy. To address this limitation, we propose a novel framework that incorporates body part-specific learnable text tokens, leveraging visual language information related to specific body regions. This approach is essential for mitigating the impact of occlusions and enhancing the robustness of ReID systems in practical settings. The process of applying visual language information through CLIP-ReID involves several stages. First, body part regions are identified and segmented within the image. Next, visual features specific to these regions are extracted and mapped to corresponding text tokens that describe these features in natural language. Finally, these text tokens are integrated with the image features to create a more comprehensive representation that captures both visual and semantic aspects, improving the discrimination of individuals based on specific anatomical features. Experimental results not only using the MSMT17 [2] and Market-1501 [3] datasets but also from a real-world scenario involving 11 CCTV cameras installed on the campus of Chung-Ang University demonstrated that the proposed method significantly outperformed existing models. This confirms the effectiveness of vision-language learning that utilizes segmented body part information in the image re-identification task. © 2025 IEEE.

关键词： Text processing

来源：评论

学校读者我要写书评

暂无评论

No-reference Stereoscopic image Quality Assessment Based on Parallel Multi-scale Perception

No-reference Stereoscopic Image Quality Assessment Based on ...

引用

IEEE visual communications and image processing (VCIP)

作者： Ziyi Zhang Sumei Li School of Electrical and Information Engineering Tianjin University Tianjin China

ISBN: (纸本)9781665475938

With the rapid development of 3D technologies, effective no-reference stereoscopic image quality assessment (NR-SIQA) methods are in great demand. In this paper, we propose a parallel multi-scale feature extraction convolution neural network (CNN) model combined with novel binocular feature interaction consistent with human visual system (HVS). In order to simulate the characteristics of HVS sensing multi-scale information at the same time, parallel multi-scale feature extraction module (PMSFM) followed by compensation information is proposed. And modified convolutional block attention module (MCBAM) with less computational complexity is designed to generate visual attention maps for the multi-scale features extracted by the PMSFM. In addition, we employ cross-stacked strategy for multi-level binocular fusion maps and binocular disparity maps to simulate the hierarchical perception characteristics of HVS. Experimental results show that our method is superior to the state-of-the-art metrics and achieves an excellent performance.

关键词： image quality visualization Three-dimensional displays visual communication Stereo image processing Neural networks visual systems

来源：评论

学校读者我要写书评

暂无评论

Flicker-Free Adaptive Enhancement for Infrared Video 13

Flicker-Free Adaptive Enhancement for Infrared Video

引用

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

作者： Wei, Caixia Gan, Zongliang Nanjing University of Posts and Telecommunications Jiangsu Provincial Key Lab of Image Processing and Image Communication Nanjing China

ISBN: (纸本)9781665407854

Infrared videos often suffer from low contrast and insufficient texture. In order to improve poor visual effect, a novel infrared video enhancement method is proposed, which contains intra-frame brightness enhancement and inter-frame brightness continuity adjustment. In intra-frame brightness enhancement, it has two steps including global contrast enhancement and local details enhancement. To global contrast enhancement, the processed image contrast by geometric distribution, and it is incorporated into an optimization problem with a sorted histogram of each frame to yield a modified histogram. To local details enhancement, after Retinex decomposition, the reflection component is magnified by boundary preserving filter, and this strategy can effectively suppress noise in relatively uniform regions. Furthermore, to maintain inter-frame brightness continuity, adaptive parameters are introduced through optical flow to control the combination ratio of geometric distribution histogram, in which the enhancement degree of each frame can be adjusted according to inter-frame similarity and the moving region are enhanced adaptively according to the change of each frame. Experimental results demonstrate that proposed algorithm can effectively enhance the contrast and detail of infrared video, and improve the visual effect in subjective and objective quality evaluation. © 2021 IEEE.

关键词： Luminance

来源：评论

学校读者我要写书评

暂无评论

image Forgery Detection Using Hybrid Model

Image Forgery Detection Using Hybrid Model

引用

Intelligent Signal processing and Effective Communication Technologies (INSPECT), IEEE International conference on

作者： Priya Metri Sakshi Balla Shreya Pawar Atharva Sharma Prashant Sakunde Artificial Intelligence and Data Science Dr. D. Y. Patil Institute of Technology Pimpri Pune India

ISBN: (数字)9798350379525

ISBN: (纸本)9798350379532

The growing demand for trustworthy picture forgery detection techniques to maintain the integrity of visual content across a range of applications is addressed in this work. To improve picture authentication accuracy and efficiency, a user-friendly cascaded framework combining Support Vector Machines (SVM) and VGG 16 is presented. First, a highly effective supervised learning system called Support Vector Machines (SVM) rapidly filters photos by identifying overt alteration indi-cators. After passing this phase, images are examined and refined even more with the help of the VGG 16 deep learning model. When SVM and VGG16 are combined, their complimentary strengths are utilised, which improves accuracy and speeds up identification when compared to other approaches. According to benchmark datasets, the proposed method outperforms earlier methods with respect to accuracy and computational efficiency. This strategy may benefit many real-world applications- based on forensic verification, verification of media integrity, medical image authentication, and intellectual property protection-in the here-and-now solutions. This work enhances the confidence and trustworthiness of digital communications by providing an efficient, friendly user tool for the verification of visual content.

关键词： Support vector machines visualization Accuracy Filters Forensics Supervised learning Authentication Intellectual property Media Forgery

来源：评论

学校读者我要写书评

暂无评论

DNAT: Multi-scale Transformer with Dilated Neighborhood Attention for image Classification

DNAT: Multi-scale Transformer with Dilated Neighborhood Atte...

引用

International conference on Wireless communications and Signal processing (WCSP)

作者： Chenfeng Jiang Quan Zhou Zhiyi Mo Jing Wang Yawen Fan Xiaofu Wu Suofei Zhang Bin Kang National Engineering Research Center of Communications and Networking Nanjing University of Posts & Telecommunications P.R. China Guangxi Colleges and Universities Key Laboratory of Intelligent Industry Software Wuzhou University Wuzhou China Department of Internet of Things Nanjing University of Posts & Telecommunications P.R. China

Recently, Transformer-based models have achieved remarkable progress for image classification. In order to reduce the computational costs of multi-head self-attention (MHSA) that is widely adopted in recently-proposed visual Transformers, some window-based Transformers employ local self-attention via shrinking number of input tokens. Nevertheless, these approaches to some extent are short to model long-range dependencies. To address this problem, this paper presents an effective and powerful Transformer backbone, called Dilated Neighborhood Attention Transformer (DNAT) that has a mutli-path architecture, for image classification. DNAT is able to explore long-range interactions through dilated neighborhood attention (DNA). When dilation rate is small, DNAT degenerates to local self-attention that is computationally efficient to capture local features. As the dilation rate increases, more and more long-range token interactions are explored step-by-step. Finally, by integrating weighted features derived from various dilation rates, DNAT seamlessly harvests local-to-global context, yet with acceptable growth of model size and computational budgets. The extensive experiments on imageNet-1K and CIFAR100 datasets demonstrate the effectiveness of DNAT for image classification.

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 << < 62 63 64 65 66 67 68 69 70 71 > >>

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：