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

165 篇 会议
19 篇 期刊文献
3 册 图书

馆藏范围

187 篇 电子文献
0 种 纸本馆藏

日期分布

学科分类号

158 篇 工学
- 99 篇 计算机科学与技术...
- 70 篇 软件工程
- 53 篇 电气工程
- 43 篇 信息与通信工程
- 33 篇 光学工程
- 13 篇 电子科学与技术（可...
- 7 篇 仪器科学与技术
- 6 篇 材料科学与工程（可...
- 6 篇 控制科学与工程
- 5 篇 环境科学与工程（可...
- 5 篇 生物医学工程（可授...
- 4 篇 航空宇航科学与技...
- 4 篇 生物工程
- 2 篇 机械工程
- 2 篇 动力工程及工程热...
- 2 篇 化学工程与技术
- 2 篇 轻工技术与工程
- 1 篇 建筑学
86 篇 理学
- 58 篇 物理学
- 35 篇 数学
- 7 篇 生物学
- 6 篇 系统科学
- 5 篇 大气科学
- 5 篇 地球物理学
- 4 篇 统计学（可授理学、...
- 3 篇 化学
21 篇 医学
- 21 篇 临床医学
6 篇 管理学
- 4 篇 图书情报与档案管...
- 3 篇 管理科学与工程(可...
1 篇 文学
- 1 篇 外国语言文学

主题

39 篇 image processing
16 篇 image coding
9 篇 deep learning
8 篇 image compressio...
8 篇 image quality
7 篇 image segmentati...
7 篇 visualization
6 篇 image enhancemen...
6 篇 signal processin...
6 篇 image retrieval
6 篇 visual communica...
6 篇 quantization
5 篇 image edge detec...
5 篇 visual system
4 篇 algorithm develo...
4 篇 data modeling
4 篇 humans
4 篇 image analysis
4 篇 computer vision
4 篇 sensors

机构

4 篇 the analytic sci...
2 篇 department of el...
2 篇 institute of ima...
2 篇 bytedance
2 篇 analytic science...
2 篇 telecommunicatio...
2 篇 department of el...
1 篇 minist commun it...
1 篇 united int coll ...
1 篇 school of electr...
1 篇 laboratory for i...
1 篇 east china inst....
1 篇 nagarjuna coll e...
1 篇 univ cent florid...
1 篇 school of comput...
1 篇 institute of inf...
1 篇 informat & commu...
1 篇 faculty of engin...
1 篇 bell communicati...
1 篇 old dominion uni...

作者

3 篇 zeevi y.y.
3 篇 paik joonki
2 篇 puech w.
2 篇 sawabe t
2 篇 liu tsann-shyong
2 篇 chang gan-how
2 篇 kim munchurl
2 篇 izraelevitz davi...
2 篇 ro yong man
2 篇 anastassiou dimi...
2 篇 chen t.c.
2 篇 boekee d.e.
2 篇 fujii t
2 篇 bovik ac
2 篇 wang lin
2 篇 s. rajala
2 篇 carlotto mark j.
2 篇 chaumont m.
2 篇 yang seungji
2 篇 jeng bor-shenn

语言

180 篇 英文
5 篇 其他
2 篇 中文

检索条件"任意字段=Visual Communications and Image Processing II 1987"

共 187 条记录，以下是1-10 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：

Are Standard CNNs Good Enough for No-Reference Stereoscopic image Quality Assessment? 15

Are Standard CNNs Good Enough for No-Reference Stereoscopic ...

引用

15th International Conference on Signal processing and communications (SPCOM)

作者： Bardhan, Ishita Channappayya, Sumohana Banerjee, Abhik Forkan, Abdur Rahim Mohammad Jayaraman, Prem Kumar, Abhinav Indian Inst Technol Hyderabad Dept Artificial Intelligence Kandi Telangana India Swinburne Univ Technol Dept Comp Technol Melbourne Vic Australia

ISBN: (纸本)9798350350463;9798350350456

Perceptual quality metrics derived from deep features have led to a boost in modelling the Human visual System (HVS) to perceive the quality of visual content. In this work, we study the effectiveness of fine-tuning three standard convolutional neural networks (CNNs) viz. ResNet50, VGG16 and MobileNetV2 to predict the quality of stereoscopic images in the no-reference setting. This work also aims to understand the impact of using disparity maps for quality prediction. Interestingly, our experiments demonstrate that disparity maps do not significantly contribute to improving perceptual quality estimation in the deep learning framework. To the best of our knowledge, this is the first study that explores the impact of disparity along with the chosen models for Stereoscopic image Quality Assessment. We present a detailed study of our experiments with various architectural configurations on the LIVE Phase I and ii datasets. Further, our results demonstrate the innate capability of deep features for quality prediction. Finally, the simple fine-tuning of the models results in solutions that compete with state-of-the-art patch-based stereoscopic image quality assessment methods.

关键词： Stereocenters

来源：评论

学校读者我要写书评

暂无评论

image Generation from Arabic Text: Comparative Study of Proposed Architectures 8th

Image Generation from Arabic Text: Comparative Study of Prop...

引用

8th International Conference on Arabic Language processing

作者： Bahani, Mourad El Ouaazizi, Aziza Maalmi, Khalil Essahlaoui, Abdelouahed Sidi Mohamed Ben Abdellah Univ Natl Sch Appl Sci Artificial Intelligence Data Sci & Emerging Syst Fes Morocco Sidi Mohamed Ben Abdellah Univ Lab Engn Sci FPT Taza Morocco

ISBN: (纸本)9783031804373;9783031804380

Text-to-image generation is a cutting-edge technology that enables computers to generate images from textual descriptions. While this technology has been extensively researched and applied to English language text, applying it to Arabic language text is still in its early stages. Additionally, the Arabic language is challenging due to its right-to-left writing system and extensive vocabulary of 1.3 million words. In this paper, we explore text-to-image generation for generating images from Arabic language text descriptions. Firstly, we fine-tune a transformer-based model pre-trained on the Arabic text to transform the text information into affine transformation within the DF-GAN generator. Secondly, we present a text transformer that combines LSTM layers to address the limitation of unrecognized words. Thirdly, a mask predictor is trained into the generator using a weakly supervised method and incorporated into the affine transformation for a more effective integration of image and text features. In addition, we add the DAMSM loss function as a regularization to the loss function to achieve convergences and stability in the training phase. The experiment on two challenging datasets CUB and Oxford-flower shows that our architectures can accurately generate high-quality images faithfully representing the Arabic textual descriptions. We believe the scaling of this task could have critical applications in fields such as Arabic visual learning, e-commerce, advertising, and entertainment.

关键词： Machine Learning Deep Learning Computer Vision Generative Adversarial Networks Text-to-image Generation Arabic Text processing

来源：评论

学校读者我要写书评

暂无评论

Deep Neural Networks for Efficient image Caption Generation 3rd

Deep Neural Networks for Efficient Image Caption Generation

引用

3rd International Conference on Advanced Network Technologies and Intelligent Computing (ANTIC)

作者： Rai, Riddhi Guruprasad, Navya Shimoga Tumuluru, Shreya Sindhu Ramaiah Inst Technol Bangalore Karnataka India

ISBN: (纸本)9783031640636;9783031640643

In the era of rapidly advancing technology, the integration of computer vision and natural language processing has emerged as a pivotal area of research, with deep learning playing a central role. The task of generating descriptive textual captions for images is known as image captioning. It is necessary for enhancing accessibility, aiding visually impaired individuals, and improving human-computer interaction by providing meaningful context to visual content. Generating relevant descriptions for high-level image semantics involves not just recognizing objects and scenes but also analyzing the state, attributes, and relationships among them. This research paper investigates the synergy of Convolutional Neural Networks (CNNs) for effective image feature extraction and Long Short-Term Memory (LSTM) networks for capturing sequential dependencies in generating descriptive and coherent textual captions. It has been demonstrated that it can produce precise and contextually relevant descriptions for a variety of images.

关键词： image Captioning Deep Learning CNN LSTM

来源：评论

学校读者我要写书评

暂无评论

Fidelity-preserving Learning-Based image Compression: Loss Function and Subjective Evaluation Methodology

Fidelity-preserving Learning-Based Image Compression: Loss F...

引用

2023 IEEE International Conference on visual communications and image processing, VCIP 2023

作者： Mohammadi, Shima Wu, Yaojun Ascenso, Joao Instituto de Telecomunicações Instituto Superior Técnico Portugal Bytedance China

ISBN: (纸本)9798350359855

Learning-based image compression methods have emerged as state-of-The-Art, showcasing higher performance compared to conventional compression solutions. These data-driven approaches aim to learn the parameters of a neural network model through iterative training on large amounts of data. The optimization process typically involves minimizing the distortion between the decoded and the original ground truth images. This paper focuses on perceptual optimization of learning-based image compression solutions and proposes: i) novel loss function to be used during training and ii) novel subjective test methodology that aims to evaluate the decoded image fidelity. According to experimental results from the subjective test taken with the new methodology, the optimization procedure can enhance image quality for low-rates while offering no advantage for high-rates. © 2023 IEEE.

关键词： image compression

来源：评论

学校读者我要写书评

暂无评论

Textual Training for the Hassle-Free Removal of Unwanted visual Data: Case Studies on OOD and Hateful image Detection 38

Textual Training for the Hassle-Free Removal of Unwanted Vis...

引用

38th Conference on Neural Information processing Systems, NeurIPS 2024

作者： Lee, Saehyung Mok, Jisoo Park, Sangha Shin, Yongho Jung, Dahuin Yoon, Sungroh Department of Electrical and Computer Engineering Seoul National University Korea Republic of Qualcomm Korea YH Seoul Korea Republic of School of Computer Science and Engineering Soongsil University Korea Republic of Interdisciplinary Program in Artificial Intelligence Seoul National University Korea Republic of

In our study, we explore methods for detecting unwanted content lurking in visual datasets. We provide a theoretical analysis demonstrating that a model capable of successfully partitioning visual data can be obtained using only textual data. Based on the analysis, we propose Hassle-Free Textual Training (HFTT), a streamlined method capable of acquiring detectors for unwanted visual content, using only synthetic textual data in conjunction with pre-trained vision-language models. HFTT features an innovative objective function that significantly reduces the necessity for human involvement in data annotation. Furthermore, HFTT employs a clever textual data synthesis method, effectively emulating the integration of unknown visual data distribution into the training process at no extra cost. The unique characteristics of HFTT extend its utility beyond traditional out-of-distribution detection, making it applicable to tasks that address more abstract concepts. We complement our analyses with experiments in out-of-distribution detection and hateful image detection. Our codes are available at https://***/Saehyung-Lee/HFTT. © 2024 Neural information processing systems foundation. All rights reserved.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Design of 3D image visual Communication System Based on Computer image Technology 4th

Design of 3D Image Visual Communication System Based on Comp...

引用

4th International Conference on Machine Learning, image processing, Network Security and Data Sciences (MIND)

作者： Gou, Shuangxiao Mei, Ling Chongqing Univ Arts & Sci Coll Fine Arts & Design Chongqing 402160 Peoples R China Chongqing Water Resources & Elect Engn Coll Large Data Inst Chongqing 402160 Peoples R China

ISBN: (纸本)9783031243660;9783031243677

Computer imaging technology is a kind of use of digital photography, using a computer as amedium to realize interactive communication and interaction between humans and machines through the collection and processing of images and the editing and storage of graphic information. The purpose of this paper to study the design of the 3D image visual communication system based on computer image technology is to improve the mastery of 3D image technology and design the visual communication system. This article mainly uses experimental and comparative methods to analyze the feature extraction situation of the 3D image visual communication system, and finds that the error of the improved RANSAC algorithm in image feature extraction is about 54%, while the unimproved algorithm and other algorithms The error is greater. This shows that the improved algorithm proposed in this paper is incomparable in the 3D image visual communication system.

关键词： Computer image technology 3-dimensional image visual communication System design

来源：评论

学校读者我要写书评

暂无评论

Fine-grained Single-layer Tiling for Viewport-Adaptive 360-degree Video Streaming

Fine-grained Single-layer Tiling for Viewport-Adaptive 360-d...

引用

2023 IEEE International Conference on visual communications and image processing, VCIP 2023

作者： Jeong, Jong-Beom Park, Jun-Hyeong Lee, Soonbin Ryu, Eun-Seok Department of Computer Science Education Seoul Korea Republic of Department of Immersive Media Engineering Seoul Korea Republic of Multimedia Communications Group Berlin Germany

ISBN: (纸本)9798350359855

Tile-based streaming is widely adopted for viewport-Adaptive 360-degree video streaming due to its potential for bitrate reduction. However, for legacy devices equipped with a single decoder, managing multiple tile bitstreams poses a challenge, particularly with regards to synchronizing multiple decoders. This paper introduces Butterfly360, a fine-grained single-layer tiling method that advances two main ideas: (i) an optimal tiling scheme decision method for single-layer merging of tiles using various tile sizes, and (ii) a simple rate adaptation method for viewport tiles. Experimental results demonstrate that the proposed method offers advantages in terms of bitrate savings and reduction in decoding runtime. Furthermore, the proposed method facilitates the use of either multiple tile bitstreams or a single-layer merged bitstream. © 2023 IEEE.

关键词： Video streaming

来源：评论

学校读者我要写书评

暂无评论

Accelerating Traditional Object Detection Methods on Sophisticated Embedded Systems 4th

Accelerating Traditional Object Detection Methods on Sophist...

引用

4th International Conference on Intelligent Systems and Pattern Recognition-ISPR

作者： Sehairi, Kamal Bouhafs, Abdelkader Boucherit, Ibtissam Mama Bouwmans, Thierry Chouireb, Fatima Ecole Normale Super Laghouat Dept Phys Lab Appl Sci & Didact Laghouat Algeria Univ Amar Telidji Laghouat Dept Elect Telecommun Signals & Syst Lab Laghouat Algeria Univ La Rochelle Dept Comp Sci Lab Math Image & Applicat La Rochelle France

ISBN: (纸本)9783031821523;9783031821530

Identifying and locating objects in images and videos, including elements like traffic signs, vehicles, buildings, and people, constitutes a fundamental and demanding task in computer vision, known as object detection. Due to the higher computing complexity of this technique and the large amount of data carried by the video signal, it is nearly impossible for ordinary general-purpose processors GPPs or CPUs to run these techniques in real-time, especially for embedded systems applications. Therefore, special hardware that can acquire, control, or execute in parallel is required. These specialized hardware systems include Digital Signal Processors DSPs, Field Programmable Gate Arrays FPGAs, visual processing Units VPUs, Tensor processing Units TPUs, Neural processing Units NPUs or Graphics processing Units GPUs. This work presents the benefits of accelerating traditional object detection methods on a high-end embedded system, the Jetson Nano Developer Kit. This single computer board is equipped with the Tegra K1 System on Chip SoC, which is composed of a quad-core ARM A15 and 192 cores of Kepler-embedded GPU. Computing acceleration was ensured via the use of the CUDA OpenCV library for both the Histogram of Oriented Gradients HOG and the Haar Cascade Classifier. For VGA resolution, results reveal that the GPU implementation on this embedded system is 1.4x faster than the CPU for the HOG method and 2x for the Haar Cascade Classifier method.

关键词： Object detection Machine Learning Haar Cascade HOG Local feature descriptors GPU implementation OpenCV CUDA SoC Tegra X1 Jetson Nano

来源：评论

学校读者我要写书评

暂无评论

3D Printing Design Simulation of Ceramic Products Based on 3D image Reproduction Technology 4th

3D Printing Design Simulation of Ceramic Products Based on 3...

引用

4th International Conference on Machine Learning, image processing, Network Security and Data Sciences (MIND)

作者： Yao, Lan Shanghai Art & Design Acad Shanghai Peoples R China

ISBN: (纸本)9783031243660;9783031243677

With the development of communication technology, people will be exposed to more and more graphics and images in the process of life andwork. Like using digital devices such as camera, scanner and camera to obtain images, but these instruments and equipment can only obtain two-dimensional image information of objects, which is completely insufficient. Inmany fields, three-dimensional information of objects is necessary. In this paper, the 3D printing design of ceramic products is simulated based on 3D image reproduction technology. The satisfaction of users with the ceramic visual effect and hand-held comfort produced by 3D image reproduction simulation technology is investigated by means of questionnaire, and the computer vision technology and stereo matching technology are compared. The results show that more than 85% of users are very satisfied with the ceramic visual effect and hand-held comfort of three-dimensional image reproduction simulation technology, and less than 5% of users are not satisfied;The satisfaction of ceramic visual effect produced by computer vision technology and stereo matching technology is less than 60%, and the hand-held comfort is less than 70%.

关键词： 3D image reproduction technology Ceramic products 3D printing design Simulation research

来源：评论

学校读者我要写书评

暂无评论

Artificial Intelligence of Internet of Things and Virtual Reality Technology in the image Reconstruction of Film and Television Characters 4th

Artificial Intelligence of Internet of Things and Virtual Re...

引用

4th International Conference on Machine Learning, image processing, Network Security and Data Sciences (MIND)

作者： Guo, Hanlin United Int Coll Div Culture & Creat Anshan 114000 Liaoning Peoples R China

ISBN: (纸本)9783031243660;9783031243677

The animation market structure continues to be optimized, and the animation economic cake continues to grow. Character image building is a very important work content, this part of the work is the most important part of the whole film and TVseries. Animation characters from the character, characteristics, character psychological activities, action and other aspects to show their own character image. All these features are innovative elements in film and television, which provide their own services for the development of film and television plot and make the development of film and television more visual. This paper studies the research on the image reconstruction of Internet of Things artificial intelligence and virtual reality technology in film and television character reconstruction, and points out the related content of the research on the image reconstruction of film and television character reconstruction. The test confirmed that artificial intelligence of the Internet of Things and virtual reality technology had excellent performance in the image reconstruction of film and television character role shaping.

关键词： Internet of things artificial intelligence Virtual reality technology Film and television character shaping image reconstruction research

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19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：