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

15,874 篇 会议
207 篇 期刊文献
147 册 图书
1 篇 专利

馆藏范围

16,230 篇 电子文献
0 种 纸本馆藏

日期分布

学科分类号

10,022 篇 工学
- 8,692 篇 计算机科学与技术...
- 6,598 篇 软件工程
- 3,111 篇 信息与通信工程
- 2,993 篇 光学工程
- 2,501 篇 生物工程
- 1,558 篇 控制科学与工程
- 1,487 篇 生物医学工程（可授...
- 1,169 篇 电气工程
- 854 篇 电子科学与技术（可...
- 620 篇 化学工程与技术
- 562 篇 安全科学与工程
- 541 篇 机械工程
- 472 篇 网络空间安全
- 399 篇 交通运输工程
- 342 篇 仪器科学与技术
- 282 篇 材料科学与工程（可...
5,917 篇 理学
- 2,958 篇 物理学
- 2,563 篇 生物学
- 1,899 篇 数学
- 677 篇 化学
- 664 篇 统计学（可授理学、...
2,183 篇 管理学
- 1,290 篇 图书情报与档案管...
- 1,024 篇 管理科学与工程(可...
- 410 篇 工商管理
1,628 篇 医学
- 1,459 篇 临床医学
- 891 篇 基础医学(可授医学...
- 759 篇 药学(可授医学、理...
- 260 篇 公共卫生与预防医...
344 篇 农学
- 337 篇 作物学
302 篇 法学
- 280 篇 社会学
166 篇 经济学
135 篇 教育学
65 篇 文学
38 篇 军事学
2 篇 哲学
2 篇 历史学
2 篇 艺术学

主题

1,289 篇 computer vision
783 篇 deep learning
488 篇 image segmentati...
413 篇 image processing
386 篇 object detection
360 篇 image enhancemen...
339 篇 feature extracti...
305 篇 convolutional ne...
299 篇 image classifica...
275 篇 machine learning
202 篇 training
200 篇 computational mo...
198 篇 signal processin...
195 篇 image recognitio...
168 篇 visualization
163 篇 neural networks
158 篇 artificial intel...
153 篇 convolution
150 篇 face recognition
132 篇 generative adver...

机构

54 篇 chitkara univers...
41 篇 peng cheng labor...
39 篇 university of ch...
38 篇 school of comput...
32 篇 university of sc...
31 篇 tsinghua univers...
30 篇 the islamic univ...
26 篇 college of compu...
26 篇 college of compu...
25 篇 school of comput...
24 篇 shanghai jiao to...
23 篇 school of electr...
22 篇 college of compu...
21 篇 shenzhen interna...
21 篇 school of comput...
20 篇 school of comput...
19 篇 centre of interd...
19 篇 department of co...
19 篇 national univers...
19 篇 shanghai ai labo...

作者

18 篇 li li
18 篇 chen chen
18 篇 yang yang
16 篇 lee sung-hak
16 篇 liu yang
14 篇 jia zhenhong
14 篇 li yang
14 篇 kim young-choon
13 篇 hao zhang
13 篇 luc van gool
12 篇 luo xiaonan
12 篇 zhou gang
12 篇 zhang bo
11 篇 yulun zhang
11 篇 wang wei
10 篇 li xin
10 篇 zhang lei
10 篇 wang jing
10 篇 chen dong
10 篇 liu lei

语言

15,814 篇 英文
400 篇 其他
143 篇 中文
3 篇 土耳其文
2 篇 西班牙文

检索条件"任意字段=2023 International Conference on Image Processing and Computer Vision, IPCV 2023"

共 16230 条记录，以下是4721-4730 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：

Hybrid Edge Detection and Singular Value Decomposition for image Background Removal 7th

Hybrid Edge Detection and Singular Value Decomposition for I...

引用

7th National conference on New Trends in Information and Communications Technology Applications, NTICT 2023

作者： Faisal, Zahraa Ameer, Esraa H. Abdul El Abbadi, Nidhal K. Computer Science Department Education College University of Kufa Najaf Iraq Computer Science Department College of Education for Girls University of Kufa Najaf Iraq Al-Mustaqbal Center for AI Applications Al-Mustaqbal University Babylon Iraq

ISBN: (纸本)9783031628139

image background removal is a crucial technique for enhancing the visual impact of images or altering their composition, finding applications in various fields such as photography and computer vision. This process can be executed manually through conventional image editing software or automated using advanced image processing algorithms. In this context, we present a novel algorithm that combines edge detection and singular value decomposition (SVD) to precisely segment the primary connected object within RGB images. The proposed methodology initiates with pre-processing and edge detection, leveraging an innovative filter amalgamating Markov and Laplace filters. Subsequently, the image undergoes block division, and features are extracted through the application of SVD transformation. To ensure optimal threshold determination, a unique approach is employed, resulting in the generation of a binary image. In the final stage, morphological operations are implemented to rectify fragmented object sections, eliminate small artifacts, and fill in gaps. The binary image, when multiplied by the original image, yields a meticulously segmented color object. This paper’s distinctive contributions include the introduction of a novel threshold determination approach and the utilization of SVD for image background removal. Comparative assessments against alternative strategies consistently affirm the efficacy of our proposed technique, with accuracy measurements reaching up to 99%. The experimental results underscore the robustness and superiority of our approach, establishing it as a valuable addition to the repertoire of image background removal methodologies. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2024.

关键词： Morphology

来源：评论

学校读者我要写书评

暂无评论

Generating Scene Layout from Textual Descriptions Using Transformer 10

Generating Scene Layout from Textual Descriptions Using Tran...

引用

10th international conference on Advanced Informatics: Concept, Theory and Application, ICAICTA 2023

作者： Takahashi, Haruka Kuriyama, Shigeru Toyohashi University of Technology Computer Science and Engineering Aichi Japan

ISBN: (纸本)9798350329919

Creating images through generative AI technology is still challenging because it requires specifying detailed layouts and contents of objects. This paper introduces a layout generation method that uses Transformer-based deep neural networks to generate scene representations with multiple objects. This approach allows for an explainable layout of the image's objects, generated automatically from the text. Unlike the conventional layout generation process that requires sequential object predictions and post-processing of duplicate bounding boxes, our end-To-end approach uses parallel decoding. We conducted experiments to compare our method's quality and computational cost against existing ones, demonstrating its effectiveness and efficiency in generating layouts from textual representations. Our Text-To-Layout approach offers practical authoring tools that are computable with relatively lightweight networks while facilitating explainable image generation. © 2023 IEEE.

关键词： Deep neural networks

来源：评论

学校读者我要写书评

暂无评论

Infrared and Visible image Fusion by Using Multi-Scale Transformation and Fractional-Order Gradient Information 48

Infrared and Visible Image Fusion by Using Multi-Scale Trans...

引用

48th IEEE international conference on Acoustics, Speech and Signal processing, ICASSP 2023

作者： Wu, Shiwei Zhang, Kang Yuan, Xia Zhao, Chunxia Nanjing University of Science and Technology School of Computer Science and Engineering Nanjing210094 China

ISBN: (纸本)9781728163277

The fusion of infrared and visible images is hard due to their different modalities. Different from existing methods using the integer-order gradient, we design an optimization model to fuse infrared and visible images using fractional-order gradient information. In this way, the complementary information of the source images can be better preserved. In order to better highlight the target and retain effective details, we use the results of the optimization model as pre-fusion images to guide the final image fusion. For better highlighting the target, we use MDLatLRR to extract the base layer of the pre-fusion image and use it as the base layer of the fused image. In addition, for getting more effective details, we use the pre-fusion image to calculate the weight map, which is used as the tradeoff parameter of the norm optimization problem to get the fused detail layers. Experimental results show that our method can highlight the target better while maintaining effective details. Compared with the current state-of-the-art image fusion methods, our method shows better fusion performance in both subjective and objective evaluation. © 2023 IEEE.

关键词： image fusion

来源：评论

学校读者我要写书评

暂无评论

An Efficient Knock Code Decoding Approach to assist the People with Communication Impairments 3

An Efficient Knock Code Decoding Approach to assist the Peop...

引用

3rd international conference on Advanced Research in Computing, ICARC 2023

作者： Surasinghe, Pabasara Thanikasalam, Kokul University of Vavuniya Department of Physical Science Sri Lanka University of Jaffna Department of Computer Science Sri Lanka

ISBN: (纸本)9798350347371

Communicating with communication impaired people is a challenging task for doctors and caretakers and hence computer based automated assistant systems are important to identify their needs in real-time. An efficient automated assistant system should be simple, fast and easy to use. To achieve these objectives, we have proposed a novel communication assistant approach based on the Knock code. In the proposed approach, communication impaired people are able to encode their messages into knock sounds. Then the sound patterns are decoded as the English words by processing the corresponding waveform images using a sequence of image processing algorithms. Finally, the decoded text is displayed to the patient and a voice message is also produced. Based on the evaluation studies, proposed approach is able to recognize the English words with accuracy of 94.11 percentage in real-time. © 2023 IEEE.

关键词： Taps

来源：评论

学校读者我要写书评

暂无评论

TON-ViT: A Neuro-Symbolic AI Based on Task Oriented Network with a vision Transformer 27th

TON-ViT: A Neuro-Symbolic AI Based on Task Oriented Network ...

引用

27th Annual conference on Medical image Understanding and Analysis (MIUA)

作者： Zhuo, Yupeng Jiang, Nina Kirkpatrick, Andrew W. Couperus, Kyle Oanh Tran Beck, Jonah DeVane, DeAnna Candelore, Ross McKee, Jessica Gorbatkin, Chad Birch, Eleanor Colombo, Christopher Duerstock, Bradley Wachs, Juan Purdue Univ Sch Ind Engn W Lafayette IN 47907 USA Univ Calgary Calgary AB Canada Madigan Army Med Ctr Joint Base Lewis McChord WA USA William Beaumont Army Med Ctr Ft Bliss TX USA Geneva Fdn Tacoma WA USA

ISBN: (纸本)9783031485923;9783031485930

The objective of this paper is to present a neuro-symbolic AI based technique to represent field-medicine knowledge, referred as to TON-ViT. TON-ViT integrates a Deep Learning Model with an explicit symbolic manipulation, a task graph. This task graph describes the steps of each trauma resuscitation as denoted by a verb and noun pair. Through this representation, symbolic processing and manipulation on task graphs, we can find stereotypical procedures, regardless of style of the performer. Furthermore, we can use this technique to find differences in styles, errors, shortcuts and generate procedures never seen before. When used in combination with a transformer, it can help recognize actions in egocentric vision datasets. Last, through symbolic manipulations on the graph, it is possible to generate medical knowledge which the model has not seen before. We present preliminary results after testing the TON-ViT with the Trauma Thompson Dataset.

关键词： task graph knowledge graph semantic understanding vision transformer neuro-symbolic AI medical procedures

来源：评论

学校读者我要写书评

暂无评论

Tracked-Vehicle Retrieval by Natural Language Descriptions with Multi-Contextual Adaptive Knowledge

Tracked-Vehicle Retrieval by Natural Language Descriptions w...

引用

2023 IEEE/CVF conference on computer vision and Pattern Recognition Workshops, CVPRW 2023

作者： Le, Huy Dinh-Anh Qui-Vinh Nguyen, Quang Luu, Duc Trung Thi-Thanh Chau, Truc Chung, Nhat Minh Viet-Uyen Ha, Synh International University School of Computer Science and Engineering Ho Chi Minh City Viet Nam Vietnam National University Ho Chi Minh City Viet Nam

ISBN: (纸本)9798350302493

This paper introduces our solution for Track 2 in AI City Challenge 2023. The task is tracked-vehicle retrieval by natural language descriptions with a real-world dataset of various scenarios and cameras. Our solution mainly focuses on four points: (1) To address the linguistic ambiguity in the language query, we leverage our proposed standardized version for text descriptions for the domain-adaptive training and post-processing stage. (2) Our baseline vehicle retrieval model utilizes CLIP to extract robust visual and textual feature representations to learn the unified cross-modal representations between textual and visual features. (3) Our proposed semi-supervised domain adaptive (SSDA) training method is leveraged to address the domain gap between the train and test set. (4) Finally, we propose a multi-contextual post-processing technique that prunes out the wrong results based on multi-contextual attributes information that effectively boosts the final retrieval results. Our proposed framework has yielded a competitive performance of 82.63% MRR accuracy on the test set, achieving 1st place in the competition. Codes will be available at https://***/zef1611/AIC23-NLRetrieval-HCMIU-CVIP © 2023 IEEE.

关键词： Tracked vehicles

来源：评论

学校读者我要写书评

暂无评论

Multi-directional Total Variation Hyperspectral image Destriping based on Tensor Decomposition and Group Sparsity 4

Multi-directional Total Variation Hyperspectral Image Destri...

引用

4th international conference on computer, Big Data and Artificial Intelligence, ICCBD+AI 2023

作者： Deng, Lizhen Xu, Guoxia Wang, Zhongyang Zhu, Hu Nanjing University of Posts and Telecommunications School of Communications and Information Engineering Nanjing China

ISBN: (纸本)9798350373233

Most of the traditional destriping work is based on matrix domain (band-by-band) processing hyperspectral images, although satisfactory results can be obtained, some important prior conditions are still ignored. In fact, a hyperspectral remote sensing data can be regarded as a third-order tensor, and the space-spectrum Total Variation based on the tensor has been widely used in destriping work. However, the processing of the strip part rarely involves tensor operations. Driven by the high correlation between hyperspectral data in different spectral bands, in this paper, we proposed a multi-directional total variation destriping algorithm based on tensor decomposition and group sparsity. For the target image, a multi-directional full variational regularization constraint is used to ensure piecewise smoothness while preserving continuity between adjacent spectrums. For stripe noise, we adopted low-rank Dicker decomposition and weighted L21 norm joint constraints. Low-rank Dicker decomposition treats stripe noise as a tensor data, which can better describe global correlation;Weighted L21 norm is used to describe group sparsity of stripe noise. A series of experimental results show that our algorithm can effectively remove all kinds of stripe noise while better retaining the detailed information of the target image. © 2023 IEEE.

关键词： Tensors

来源：评论

学校读者我要写书评

暂无评论

'Pre-training+Fine-tuning' Model-based 1/2 Folded image Restoration 4

'Pre-training+Fine-tuning' Model-based 1/2 Folded Image Rest...

引用

4th international Symposium on computer Engineering and Intelligent Communications, ISCEIC 2023

作者： Song, Huijia Wei, Jiacheng Lin, Xiaozhu Zhang, Huainian Beijing Institute of Petrochemical Technology School of Information Engineering Beijing102617 China

ISBN: (纸本)9798350306323

The 1/2 folded image refers to folding the original image at the halfway point along the horizontal or vertical direction, creating an image with partial overlap. The purpose of restoring 1/2 folded images is to repair folded, damaged, or partially hidden images in order to restore image integrity, recover data, analyze and process images, and perform reverse hiding and steganography analysis. In response to the restoration problem of 1/2 folded images, a model called 'pre-training + fine-tuning' was applied to restore folded images using unsupervised pre-training and supervised fine-tuning modes. The WGAN-GP model with gradient penalty is used for the pre-training model. A four-layer non-linear fully connected network is selected for the fine-tuning model. The experimental process consists of two stages. Firstly, the WGAN-GP network is subjected to unsupervised pre-training to obtain a generator capable of generating clear images. Then, in the fine-tuning stage, the output of the generator is used as the input for a fully connected network, and the target results of the fully connected network model are fixed for fine-tuning, aiming to restore the folded images to be close to the original ones. The applied method is validated on the MNIST and Fashion-MNIST datasets in this paper. The experimental result shows that the 'pre-training + fine-tuning' mode achieves good restoration performance on 1/2 folded handwritten digit images and Fashion-MNIST images, with the maximum similarity score between the restored images and the original images is around 0.98. Moreover, this technique can enhance image quality and information integrity, expand the application areas of image processing and computer vision. © 2023 IEEE.

关键词： Restoration

来源：评论

学校读者我要写书评

暂无评论

Poisoning-Based Backdoor Attacks in computer vision 37

Poisoning-Based Backdoor Attacks in Computer Vision

引用

37th AAAI conference on Artificial Intelligence, AAAI 2023

作者： Li, Yiming Tsinghua Shenzhen International Graduate School Tsinghua University China

ISBN: (纸本)9781577358800

Recent studies demonstrated that the training process of deep neural networks (DNNs) is vulnerable to backdoor attacks if third-party training resources (e.g., samples) are adopted. Specifically, the adversaries intend to embed hidden backdoors into DNNs, where the backdoor can be activated by pre-defined trigger patterns and leading malicious model predictions. My dissertation focuses on poisoning-based backdoor attacks in computer vision. Firstly, I study and propose more stealthy and effective attacks against image classification tasks in both physical and digital spaces. Secondly, I reveal the backdoor threats in visual object tracking, which is representative of critical video-related tasks. Thirdly, I explore how to exploit backdoor attacks as watermark techniques for positive purposes. I design a Python toolbox (i.e., BackdoorBox) that implements representative and advanced backdoor attacks and defenses under a unified and flexible framework, based on which to provide a comprehensive benchmark of existing methods at the end. Copyright © 2023, Association for the Advancement of Artificial Intelligence (***). All rights reserved.

关键词： Deep neural networks

来源：评论

学校读者我要写书评

暂无评论

Emotion Recognition using Autoencoders: A Systematic Review

Emotion Recognition using Autoencoders: A Systematic Review

引用

2023 international conference on Intelligent Systems for Communication, IoT and Security, ICISCoIS 2023

作者： Mohana, M. Subashini, P. Avinashilingam University Department of Computer Science Coimbatore India

ISBN: (纸本)9798350335835

During recent decades, facial expression recognition is a hot area of research in deep learning and computer vision. However, numerous research has been done on emotion recognition through facial expression using deep neural networks and achieved remarkable results on image datasets. Moreover, convolutional neural networks (CNN) often require a large number of layers when extracting useful information from facial images, thus increasing the network complexity and training time. For overcoming the challenges in CNN, researchers have been employing autoencoders to recognize facial emotions. This paper reviews all available work on autoencoders using facial expression recognition, and variations in autoencoders. For this analysis, a literature review paper has been collected from IEEE, Scopus, and Web of Science databases. Furthermore, publicly available facial expression recognition benchmark datasets are discussed. In addition, this paper discusses how unsupervised autoencoder has been applied in classification problems. Furthermore, this comprehensive review will be helpful for young researchers in FER and provide an overview of autoencoder in facial emotion recognition using facial expressions. © 2023 IEEE.

关键词： Emotion Recognition

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 << < 469 470 471 472 473 474 475 476 477 478 > >>

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：