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

25,302 篇 会议
282 篇 期刊文献
21 册 图书
3 篇 学位论文

馆藏范围

25,608 篇 电子文献
0 种 纸本馆藏

日期分布

学科分类号

15,841 篇 工学
- 9,889 篇 计算机科学与技术...
- 6,081 篇 电气工程
- 5,776 篇 信息与通信工程
- 5,626 篇 软件工程
- 2,039 篇 光学工程
- 1,454 篇 控制科学与工程
- 1,281 篇 机械工程
- 1,155 篇 电子科学与技术（可...
- 876 篇 生物医学工程（可授...
- 833 篇 生物工程
- 797 篇 仪器科学与技术
- 265 篇 网络空间安全
- 253 篇 化学工程与技术
- 246 篇 安全科学与工程
- 241 篇 交通运输工程
- 183 篇 材料科学与工程（可...
- 167 篇 土木工程
- 164 篇 建筑学
5,729 篇 理学
- 3,491 篇 物理学
- 2,209 篇 数学
- 886 篇 生物学
- 567 篇 统计学（可授理学、...
- 419 篇 系统科学
- 313 篇 化学
3,024 篇 医学
- 2,899 篇 临床医学
- 314 篇 基础医学(可授医学...
- 229 篇 药学(可授医学、理...
1,396 篇 管理学
- 853 篇 管理科学与工程(可...
- 615 篇 图书情报与档案管...
- 169 篇 工商管理
181 篇 法学
134 篇 农学
58 篇 教育学
52 篇 文学
51 篇 经济学
51 篇 军事学
22 篇 艺术学

主题

3,124 篇 image processing
2,086 篇 image coding
2,026 篇 visualization
1,755 篇 image segmentati...
1,490 篇 feature extracti...
1,083 篇 image reconstruc...
908 篇 cameras
885 篇 signal processin...
833 篇 image color anal...
756 篇 humans
717 篇 image edge detec...
692 篇 image enhancemen...
666 篇 computer vision
651 篇 training
582 篇 image analysis
574 篇 deep learning
536 篇 image quality
481 篇 conferences
473 篇 object detection
470 篇 robustness

机构

51 篇 school of electr...
49 篇 shanghai jiao to...
39 篇 ieee
38 篇 university of sc...
36 篇 shanghai jiao to...
36 篇 school of comput...
34 篇 shanghai jiao to...
33 篇 university of ch...
32 篇 microsoft resear...
26 篇 national institu...
25 篇 department of el...
24 篇 hendisli&#x011f
23 篇 institute for in...
23 篇 institute of ima...
23 篇 istanbul teknik ...
23 篇 institute of dig...
22 篇 peking univ inst...
21 篇 institute of inf...
21 篇 univ chinese aca...
21 篇 univ sci & techn...

作者

62 篇 guangtao zhai
46 篇 song li
45 篇 zhai guangtao
32 篇 jie yang
27 篇 li li
25 篇 m. vetterli
25 篇 bovik alan c.
25 篇 li sumei
25 篇 li song
25 篇 sarp ertürk
24 篇 jing zhang
24 篇 b. macq
23 篇 zhang lei
23 篇 li zhuo
23 篇 d.r. bull
22 篇 jürgen seiler
21 篇 shi guangming
20 篇 liu yang
20 篇 zhang wenjun
18 篇 mohamed-chaker l...

语言

24,611 篇 英文
489 篇 土耳其文
393 篇 其他
137 篇 中文
2 篇 西班牙文
2 篇 葡萄牙文

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

共 25608 条记录，以下是4171-4180 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：

Pre-training with Synthetic Patterns for Audio

Pre-training with Synthetic Patterns for Audio

引用

International conference on Acoustics, Speech, and Signal processing (ICASSP)

作者： Yuchi Ishikawa Tatsuya Komatsu Yoshimitsu Aoki LY Corporation Keio University Tokyo Japan LY Corporation Tokyo Japan Keio University Kanagawa Japan

ISBN: (数字)9798350368741

ISBN: (纸本)9798350368758

In this paper, we propose to pre-train audio encoders using synthetic patterns instead of real audio data. Our proposed framework consists of two key elements. The first one is Masked Autoencoder (MAE), a self-supervised learning framework that learns from reconstructing data from randomly masked counterparts. MAEs tend to focus on low-level information such as visual patterns and regularities within data. Therefore, it is unimportant what is portrayed in the input, whether it be images, audio mel-spectrograms, or even synthetic patterns. This leads to the second key element, which is synthetic data. Synthetic data, unlike real audio, is free from privacy and licensing infringement issues. By combining MAEs and synthetic patterns, our framework enables the model to learn generalized feature representations without real data, while addressing the issues related to real audio. To evaluate the efficacy of our framework, we conduct extensive experiments across a total of 13 audio tasks and 17 synthetic datasets. The experiments provide insights into which types of synthetic patterns are effective for audio. Our results demonstrate that our framework achieves performance comparable to models pre-trained on AudioSet-2M and partially outperforms image-based pre-training methods.

关键词： Data privacy visualization Autoencoders Self-supervised learning Signal processing Licenses Data models Speech processing image reconstruction Synthetic data

来源：评论

学校读者我要写书评

暂无评论

FEW-SHOT image CLASSIFICATION WITH MULTI-FACET PROTOTYPES

FEW-SHOT IMAGE CLASSIFICATION WITH MULTI-FACET PROTOTYPES

引用

ieee International conference on Acoustics, Speech and Signal processing (ICASSP)

作者： Yan, Kun Bouraoui, Zied Wang, Ping Jameel, Shoaib Schockaert, Steven Peking Univ Sch Software & Microelect Beijing Peoples R China Univ Artois CRIL Arras France CNRS Paris France Peking Univ Natl Engn Res Ctr Software Engn Beijing Peoples R China Minist Educ Key Lab High Confidence Software Technol PKU Beijing Peoples R China Univ Essex Sch Comp Sci & Elect Engn Colchester Essex England Cardiff Univ Sch Comp Sci & Informat Cardiff Wales

ISBN: (纸本)9781728176055

The aim of few-shot learning (FSL) is to learn how to recognize image categories from a small number of training examples. A central challenge is that the available training examples are normally insufficient to determine which visual features are most characteristic of the considered categories. To address this challenge, we organise these visual features into facets, which intuitively group features of the same kind (e.g. features that are relevant to shape, color, or texture). This is motivated from the assumption that (i) the importance of each facet differs from category to category and (ii) it is possible to predict facet importance from a pre-trained embedding of the category names. In particular, we propose an adaptive similarity measure, relying on predicted facet importance weights for a given set of categories. This measure can be used in combination with a wide array of existing metric-based methods. Experiments on miniimageNet and CUB show that our approach improves the state-of-the-art in metric-based FSL.

关键词： Few-shot learning multi-facet representations metric-based learning BERT

来源：评论

学校读者我要写书评

暂无评论

Comparative Analysis of Vision Transformers and Morphological Approaches for Ki-67 Index Estimation on Histopathologic images: An Experimental Evaluation

Comparative Analysis of Vision Transformers and Morphologica...

引用

ieee Signal processing and communications Applications (SIU)

作者： Ahmet Sezer Akdeniz Berkan Özgür Emre Şahin Özge Öztimur Karadağ Özlem Ceren Günizi Bilgisayar Mühendisliği Bölümü Alanya Alaaddin Keykubat Üniversitesi Antalya Türkiye Tıbbi Patoloji Ana Bilim Dalı Alanya Alaaddin Keykubat Üniversitesi Antalya Türkiye

ISBN: (数字)9798350388961

ISBN: (纸本)9798350388978

This research comprehensively compares two different methodologies for predicting the Ki-67 index- morphological-based analysis and Vision Transformers (ViT). The morphological method focuses on the shape and structural features of tissues and cell structures. On the other hand, Vision Transformers represents an innovative approach developed through the use of attention mechanisms and transformer architectures. ViT offers a different perspective by modeling global context information in recognizing image patterns. This analysis provides a deeper understanding of the accuracy, efficiency, and applicability of current techniques in histopathological image processing, highlighting the potential to advance existing methodologies used in cancer diagnosis. This comparative study aims to evaluate the performance differences between morphological analyses and transformer-based models, identifying the most effective and reliable methods for predicting the Ki-67 index. Experimental analysis, revealed that due to the limited number of labeled data on this domain, traditional morphologic approaches are currently more promising than the vision transformers.

关键词： Computer vision Shape Microprocessors Computer architecture Signal processing Predictive models Pattern recognition

来源：评论

学校读者我要写书评

暂无评论

DUNE: Deep UNcertainty Estimation for tracked visual features

DUNE: Deep UNcertainty Estimation for tracked visual feature...

引用

International image processing, Applications and Systems conference (IPAS)

作者： Katia Sousa Lillo Andrea de Maio Simon Lacroix Amaury Negre Michéle Rombaut Nicolas Marchand Nicolas Vercier Thales AVS Thales Group Valence France GIPSA-lab Univ. Grenoble Alpes CNRS Grenoble INP Grenoble France LAAS-CNRS Université de Toulouse Toulouse France

ISBN: (纸本)9781665462204

Uncertainty estimation of visual feature is essential for vision-based systems, such as visual navigation. We show that errors inherent to visual tracking, in particular using KLT tracker, can be learned using a probabilistic loss function to estimate the covariance matrix on each tracked feature position. The proposed system is trained and evaluated on synthetic data, as well as on real data, highlighting good results in comparison to the state of the art. The benefits of the tracking uncertainty estimates are illustrated for visual motion estimation.

关键词： visualization Uncertainty Tracking Navigation Motion estimation image processing Estimation

来源：评论

学校读者我要写书评

暂无评论

Watershed Segmentation with Gradient Vista and SOBEL-Crafted Contours for Analyzing EMDS-6 Microbial Environmental Dataset

Watershed Segmentation with Gradient Vista and SOBEL-Crafted...

引用

Contemporary Computing and communications (InC4), ieee International conference on

作者： R Mahalakshmi Priya M. Sumathi Madurai Kamaraj University (MKU) Madurai Tamilnadu India PG & Research Dept. of Computer Science Sri Meenakshi Govt. Arts College for Women Madurai Tamilnadu India

ISBN: (数字)9798350383652

ISBN: (纸本)9798350383669

The aim of this research is to present a comprehensive framework for image analysis applied to the EMDS-6 dataset to help identify microorganisms in environmental studies. In order to identify and quantify diverse environmental microorganisms, a reliable methodology is required. Even under the heterogeneous imaging conditions inherent in the EMDS-6 dataset, the proposed methodology proved effective in delineating microorganism boundaries and isolating clustered entities. A framework for image analysis of the EMDS-6 dataset was developed to reliably recognize and quantify a variety of environmental microorganisms. Pre-processing of the images, precision edge detection with SOBEL contours, and advanced segmentation of Graduate Vista Watersheds are among the methods used. Using this combination of techniques, microorganism boundaries can be precisely defined and clustered entities can be isolated across heterogeneous EMDS-6 imaging conditions. According to our methodology, the pipeline classified microorganisms with 93% accuracy, focused edges with 55% Peak Signal-to-Noise Ratio, and segmented objects with 95% Jaccard Index. Compared to baseline approaches, qualitative results indicate considerable improvements in signal localization, feature representation, and region identification. To automate the recognition of species and parsing of complex microbiology images, customized computer vision and stability-driven propagation methods hold great promise. Smart imaging systems will soon be capable of screening environmental samples rapidly, identifying salient organisms, and adapting to detect emerging agents based on this knowledge.

关键词： image segmentation Computer vision Microorganisms PSNR image analysis image edge detection Heuristic algorithms

来源：评论

学校读者我要写书评

暂无评论

Evolutionary Algorithms and Efficient Data Analytics for image processing 15

Evolutionary Algorithms and Efficient Data Analytics for Ima...

引用

15th International conference on Ubiquitous Information Management and Communication (IMCOM)

作者： Mohammadi, Farid Ghareh Shenavarmasouleh, Farzan Amini, M. Hadi Arabnia, Hamid R. Univ Georgia Dept Comp Sci Athens GA 30602 USA Florida Int Univ Sch Comp & Informat Sci Miami FL 33199 USA

ISBN: (纸本)9781665423182

Steganography algorithms facilitate communication between a source and a destination in a secret manner. This is done by embedding messages/text/data into images without impacting the appearance of the resultant images/videos. Steganalysis is the science of determining if an image has secret messages embedded/hidden in it. Because there are numerous steganography algorithms, and since each one of them requires a different type of steganalysis, the steganalysis process is extremely challenging. Thus, researchers aim to develop one universal steganalysis to detect all steganography algorithms. Universal steganalysis extracts a large number of features to distinguish stego images from cover images. However, this leads to the problem of the curse of dimensionality (CoD), which is considered to be an NP-hard problem. Generating a machine learning based model also takes a long time which makes real-time processing appear impossible in any optimization for time-intensive fields such as visual computing. In this study, we investigate previously developed evolutionary algorithms for boosting real-time image processing and argue that they provide the most promising solutions for the CoD problem.

关键词： image steganalysis image classification Feature extraction Feature selection Curse of dimensionality Dimension reduction NP-hard problem Data science

来源：评论

学校读者我要写书评

暂无评论

Attention Based CNN-RNN Hybrid Model for image Captioning

Attention Based CNN-RNN Hybrid Model for Image Captioning

引用

Global conference for Advancement in Technology (GCAT)

作者： Anisha Raphael Abisri S Anitha E Ritika S Manju Venugopalan Department of Electronics and Communication Engineering Amrita School of Engineering Bengaluru Amrita Vishwa Vidyapeetham India Department of Computer Science and Engineering Amrita School of Computing Bengaluru Amrita Vishwa Vidyapeetham India

ISBN: (数字)9798350376685

ISBN: (纸本)9798350376692

image captioning enables computers understand and interpret visual content by bridging the gap between natural language processing and computer vision. The model proposed in this paper for image captioning that employs a hybrid deep learning method and includes an attention mechanism. Combining the strengths of convolutional neural networks (CNNs) for image interpretation and recurrent neural networks (RNNs) for caption generation allows machines to provide more accurate and contextually appropriate descriptions. The CNN+RNN with attention technique improves captioning by dynamically focusing on relevant image regions, and the CNN+RNN encoder-decoder structure serves as a robust foundation for textual descriptions. In contrast, the Vision Transformer (ViT) with GPU acceleration provides greater feature extraction and faster processing, using global context for potentially more accurate and efficient caption production. This work presents a detailed approach to image captioning using a well-chosen dataset from Kaggle. This dataset features images with human-written captions, which helps train the model more effectively. The models experimented were CNN+RNN with attention mechanism, CNN+RNN encoder-decoder and ViT+GPU2. The best results are reported from DenseNet201 which is based on CNN+RNN with attention mechanism achieving an average BLEU score of 0.668 and an average ROUGE-L score of 0.746.

关键词： Computer vision visualization Attention mechanisms Recurrent neural networks Accuracy Graphics processing units Production Transformers Natural language processing Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Urban Change Detection and Analysis of Symbiosis University Nagpur, India Based on Remote Sensing Techniques 3

Urban Change Detection and Analysis of Symbiosis University ...

引用

3rd International conference on Signal processing and Communication (ICPSC)

作者： Gaidhane, Pritesh D. Dorge, Prabhakar D. Balamwar, Sanjay V. Yeshwantrao Chavan Coll Engn Dept Elect & Telecommun Engn Nagpur Maharashtra India Applicat Ctr Dept Maharashtra Remote Sensing Nagpur Maharashtra India

ISBN: (纸本)9781665428644

Remote sensing is basically the method of detection of the physical parameters of a specific area along with that it also monitors the area by measuring the radiation parameters from satellite. The cameras are designed to gather remotely sensed images, which are used to sense things of the earth's surface. Like the cameras on the satellites and the airplanes takes pictures of the different area, allowing us to get every minute detail about it. Now, change detection is the process to identify the changes or differences in various parts of land characteristics at different intervals. This process can be carried by manual observation or by the use of remote sensing software. Because of the rapid urbanization there has been a significant impact on resources and urban environment. But with the use of high quality multi-spatial and multi-temporal remote sensing data, it is quite easy to possibly observe the changes in the urban environment. Therefore, the given study aims to quantify changes in the urban area of Symbiosis University Nagpur, Maharashtra India using Land satellite image. These changes of urbanization are detected by satellite images of Land-Sat MSS in march-2016, march-2018 and may-2020 using a geographic information system (GIS). The change of urbanization in Symbiosis University is for building, road, garden and ground are 17.35%, 20.71%, 1.65% and 0.89% respectively and the total change is 43.51%. From this change we will receive the taxes as per its ongoing construction and it will be easy for government.

关键词： Mobility patterns K-means GIS-image resolution digital image processing remote sensing image classification image thresholding mapping of images etc.

来源：评论

学校读者我要写书评

暂无评论

image Enhancement for High-Resolution visual Contents

Image Enhancement for High-Resolution Visual Contents

引用

International conference on Electronics, Information and communications (ICEIC)

作者： Heunseung Lim Jaehee Lee Hyuncheol Kim Heungmin Oh Joonki Paik The Graduate School of Advanced Imaging Science Multimedia & Film Chung-Ang University Seoul Korea 4by4 Incorporated Pixell Lab Seoul Korea The Graduate School of Artificial Intelligence Seoul Korea

This paper proposes an image enhancement method using gamma neural networks and exponential transformation. When acquiring an image, degradation occurs in very many imaging systems, and the quality of the image acquired by surrounding environmental factors decreases due to the combination of deteriorating elements. Alternatively, work that facilitates post-treatment may be performed by artificially deteriorating for post-treatment directly. However, if the information on these additional tasks is not known, there is a problem that the post-processing process is expensive or additional degradation occurs. To solve this problem, this paper uses a neural network that estimates gamma maps through residual learning for images that require post-processing, and finally applies exponential transformations to perform contrast improvement. The contrast improvement method proposed through the experimental results provides an image with less color distortion compared to the existing method.

关键词： Degradation visualization image color analysis Neural networks Imaging Distortion Environmental factors

来源：评论

学校读者我要写书评

暂无评论

Partial Sampling-based Semantic communications for Internet of Things

Partial Sampling-based Semantic Communications for Internet ...

引用

ieee conference on Vehicular Technology (VTC)

作者： Kaiwen Yu Qi He Gang Wu National Key Laboratory of Wireless Communications University of Electronic Science and Technology of China Chengdu China

ISBN: (数字)9798350387414

ISBN: (纸本)9798350387421

More and more intelligent tasks rely on network edge nodes to collect data, which brings inevitable communication problems such as limited bandwidth and high data volume. As-sisted by deep learning, semantic communication technology is an effective means to improve the efficiency of joint communication and intelligent task execution. However, the commonly used global sampling-based pattern ignores the fact that the data processing ability of edge devices is strictly limited and only a small part of information is available at one time in some applications. This paper proposes a novel partial sampling based semantic communication framework where an edge device is guided by feedback from the receiver to locate and collect only part of the semantic content relevant to the target task at one time. Taking the vision-based task as an example, the transmitter selectively samples a small patch of a large-size image until the intelligent task is successfully executed at the receiver. Simulation results demonstrate that the proposed partial sampling-based framework can locate the informative areas accurately and achieve com-petitive performance compared to existing global sampling-based methods.

关键词： Vehicular and wireless technologies Transmitters Communication systems Simulation image edge detection Semantics Receivers

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 << < 414 415 416 417 418 419 420 421 422 423 > >>

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：