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

4,504 篇 会议
49 篇 期刊文献
18 册 图书
1 篇 学位论文

馆藏范围

4,572 篇 电子文献
0 种 纸本馆藏

日期分布

学科分类号

2,608 篇 工学
- 1,697 篇 计算机科学与技术...
- 1,111 篇 信息与通信工程
- 990 篇 软件工程
- 698 篇 电气工程
- 281 篇 光学工程
- 126 篇 电子科学与技术（可...
- 119 篇 生物工程
- 115 篇 控制科学与工程
- 103 篇 仪器科学与技术
- 97 篇 网络空间安全
- 95 篇 生物医学工程（可授...
- 72 篇 机械工程
- 45 篇 化学工程与技术
- 31 篇 安全科学与工程
- 30 篇 动力工程及工程热...
- 26 篇 轻工技术与工程
1,245 篇 医学
- 1,236 篇 临床医学
- 35 篇 基础医学(可授医学...
- 29 篇 药学(可授医学、理...
1,042 篇 理学
- 746 篇 物理学
- 338 篇 数学
- 128 篇 生物学
- 105 篇 统计学（可授理学、...
- 48 篇 系统科学
- 47 篇 化学
189 篇 管理学
- 102 篇 管理科学与工程(可...
- 98 篇 图书情报与档案管...
- 32 篇 工商管理
77 篇 军事学
- 74 篇 军队指挥学
38 篇 法学
- 30 篇 社会学
10 篇 文学
8 篇 经济学
7 篇 农学
6 篇 教育学

主题

552 篇 image coding
469 篇 image processing
353 篇 visual communica...
318 篇 visualization
276 篇 image segmentati...
260 篇 feature extracti...
181 篇 image compressio...
168 篇 video coding
165 篇 image reconstruc...
158 篇 cameras
153 篇 humans
137 篇 image quality
132 篇 image retrieval
126 篇 training
123 篇 image edge detec...
123 篇 image color anal...
115 篇 image enhancemen...
114 篇 signal processin...
114 篇 image analysis
110 篇 motion estimatio...

机构

36 篇 shanghai jiao to...
29 篇 institute of ima...
28 篇 school of electr...
24 篇 school of electr...
21 篇 university of sc...
18 篇 shanghai jiao to...
17 篇 shanghai jiao to...
16 篇 tianjin univ sch...
16 篇 beijing universi...
14 篇 institute for in...
11 篇 school of comput...
11 篇 university of el...
11 篇 cas key laborato...
11 篇 tsinghua univ de...
10 篇 univ sci & techn...
10 篇 zhejiang univers...
10 篇 peking univ inst...
10 篇 institute of ima...
9 篇 microsoft resear...
9 篇 tsinghua univ de...

作者

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

语言

4,497 篇 英文
49 篇 土耳其文
25 篇 中文
18 篇 其他

检索条件"任意字段=Conference on Visual Communications and Image Processing 2003"

共 4572 条记录，以下是251-260 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：

RGFormer: Residual Gated Transformer for image Captioning 23rd

RGFormer: Residual Gated Transformer for Image Captioning

引用

23rd Asia Simulation conference, AsiaSim 2024

作者： Jin, Zehui Chen, Kai Fang, Guoyu Tang, Dunbing Nanjing University of Aeronautics and Astronautics Nanjing210016 China

ISBN: (纸本)9789819772247

image captioning is a cross-modal task that combines computer vision and natural language processing. The model is required to generate an appropriate caption for the given image. To address this challenge, we proposed a Residual Gated Transformer, RGFormer, as an enhancement of Transformer architecture. The model based on CLIP and RGFormer, CRM, is then proposed for image captioning. CRM utilizes the encoder of CLIP to extract image features as a prefix to the caption. The prefix is projected into language space using RGFormer, a lightweight mapping network, and then fed into GPT-2 to generate captions. CLIP was trained on an extensive dataset comprising image-text pairs, which contains rich visual and semantic information and is exceptionally well-suited for vision-language tasks. The core idea of CRM is to reduce the disparity between visual and textual representations by using RGFormer to accomplish the cross-modal task. CRM could generate meaningful captions for diverse and large-scale datasets in a short training time without additional annotations or pre-training. Quantitative evaluation experiments show that CRM achieves results comparable to some advanced models on the COCO Caption dataset more efficiently. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2024.

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

The Potential Utility of image Descriptions: User Identity Linkage across Social Networks Based on MultiModal Self-Attention Fusion

The Potential Utility of Image Descriptions: User Identity L...

引用

IEEE International Performance, Computing, and communications conference (IPCCC)

作者： Li, Yunfeng Gou, Gaopeng Xiong, Gang Li, Zhen Cui, Mingxin Chinese Acad Sci Inst Informat Engn Beijing Peoples R China Univ Chinese Acad Sci Sch Cyber Secur Beijing Peoples R China

ISBN: (纸本)9798350302936

The task of user identity linkage across social networks aims to predict whether users from different social networks refer to the same person. This task plays a crucial role in cross-social network information dissemination and intelligent recommendations. However, existing user identity linkage tasks suffer from several challenges: 1) excessive reliance on social network topology, neglecting users' visual modality information;2) inadequate handling of noise in user feature data;and 3) ineffective fusion of users' multimodal information. To address these issues, we investigated a method that utilizes heterogeneous multimodal posts, including user-generated text, images, and check-in messages, to achieve user identity linkage across social networks. We innovatively leveraged a pre-trained model for image-to-text conversion to further explore users' image data and proposed an adversarial learning model based on the multimodal self-attention mechanism (AMSA). The AMSA model consists of four components: user feature extraction, user feature processing, user feature fusion, and adversarial learning. Specifically, AMSA initially employed advanced pre-trained models to extract features from multiple modalities of users, including images and text. Subsequently, it utilized multiple mechanisms, such as multi-head self-attention, to process data from each modality separately and then fused them into user representation vectors. Finally, AMSA employed adversarial learning to enhance the model's learning capacity and mitigate semantic disparities in user information across different platforms. We conducted model performance evaluations on publicly available datasets, and experimental results demonstrated the superiority of the proposed AMSA model.

关键词： User Identity Linkage Deep learning Multi-Modal Learning Self-Attention

来源：评论

学校读者我要写书评

暂无评论

Fast detection of sulcal regions for classification of Alzheimer's disease and Mild Cognitive Impairment 14

Fast detection of sulcal regions for classification of Alzhe...

引用

14th IEEE International conference on Signal processing and communications (SPCOM)

作者： Dhere, Abhinav Vazhayil, Vikas Sivaswamy, Jayanthi Int Inst Informat Technol Hyderabad Ctr Visual Informat Technol Hyderabad India Natl Inst Mental Hlth & Neurosci Dept Neurosurg Bangalore Karnataka India

ISBN: (数字)9781665482509

ISBN: (纸本)9781665482509

Alzheimer's disease (AD) and Mild Cognitive Impairment (MCI) are neurogenerative impairments with similar symptoms and risk factors. Sulcal width and depth are known biomarkers for discriminating between AD and MCI. This paper presents a novel 2D image representation for a brain mesh surface, called a height map. The basic idea behind the height map is to represent the surface as a function of spherical coordinates of the mesh vertices. We present a method to derive a height map from a given neuroimage (MRI) and extract sulcal regions from the height map. We demonstrate the height map's utility for classifying a given neuroimage into healthy, MCI and AD classes. Two approaches for extracting sulcal regions are explored. The proposed method is computationally light, and obtaining sulcal regions from a brain surface mesh takes about 24 seconds on a standard Intel i5-7200 CPU. The proposed method achieves 76.1% accuracy, and 76.3% F1-score for healthy, MCI, AD classification on a publicly available dataset.

关键词： visualization Brain Magnetic resonance imaging conferences Signal processing image representation Biomarkers

来源：评论

学校读者我要写书评

暂无评论

T2CI-GAN: Text to Compressed image Generation Using Generative Adversarial Network 7th

T2CI-GAN: Text to Compressed Image Generation Using Generati...

引用

7th International conference on Computer Vision and image processing, CVIP 2022

作者： Rajesh, Bulla Dusa, Nandakishore Javed, Mohammed Dubey, Shiv Ram Nagabhushan, P. Department of IT IIIT Allahabad U.P Prayagraj211015 India Department of CSE Vignan University A.P Guntur522213 India

ISBN: (纸本)9783031314162

The problem of generating textual descriptions for the visual data has gained research attention in the recent years. In contrast to that the problem of generating visual data from textual descriptions is still very challenging, because it requires the combination of both Natural Language processing (NLP) and Computer Vision techniques. The existing methods utilize the Generative Adversarial Networks (GANs) and generate the uncompressed images from textual description. However, in practice, most of the visual data are processed and transmitted in the compressed representation. Hence, the proposed work attempts to generate the visual data directly in the compressed representation form using Deep Convolutional GANs (DCGANs) to achieve the storage and computational efficiency. We propose GAN models for compressed image generation from text. The first model is directly trained with JPEG compressed DCT images (compressed domain) to generate the compressed images from text descriptions. The second model is trained with RGB images (pixel domain) to generate JPEG compressed DCT representation from text descriptions. The proposed models are tested on an open source benchmark dataset Oxford-102 Flower images using both RGB and JPEG compressed versions, and accomplished the state-of-the-art performance in the JPEG compressed domain. The code will be publicly released at GitHub after acceptance of paper. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2023.

关键词： Generative adversarial networks

来源：评论

学校读者我要写书评

暂无评论

OPTICS LENS DESIGN FOR PRIVACY-PRESERVING SCENE CAPTIONING 29

OPTICS LENS DESIGN FOR PRIVACY-PRESERVING SCENE CAPTIONING

引用

IEEE International conference on image processing (ICIP)

作者： Arguello, Paula Lopez, Jhon Hinojosa, Carlos Arguello, Henry Univ Ind Santander Dept Comp Sci Bucaramanga 680002 Colombia

ISBN: (数字)9781665496209

ISBN: (纸本)9781665496209

image captioning is a challenging task that connects two major artificial intelligence fields: computer vision and natural language processing. image captioning models use traditional images to generate a natural language description of the scene. However, the scene could contain private information that we want to hide but still generate the captions. Inspired by the trend of jointly designing optics and algorithms, this paper addresses the problem of privacy-preserving scene captioning. Our approach promotes privacy preservation, by hiding the faces in the images, during the acquisition process with a designed refractive camera lens while extracting useful features to perform image captioning. The refractive lens and an image captioning deep network architecture are optimized end-to-end to generate descriptions directly from the blurred images. Simulations show that our privacy-preserving approach degrades private visual attributes (e.g., face detection fails with our distorted images) while achieving comparable captioning performance with traditional non-private methods on the COCO dataset.

关键词： image Captioning Privacy-preserving Lens Design Deep Optics Computational Optics

来源：评论

学校读者我要写书评

暂无评论

Dynamic Template Update Mechanism for visual Object Tracking 8

Dynamic Template Update Mechanism for Visual Object Tracking

引用

8th International conference on Intelligent Computing and Signal processing, ICSP 2023

作者： Hu, YongQi Cai, ZhongWang Nie, ZiJun Yu, ZiZheng Cao, Ying Yin, Zhijian Yang, Zhen Jiangxi Science and Technology Normal University School of Communications and Electronics Nanchang China Ministry of Education Key Laboratory of System Control and Information Processing Shanghai China

ISBN: (纸本)9798350302455

Given the requirements for robust target classification and accurate target state estimation in visual tracking, SiamFC++ proposes a set of practical guidelines for designing high-performance general-purpose trackers by considering the special nature of visual tracking problems. Inspired by dynamic modules, We propose an empirical method for integrating a dynamic module into the image input, which is concatenated with the template module after feature maps are extracted by the backbone network. Since the position and shape of the object can change significantly within a video sequence, the added dynamic module can better focus on the target region of the feature map to obtain better similarity maps. Extensive experiments and comparisons demonstrate that our simple and effective method achieves reliable results on the benchmarks of LaSOT, TrackingNet, and GOT-10K and provides a significant speed advantage in real-time. © 2023 IEEE.

关键词： Computer vision

来源：评论

学校读者我要写书评

暂无评论

Proceedings - 2023 IEEE International conference on Multimedia and Expo, ICME 2023

Proceedings - 2023 IEEE International Conference on Multimed...

引用

2023 IEEE International conference on Multimedia and Expo, ICME 2023

ISBN: (纸本)9781665468916

The proceedings contain 475 papers. The topics discussed include: weight-based regularization for improving robustness in image classification;weakly supervised few-shot and zero-shot semantic segmentation with mean instance aware prompt learning;a retriever-reader framework with visual entity linking for knowledge-based visual question answering;2S-DFN: dual-semantic decoding fusion networks for fine-grained image recognition;Action-GPT: leveraging large-scale language models for improved and generalized action generation;protecting intellectual property of EEG-based model with watermarking;making adversarial attack imperceptible in frequency domain: a watermark-based framework;content-adaptive adversarial embedding for image steganography using deep reinforcement learning;a robust generative image steganography method based on guidance features in image synthesis;adversarial audio watermarking: embedding watermark into deep feature;deniable diffusion generative steganography;and sea surface object detection based on background dynamic perception and cross-layer semantic interaction.

关键词：

来源：评论

学校读者我要写书评

暂无评论

A Medical image Steganography Scheme with High Embedding Capacity to Solve Falling-Off Boundary Problem Using Pixel Value Difference Method 29th

A Medical Image Steganography Scheme with High Embedding Cap...

引用

29th International conference on Neural Information processing

作者： Dharwadkar, Nagaraj, V Mahmud, Mufti Lonikar, Ashutosh A. Brown, David J. Rajarambapu Inst Technol Dept Comp Sci Islampur Maharashtra India Nottingham Trent Univ Dept Comp Sci Nottingham NG11 8NS England Nottingham Trent Univ CIRC Nottingham NG11 8NS England Nottingham Trent Univ MTIF Nottingham NG11 8NS England

ISBN: (纸本)9789819916474;9789819916481

Medical images have a vital role in the healthcare industry. The medical sector uses the internet to facilitate the distant sharing of medical information among hospitals and clinics and provide patients with e-health services. We must share a patient's report secretly so that the intruders can't steal the patient's data. The pixel value differencing technique is utilised in this study to store a patient's medical information report in various medical imaging, such as ultrasound images, computed tomography scans, X-rays, magnetic resonance images, electrocardiographs, and microscopic images. The fundamental objective is to maintain the visual appearance of the medical images so that physicians can analyse and give accurate results and extract information reports precisely. This PVD scheme works on different types of image formats such as Portable Network Graphics (PNG), Joint Photographic Experts Group (JPG or JPEG), BitMaP (BMP), and Tag image File Format (TIFF). Measurement metrics such as embedding capacity, the difference in histograms between the stego and the cover image, and the peak signal-to-noise ratio (PSNR) are employed to evaluate the effectiveness of the suggested method. On a series of medical images, we have tested this new PVD approach and found that it provides significant payload capacity with the high visual quality of the stego image. The majority of PVD techniques described in the literature only apply to grayscale images, and those that apply to RGB images have falling off boundary problem. RGB images have pixel values that span from 0 to 255, but when the pixels are modified using the PVD technique, sometimes these pixel values fall outside of this range, which causes erroneous results to be obtained during extraction. Additionally, utilising a difference in the histograms of the stego and the cover image, the attacker in a typical PVD technique can disclose the existence and length of the secret message. This novel PVD methodology tackles th

关键词： Steganography PSNR PVD RGB LSB

来源：评论

学校读者我要写书评

暂无评论

visual Communication Design of image Multidimensional visualization Fusion System Based on Machine Learning 2

Visual Communication Design of Image Multidimensional Visual...

引用

2nd Asia-Pacific conference on communications Technology and Computer Science, ACCTCS 2022

作者： Ni, Xueyan Zhang, Ruhua Art College Changchun University Changchun130022 China

ISBN: (纸本)9781665400343

With the advent of the era of big data, people are exposed to a variety of data information every day. With the rise of high technology in the computer industry, data models are becoming more and more complex and changeable. Therefore, it is necessary to combine visualization technology with machine learning technology to process data more efficiently. With the development of computer processing software and related technologies, computer image processing software is widely used in modern film and television, advertising, games, software, and commercial activities for image design and visual communication design. The works designed by this design method have strong appeal and clear features, which can easily leave a deep impression on the viewer. At the same time, the art works designed by this design method are more innovative, which also has positive and profound significance for creators. However, most researchers currently focus on the optimization of the machine learning algorithm itself, but ignore the visual communication design of the image multi-dimensional visualization fusion system based on machine learning, and cannot intuitively see the operation process of the design. Therefore, this article focuses on the analysis of the current state of research in the field of visualization related to machine learning technology. © 2022 IEEE.

关键词： visualization

来源：评论

学校读者我要写书评

暂无评论

Denoising using a Hybrid Filter Comprised of GGIF, WLS, and 2D Bilateral Filtering

Denoising using a Hybrid Filter Comprised of GGIF, WLS, and ...

引用

2023 International conference on Electrical, Computer, communications and Mechatronics Engineering, ICECCME 2023

作者： Sharma, Abhilasha Dosajh, Aryaman Chalkoo, Moin Ahmad Delhi Technological University Department of Software Engineering New Delhi India

ISBN: (纸本)9798350322972

Denoising helps improve image quality and recover important information from noisy pictures. This work introduces a novel denoising method. GGIF, WLS, and 2D Bilateral Filtering are used in a hybrid filter. The hybrid filter shown eliminates noise while preserving the picture's characteristics, edges, and textures. Denoising begins with GGIF, which preserves edges and reduces artefacts. Then, WLS reduces amplified noise and smooths the image adaptively according to the local gradient. Last, 2D bilateral filtering reduces noise while keeping structural integrity and edge information. The hybrid filter is tested using simulated and real-world noisy images. The trials reveal that the recommended strategy outperforms current denoising approaches in noise reduction, edge retention, and visual quality. The hybrid filter may solve image processing, computer vision, and remote sensing problems. It uses GGIF, WLS, and 2D Bilateral Filtering to denoise well and improved perceptual fog density. © 2023 IEEE.

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458页 << < 22 23 24 25 26 27 28 29 30 31 > >>

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：