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

1,778 篇 会议
11 篇 期刊文献
4 册 图书

馆藏范围

1,793 篇 电子文献
0 种 纸本馆藏

日期分布

学科分类号

1,386 篇 工学
- 1,114 篇 计算机科学与技术...
- 818 篇 软件工程
- 457 篇 信息与通信工程
- 331 篇 光学工程
- 303 篇 控制科学与工程
- 199 篇 电气工程
- 181 篇 生物工程
- 152 篇 机械工程
- 126 篇 生物医学工程（可授...
- 97 篇 电子科学与技术（可...
- 85 篇 仪器科学与技术
- 65 篇 安全科学与工程
- 60 篇 化学工程与技术
- 42 篇 材料科学与工程（可...
- 40 篇 交通运输工程
- 25 篇 网络空间安全
615 篇 理学
- 373 篇 物理学
- 194 篇 数学
- 192 篇 生物学
- 61 篇 统计学（可授理学、...
- 58 篇 化学
- 25 篇 系统科学
222 篇 管理学
- 129 篇 管理科学与工程(可...
- 107 篇 图书情报与档案管...
- 46 篇 工商管理
136 篇 医学
- 125 篇 临床医学
- 58 篇 基础医学(可授医学...
- 48 篇 药学(可授医学、理...
37 篇 农学
- 33 篇 作物学
25 篇 艺术学
- 25 篇 设计学（可授艺术学...
20 篇 教育学
18 篇 法学
15 篇 经济学
4 篇 军事学
1 篇 文学

主题

289 篇 computer vision
164 篇 image processing
106 篇 feature extracti...
99 篇 deep learning
99 篇 image segmentati...
50 篇 object detection
47 篇 machine vision
47 篇 computational mo...
47 篇 convolutional ne...
45 篇 image enhancemen...
44 篇 image recognitio...
43 篇 cameras
37 篇 accuracy
36 篇 image edge detec...
36 篇 face recognition
34 篇 machine learning
33 篇 image color anal...
33 篇 training
31 篇 image reconstruc...
30 篇 visualization

机构

6 篇 shenyang institu...
6 篇 university of ch...
6 篇 shenyang ligong ...
4 篇 key laboratory o...
4 篇 school of softwa...
4 篇 school of inform...
4 篇 department of co...
4 篇 department of co...
4 篇 college of compu...
4 篇 beijing informat...
3 篇 school of comput...
3 篇 shanghaitech uni...
3 篇 chitkara univers...
3 篇 university of el...
3 篇 institute for co...
3 篇 guangzhou civil ...
3 篇 institutes for r...
3 篇 babol noshirvani...
3 篇 beijing informat...
3 篇 changchun univer...

作者

5 篇 raman balasubram...
5 篇 lu zongqing
4 篇 zhang chao
4 篇 ramani sanjeev k...
4 篇 wang wei
4 篇 hossain syed akh...
4 篇 iyengar s.s.
4 篇 sanjeev kaushik ...
3 篇 liu bo
3 篇 kumar krishan
3 篇 zhang ji
3 篇 elizabeth rani g...
3 篇 neehal nafis
3 篇 rabby akm shahar...
3 篇 luc van gool
3 篇 farag aly a.
3 篇 balasubramanian ...
3 篇 zhao jiewen
3 篇 zou xiaobo
3 篇 zhang hualiang

语言

1,750 篇 英文
26 篇 其他
19 篇 中文
1 篇 土耳其文

检索条件"任意字段=2nd International Conference on Computer Vision and Image Processing, CVIP 2017"

共 1793 条记录，以下是241-250 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：

Novel View Synthesis from a Single RGBD image for Indoor Scenes 2

Novel View Synthesis from a Single RGBD Image for Indoor Sce...

引用

2nd international conference on image processing, computer vision and Machine Learning, ICICML 2023

作者： Hetang, Congrui Wang, Yuping Carnegie Mellon University PittsburghPA15213 United States University of Michigan Ann ArborMI48109 United States

ISBN: (纸本)9798350331417

In this paper, we propose an approach for synthesizing novel view images from a single RGBD (Red Green Blue-Depth) input. Novel view synthesis (NVS) is an interesting computer vision task with extensive applications. Methods using multiple images has been well-studied, exemplary ones include training scene-specific Neural Radiance Fields (NeRF), or leveraging multi-view stereo (MVS) and 3D rendering pipelines. However, both are either computationally intensive or non-generalizable across different scenes, limiting their practical value. Conversely, the depth information embedded in RGBD images unlocks 3D potential from a singular view, simplifying NVS. The widespread availability of compact, affordable stereo cameras, and even LiDARs in contemporary devices like smartphones, makes capturing RGBD images more accessible than ever. In our method, we convert an RGBD image into a point cloud and render it from a different viewpoint, then formulate the NVS task into an image translation problem. We leveraged generative adversarial networks to style-transfer the rendered image, achieving a result similar to a photograph taken from the new perspective. We explore both unsupervised learning using CycleGAN and supervised learning with Pix2Pix, and demonstrate the qualitative results. Our method circumvents the limitations of traditional multi-image techniques, holding significant promise for practical, real-time applications in NVS. © 2023 IEEE.

关键词： 3D reconstruction Generative Adversarial Network image Style Transfer Novel View Synthesis

来源：评论

学校读者我要写书评

暂无评论

Boosted Spectral Perception via Synergistic vision for Cross-Domain Few-Shot Hyperspectral image Classification 2

Boosted Spectral Perception via Synergistic Vision for Cross...

引用

2nd IEEE international conference on Signal, Information and Data processing, ICSIDP 2024

作者： Yan, Xinyi Li, Jiaojiao Zhang, Zhiyuan Xu, Haitao Zheng, Tie Du, Qian Xidian University Isn Xi'an China Nssc Key Laboratory of Eitss Beijing China Mississippi State University Department of Electrical and Computer Engineering Starkville United States

ISBN: (纸本)9798331515669

Cross-domain few-shot learning (CDFSL) hyper-spectral image classification (HSIC) techniques have significantly enhanced the performance of HSIC under a few annotations. Due to the scattered spatial distribution of HSI and limited labels, the spatial information of the HSI sample is restricted, which means the spectral information may contain more discriminative category features than spatial information. However, most existing CDFSL HSIC methods lack targeted spectral discriminative feature extraction and struggle to capture spectral subtleties. To address this, a Human Eye-like Dual-Branch Network (HEDB-Net) is proposed, comprising a central branch and a peripheral branch. The central branch focuses on extracting core features from complete spectral dimension HSI patches. Simultaneously, these patches are input into the peripheral branch via random sampling and reintegration of spectral bands, enabling the model to perceive initially dispersed spectral information. These two branches represent the model's central and peripheral vision for the spectrum, allowing it to focus on different levels of feature information and significantly boosting spectral perception capabilities. To fully leverage the advantages of synergistic vision, a consistency constraint is applied to align their category probability prediction distributions, which helps ensure consistency in classification decisions between the two branches. Experimental results on the PaviaU dataset demonstrate that HEDBNet outperforms other advanced algorithms in terms of overall accuracy(OA), average accuracy(AA), and Kappa coefficient. This proves that HEDBNet can simultaneously focus on primary and secondary spectral features, thus significantly boosting classification accuracy. © 2024 IEEE.

关键词： image annotation

来源：评论

学校读者我要写书评

暂无评论

Multi-scale Dual Attention and Global Feature Extraction Enhanced Diffusion Model for Medical image Segmentation 2

Multi-scale Dual Attention and Global Feature Extraction Enh...

引用

2nd international conference on image processing, computer vision and Machine Learning, ICICML 2023

作者： Wei, Jiaxuan Liu, Shifa Tang, Jiawei Luo, Ge Wang, Shuichao Liu, Yichen Lanzhou University School of Information Science and Engineering Lanzhou China

ISBN: (纸本)9798350331417

Denoising Diffusion Probabilistic Models (DDPMs) have garnered significant interest due to their notable capabilities in image generation. The models could used for lesion segmentation in medical images. However, a prevailing challenge with these models is that they fail to capture global information. Our proposed MDADiff addresses this limitation. Drawing inspiration from the transformer paradigm, MDADiff employs a novel approach for global information capture. Furthermore, by integrating Multi-scale Dual Attention, MDADiff effectively handles semantic information, offering more detailed segmentation insights and accelerating convergence. Importantly, we also obtained the uncertain map for each test slice. Compared with the original diffusion models, our proposed model performs achieves superior performance on the brain tumor segmentation dataset Brats2021. © 2023 IEEE.

关键词： Deep Learning Diffusion Models image Segmentation

来源：评论

学校读者我要写书评

暂无评论

3D animation face modeling and feature extraction based on computer graphics and image processing technology 2

3D animation face modeling and feature extraction based on c...

引用

2nd international conference on computer Graphics, image and Virtualization, ICCGIV 2022

作者： Liu, Yuandong Liu, Xiansheng Liu, Zhiwei Institute of Guangzhou Department of Games Software Engineering Guangzhou510990 China

ISBN: (纸本)9781665492508

After long-term efforts, people have created the era of computer 3D vision technology. In the field of new media, the application of graphics technology in animation industry is very extensive[1]. Through the analysis of computer graphics and image processing technology, this paper accurately expounds the specific process and related algorithms of 3D animation face modeling technology. On this basis, this paper also explains the specific algorithm of feature extraction in 3D design. On the basis of improving animation design, follow the design requirements of realism. © 2022 IEEE.

关键词： Animation

来源：评论

学校读者我要写书评

暂无评论

Text-to-image approach combining information blending structure and attention 2

Text-to-image approach combining information blending struct...

引用

2nd international conference on image processing, computer vision and Machine Learning, ICICML 2023

作者： Bai, Chuanao Zhang, Chao Li, Linxuan Tian, Lin Institute of Computer Science and Technology Changchun University of Science and Technology Changchun China

ISBN: (纸本)9798350331417

The semantic consistency, loss of detail features, and other problems are caused by the traditional text generation image method's focus on extracting the information transmitted by the previous layer while ignoring the information of the layer's features that are lost during the subsequent propagation process. Text-to-images combining information blending structure and attention (CAGAN) with information fusion capabilities is suggested in order to address the aforementioned issues. The word and sentence levels of the text's characteristics are encoded using the pre-trained BiLSTM model. The network structure includes a feature fusion module that receives upper-level transmission information while maintaining feature information at the same level. The resulting image's semantic coherence is enhanced, and the image's features are refined, thanks to the application of the affine transformation to map the visual features based on natural language descriptions. According to the experimental findings, the CAGAN's FID score in the CUB dataset is 15.93, and its IS index is 4.84±0.04 in the CUB dataset. It has been greatly improved when compared to the current standard AttGAN and DMGAN models, demonstrating the usefulness of the suggested network. © 2023 IEEE.

关键词： affine transformation BiLSTM feature fusion module visual features

来源：评论

学校读者我要写书评

暂无评论

Deep Learning-Based image Analysis to Track Vehicles 2

Deep Learning-Based Image Analysis to Track Vehicles

引用

2nd international conference on Disruptive Technologies, ICDT 2024

作者： Prabakaran, P. Jayasudha, R. Sandhu, Mukta Gupta, Sandeep School of Computing Sciences Vels Institute of Science Technology and Advanced Studies Department of Computer Applications Chennai India Dr.N.G.P.Institute of Technology Department of Mathematics Coimbatore India Shri Vishwakarma Skill University Skill Department of Computer Science and Engineering Haryana Palwal India Department of Electrical Engineering Dehradun India

ISBN: (纸本)9798350371055

There are many ways to track the traffic conditions on roads. With the rise of AI-based image processing technology, there has been a surge in interest in developing traffic monitoring systems that rely on camera vision data. An improved road monitoring system may be derived from the data collected in this research by placing a camera at a junction. The technique detects and classifies vehicles using a deep-learning-based methodology (YOLOv4). By comparing the positions of the vehicle with the map HD, lane-by-lane trajectories of the vehicle may be approximated. The predicted vehicle trajectories are used to calculate each lane's wait lengths and traffic volumes, broken down by travel direction. This technique was evaluated using five distinct metrics: vehicle detection rates, trajectory prediction, type of vehicle categorization, traffic volume estimate, and queue length assessment. Thousands of samples were used to assess its performance. Based on the findings, it is acceptable to assume that the system can identify vehicles with a 98% success rate and an error rate of less than 25% regarding lane-by-lane trip volume estimation and vehicle type classification. Therefore, this study's approach reveals the viability of collecting comprehensive traffic information from a camera set up at a junction. Current traffic monitoring schemes have a reasonable likelihood of being developed by this study's significant contribution, which is a strategy that combines AI with HD map approaches. © 2024 IEEE.

关键词： Artificial Intelligence HD Map Traffic Monitoring System Vehicle Type Classification YOLOv4

来源：评论

学校读者我要写书评

暂无评论

Gland segmentation based on morphological clues and feature fusion 2

Gland segmentation based on morphological clues and feature ...

引用

2nd international conference on image processing, computer vision and Machine Learning, ICICML 2023

作者： Zeng, Lingqi Wang, Huadeng Guan, Junlin Guilin University of Electronic Technology Guangxi Key Laboratory of Image and Graphic Intelligent Processing Guilin541004 China

ISBN: (纸本)9798350331417

The task of gland segmentation based on deep learning serves as a crucial auxiliary tool for diagnosing cancer. However, existing methods still exhibit shortcomings in handling gland adhesion and scale adaptability. To address these issues, we propose a gland segmentation approach that leverages morphological cues and multi-level feature fusion. By analyzing the morphological and imaging characteristics of glands, we have devised a novel scheme for label generation and loss weighting to guide model training. This scheme helps alleviate the challenge posed by the presence of adjacent glands and their adhesion. Additionally, by exploring the correlation between semantic features at different levels, we have developed a new feature fusion mechanism to mitigate issues related to model inaccuracies arising from variations in gland scales. Through experimental comparisons and discussions with classical and state-of-the-art methods, we demonstrate the effectiveness of our proposed approach. © 2023 IEEE.

关键词： Feature fusion Gland segmentation Morphological cues Multi-level feature

来源：评论

学校读者我要写书评

暂无评论

Detection of Diabetic Retinopathy from fundus images using Resnet50 2

Detection of Diabetic Retinopathy from fundus images using R...

引用

2nd international conference on Paradigm Shifts in Communications Embedded Systems, Machine Learning and Signal processing, PCEMS 2023

作者： Ali, Sarvat Raut, Shital Visvesvaraya National Institute of Technology Department of Computer Science and Engineering Nagpur India

ISBN: (纸本)9798350310719

High blood glucose levels cause lesions on the retina of the eye, resulting in a degenerative condition known as diabetic retinopathy (DR), which impacts vision and can cause irreversible vision loss. The most common cause of blindness in diabetic people is thought to be diabetic retinopathy. Early diagnosis of diabetic retinopathy is essential to efficiently maintaining the patient's vision. We attempted to give first-hand verification to this fundamental problem of DR detection to save time, money and efforts of ophthalmologists. The latter also proved to be more challenging, especially early on in the disease, when disease characteristics are less obvious in the fundus images. Deep learning algorithms and machine learning-based medical image analysis have aided in the early identification of diabetic retinopathy along with the evaluation of retinal fundus images. This paper attempts to preprocess and binary classify fundus images from the famous Aptos dataset using finetuned ResNet50 as well as features extraction from ResNet50 and later classifying using machine learning models. We have achieved an accuracy of 0.9802, an AUC score of 0.9937, F1 score of 0.9870, a precision of 0.9890, a recall as 0.9845 and kappa score of 0.9481 on the evaluation data by fine-tuning of ResNet50. © 2023 IEEE.

关键词： Learning algorithms

来源：评论

学校读者我要写书评

暂无评论

Enhancing Insect image Recognition with Sand Cat Swarm Optimization with Deep Feature Extraction 2

Enhancing Insect Image Recognition with Sand Cat Swarm Optim...

引用

2nd IEEE international conference on Advances in Information Technology, ICAIT 2024

作者： Yogaraja, C.A. Priyanka, C. Priyadharshini, S.P. Babu, J. Jagan Rajagopal, S. Poorani, S. Ramco Institute of Technology Rajapalayam India School of Artificial Intelligence Amrita Vishwa Vidyapeetham Coimbatore Campus India St. Joseph's College of Engineering OMR Chennai119 India Department of ECE R.M.D Engineering College Kavaraipettai India Department of IT National Engineering College Kovilppati India Kongu Engineering College Perundurai Erode India

ISBN: (纸本)9798350383867

Insect image recognition (IIR) is a specified field in machine learning (ML) and computer vision that efforts to automatically recognise and detection of insect species utilizing visual data attained from images. Leveraging deep learning (DL) techniques, convolutional neural network (CNN), and image processing enables exact and effective classification of a huge range of insect species. IIR has many applications that range from biodiversity observation and pest control in farming in order to entomological study and disease vector identification. The unique procedure of insect detection, it permits experts, entomologists, and ecologists to attain valuable insights, make knowledgeable decisions, and update challenges that contain insect detection which contribute to more real conservation efforts, ecological research, and agriculture management. This work contains a framework of Insect image Recognition with Sand Cat Swarm Optimization with Deep Feature Extraction (IIR-SCSODFR) model. The developed IIR-SCSODFR method incorporates a complete procedure that starts with Gaussian filtering-based image pre-processing, improving image quality and decreasing noise in order to offer a clear basis for precise analysis. Deep feature extraction is carried out to capture intricate visual designs essential to numerous insect species, using advanced models for inclusive insect characterization. For exact insect detection, Long Short-Term Memory (LSTM) systems are employed, proficient in demonstrating time-based needs in image sequences. Besides, model leverages SCSO technique for parameter tuning, adjusting model's performance to adjust unique features of a dataset. The proposed IIR-SCSODFR model signifies an important leap forward in IIR, and provides a forceful and precise solution for automated identification of various insect species. © 2024 IEEE.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Applying Genetic Algorithm and image Quality Assessment for Reproducible processing of Low-light images

Applying Genetic Algorithm and Image Quality Assessment for ...

引用

international conference on image processing and vision Engineering (IMPROVE)

作者： Parisot, Olivier Tamisier, Thomas Luxembourg Inst Sci & Technol List 5 Ave Hauts Fourneaux L-4362 Esch Sur Alzette Luxembourg

ISBN: (纸本)9789897585630

Reproducible images preprocessing is fundamental in computer vision, whether to fairly compare process algorithms or to prepare new images corpus. In this paper, we propose an approach based on genetic algorithm combined to image Quality Assessment methods to obtain a reproducible sequence of transformations for improving low-light images. Preliminary tests have been performed on state-of-the-art benchmarks.

关键词： Low-light images image Quality Assessment Genetic Algorithms

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180页 << < 21 22 23 24 25 26 27 28 29 30 > >>

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：