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

13,228 篇 会议
218 篇 期刊文献
176 册 图书
3 篇 学位论文
1 篇 资讯

馆藏范围

13,626 篇 电子文献
1 种 纸本馆藏

日期分布

学科分类号

7,033 篇 工学
- 4,653 篇 计算机科学与技术...
- 2,295 篇 软件工程
- 2,120 篇 电气工程
- 1,334 篇 信息与通信工程
- 867 篇 控制科学与工程
- 689 篇 光学工程
- 503 篇 生物医学工程（可授...
- 470 篇 电子科学与技术（可...
- 469 篇 机械工程
- 462 篇 仪器科学与技术
- 336 篇 生物工程
- 242 篇 测绘科学与技术
- 167 篇 材料科学与工程（可...
- 160 篇 航空宇航科学与技...
- 145 篇 交通运输工程
- 107 篇 安全科学与工程
- 92 篇 化学工程与技术
3,497 篇 理学
- 2,406 篇 物理学
- 932 篇 数学
- 394 篇 生物学
- 249 篇 系统科学
- 240 篇 统计学（可授理学、...
- 122 篇 化学
1,508 篇 医学
- 1,336 篇 临床医学
- 210 篇 特种医学
- 171 篇 基础医学(可授医学...
- 111 篇 药学(可授医学、理...
725 篇 管理学
- 438 篇 管理科学与工程(可...
- 311 篇 图书情报与档案管...
- 89 篇 工商管理
62 篇 法学
61 篇 农学
30 篇 教育学
29 篇 经济学
29 篇 文学
20 篇 军事学
18 篇 艺术学
1 篇 哲学

主题

2,760 篇 image processing
1,431 篇 image segmentati...
1,168 篇 signal processin...
618 篇 feature extracti...
616 篇 cameras
587 篇 image edge detec...
567 篇 signal processin...
489 篇 image coding
489 篇 image reconstruc...
470 篇 real-time system...
399 篇 algorithm design...
352 篇 image color anal...
312 篇 image enhancemen...
311 篇 pixel
310 篇 deep learning
307 篇 real time system...
302 篇 image analysis
301 篇 computer archite...
299 篇 hardware
296 篇 object detection

机构

22 篇 signal and image...
20 篇 samara national ...
14 篇 school of electr...
11 篇 samara national ...
11 篇 purdue univ sch ...
11 篇 univ texas san a...
11 篇 department of el...
11 篇 school of electr...
10 篇 samara national ...
10 篇 center for signa...
9 篇 information syst...
9 篇 institute of ima...
9 篇 university of to...
9 篇 tongji universit...
8 篇 university of ch...
8 篇 electrical compu...
8 篇 image processing...
8 篇 information syst...
7 篇 school of electr...
7 篇 department of ma...

作者

19 篇 anon
13 篇 de-shuang huang
13 篇 jagdish chand ba...
11 篇 p. pirsch
10 篇 jie yang
10 篇 panetta karen
10 篇 j.m. mendel
10 篇 r. chellappa
9 篇 c.-c.j. kuo
8 篇 frank hannig
8 篇 hannig frank
8 篇 ilias maglogiann...
8 篇 egiazarian karen
7 篇 miller jwv
7 篇 busch christoph
7 篇 semenishchev e.
7 篇 zelensky a.
7 篇 bovik alan c.
7 篇 jerry m. mendel
7 篇 kupriyanov a.v.

语言

13,395 篇 英文
140 篇 其他
78 篇 中文
20 篇 土耳其文
3 篇 西班牙文
3 篇 葡萄牙文
2 篇 俄文
1 篇 法文

检索条件"任意字段=Conference on Image Processing - Algorithms and Systems IV"

共 13626 条记录，以下是291-300 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：

Why are Visually-Grounded Language Models Bad at image Classification? 38

Why are Visually-Grounded Language Models Bad at Image Class...

引用

38th conference on Neural Information processing systems, NeurIPS 2024

作者： Zhang, Yuhui Unell, Alyssa Wang, Xiaohan Ghosh, Dhruba Su, Yuchang Schmidt, Ludwig Yeung-Levy, Serena Stanford University United States University of Washington United States Tsinghua University China

image classification is one of the most fundamental capabilities of machine vision intelligence. In this work, we revisit the image classification task using visually-grounded language models (VLMs) such as GPT-4V and LLaVA. We find that existing proprietary and public VLMs, despite often using CLIP as a vision encoder and having many more parameters, significantly underperform CLIP on standard image classification benchmarks like imageNet. To understand the reason, we explore several hypotheses concerning the inference algorithms, training objectives, and data processing in VLMs. Our analysis reveals that the primary cause is data-related: critical information for image classification is encoded in the VLM's latent space but can only be effectively decoded with enough training data. Specifically, there is a strong correlation between the frequency of class exposure during VLM training and instruction-tuning and the VLM's performance in those classes;when trained with sufficient data, VLMs can match the accuracy of state-of-the-art classification models. Based on these findings, we enhance a VLM by integrating classification-focused datasets into its training, and demonstrate that the enhanced classification performance of the VLM transfers to its general capabilities, resulting in an improvement of 11.8% on the newly collected imageWikiQA dataset. © 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

Building Safe and Reliable AI systems for Safety Critical Tasks with Vision-Language processing 45th

Building Safe and Reliable AI Systems for Safety Critical Ta...

引用

45th European conference on Information Retrieval (ECIR)

作者： Ao, Shuang Open Univ Walton Hall Milton Keynes MK7 6AA Bucks England

ISBN: (纸本)9783031282409;9783031282416

Although AI systems have been applied in various fields and achieved impressive performance, their safety and reliability are still a big concern. This is especially important for safety-critical tasks. One shared characteristic of these critical tasks is their risk sensitivity, where small mistakes can cause big consequences and even endanger life. There are several factors that could be guidelines for the successful deployment of AI systems in sensitive tasks: (i) failure detection and out-ofdistribution (OOD) detection;(ii) overfitting identification;(iii) uncertainty quantification for predictions;(iv) robustness to data perturbations. These factors are also challenges of current AI systems, which are major blocks for building safe and reliable AI. Specifically, the current AI algorithms are unable to identify common causes for failure detection. Furthermore, additional techniques are required to quantify the quality of predictions. All these contribute to inaccurate uncertainty quantification, which lowers trust in predictions. Hence obtaining accurate model uncertainty quantification and its further improvement are challenging. To address these issues, many techniques have been proposed, such as regularization methods and learning strategies. As vision and language are the most typical data type and have many open source benchmark datasets, this thesis will focus on vision-language data processing for tasks like classification, image captioning, and vision question answering. In this thesis, we aim to build a safeguard by further developing current techniques to ensure the accurate model uncertainty for safety-critical tasks.

关键词： Deep learning Model calibration Uncertainty

来源：评论

学校读者我要写书评

暂无评论

A Study on multi-scale landscape character extraction combining GIS and graphic processing algorithms 3

A Study on multi-scale landscape character extraction combin...

引用

3rd International conference on Environmental Remote Sensing and Geographic Information Technology, ERSGIT 2024

作者： Wang, Shuwei Liu, Yang Li, Guangqi Su, Xueying Wang, Sen Bai, Xuyong Center for Geophysical Survey China Geological Survey Langfang China Technology Innovation Center for Earth Near Surface Detection China Geological Survey China

ISBN: (纸本)9781510690219

This research presents an innovative approach to accurately extract multi-scale landscape characters by combining geographic information systems (GIS) and graphic processing algorithms. It is essential to recognize and analyze landscape characters at different scales. This study uses GIS advantages in spatial analysis and the K-Means clustering algorithm in image enhancement, feature extraction, image segmentation, and color quantification. Through image interpretation and deep learning, the distribution characteristics of buildings in Langfang City are obtained to provide guidance and suggestions for the future construction and development of the city. The proposed method covers data preparation, algorithm design, and system implementation. In addition, the future research direction of improving the method is also discussed, and the possibility of its application in other fields is explored. © 2025 SPIE.

关键词： Photointerpretation

来源：评论

学校读者我要写书评

暂无评论

FedDHr: Improved Adaptive Learning Strategy Using Federated Learning for image processing

FedDHr: Improved Adaptive Learning Strategy Using Federated ...

引用

2023 International conference on Self Sustainable Artificial Intelligence systems, ICSSAS 2023

作者： Velagapudi, Anuhya Jhansi, B. Hemalikha, M. Vijayalakshmi, P. Koneru Lakshmaiah Education Foundation Department of Artificial Intelligence and Data Science Andhra Pradesh Vaddeswaram India

ISBN: (纸本)9798350300857

FL (Federated learning) has grown in popularity as a field of research that allows for the training of an algorithm over many decentralised servers that are having local data samples without requiring data exchange. Numerous application domains (like medical image analysis diagnosis made by doctors) lack a significant amount of properly labeled and full data that can be found in one place. Due to the prevalence of artificial intelligence in new application sectors, there are few rising issues on privacy of data and user. New algorithms of various research works are analysed in this study and it introduces a new technique that address the data heterogeneity and adaptive learning rate of the model to perform image processing, Deep Learning. © 2023 IEEE.

关键词： Electronic data interchange

来源：评论

学校读者我要写书评

暂无评论

Clinical Breast Imaging and Deep Learning Model For image Malignancy Prediction Using Resource-Constrained Embedded Devices 4

Clinical Breast Imaging and Deep Learning Model For Image Ma...

引用

4th International conference on Artificial Intelligence and Signal processing

作者： Chokhandre, Sumedha R. Jadhav, Ms Pranjali Gole, Nilesh Thakare, Amit N. Bondade, Akansha R. Singh, Priyanka YCCE Dept Informat Technol Nagpur Maharashtra India Vishwakarma Inst Informat Technol AI & DS Dept Pune Maharashtra India Vidharbha Inst Technol Dept CSE Nagpur Maharashtra India Cummins Coll Engn Women Nagpur Maharashtra India G H Raisoni Univ Dept CSE Saikheda India VIT AP Univ Sch Comp Sci Amaravati Andhra Pradesh India

ISBN: (纸本)9798350350661;9798350350654

Computer assisted diagnosis(CAD) of diseases provides more accurate and precise diagnostic reports towards better information regarding the medical condition of patients. A clinician can minimize the error by applying his experience acquired by practice, cognitive intuition or scientific research backed by laboratory reports and computer assisted medical image analysis. The findings by the experts based on the analysis of such data are crucial as the suggested treatment is dependent on evaluation at this stage. Machine learning techniques while applied in the medical field performs decision making by mimicking the steps performed by a medical expert in diagnosing the disease, but using algorithms rather intuitive. It brings out accurate medical data through analysis of images performed by computing devices that can reveal valuable information regarding the disease prognosis. Computer aided disease diagnosis with state-of-the-art machine learning and deep learning offers seamless assistance in medical care with near human accuracy. Technology integrated medical support systems combined with sophisticated algorithms can reduce the number of false positive incidents as well as false negative cases. Convolutional neural network (CNN) models can be trained using handcrafted features to derive conclusive inferences for binary class as well as multi-class classification. Artificial Intelligence (AI) supported techniques in disease diagnosis provide assistance to medical experts in decision making by virtue of cloud based data analytics tools for storage and computing.

关键词： Computer assisted diagnosis(CAD) Convolutional neural network (CNN) Artificial Intelligence (AI) cloud based data analytics

来源：评论

学校读者我要写书评

暂无评论

A Comparative Analysis of image Partitioning and Compression Mechanisms 15

A Comparative Analysis of Image Partitioning and Compression...

引用

15th International conference on Advances in Computing, Control, and Telecommunication Technologies, ACT 2024

作者： Chaudhari, Sampada P. Thakur, Nileshsingh V. Dept. of Computer Science and Engineering Prof Ram Meghe College of Engineering & Management Badnera India Dept. of Computer Science and Engineering Yeshwantrao Chavan College of Engineering Nagpur India

ISBN: (纸本)9798331300579

This paper presents a comprehensive comparative analysis of image partitioning and compression mechanisms, two fundamental techniques in image processing and data compression. image partitioning involves dividing an image into smaller components, while compression aims to reduce the size of digital images while preserving visual quality. The analysis encompasses various aspects of both techniques, including methodologies, algorithms, and performance metrics. For image partitioning, segmentation methods such as block-based, region-based, and hierarchical partitioning are examined, along with their respective advantages and limitations. Additionally, the paper explores compression mechanisms such as transform coding, quantization, entropy coding, and predictive coding, highlighting their roles in achieving efficient compression. Furthermore, the comparative analysis evaluates the tradeoffs between different partitioning and compression techniques in terms of compression ratio, image quality, computational complexity, and applicability across different types of images and applications. Various compression standards such as JPEG and PNG are also reviewed to provide insights into real-world implementations. Finally, the paper discusses future research directions and emerging trends in image partitioning and compression, including the integration of machine learning techniques for improved segmentation and compression performance. The findings presented in this comparative analysis can serve as a valuable resource for researchers, practitioners, and developers working in the fields of image processing, data compression, and multimedia systems. © Grenze Scientific Society, 2024.

关键词： image compression

来源：评论

学校读者我要写书评

暂无评论

How to combine issues related to autonomous vehicles - a proposal with a literature review 26

How to combine issues related to autonomous vehicles - a pro...

引用

26th IEEE Signal processing: algorithms, Architectures, Arrangements, and Applications, SPA 2023

作者： Balcerek, Julian Pawlowski, Pawel Poznan University of Technology Division of Signal Processing and Electronic Systems Institute of Automatic Control and Robotics Poznan Poland

ISBN: (纸本)9798350304985

This article proposes a model that combines the issues related to autonomous vehicles into seven groups. The groups are included in mutual iterations between the user, the autonomous vehicle and the environment. They are: vehicle automation, environmental sensors, automatic perception of the environment based on the processing of vision signals, communication with external devices, interaction with the user, direct transmission of signals to the environment, and future development plans. Bearing in mind the proposed model, various latest solutions presented in the state-of-the-art literature or already offered in vehicles are collected and described. © 2023 Division of Signal processing and Electronic systems, Poznan University of Technology (DSPES PUT).

关键词： image processing

来源：评论

学校读者我要写书评

暂无评论

Application of image Security Transmission Encryption Algorithm Based on Chaos Algorithm in Networking systems of Artificial Intelligence 5

Application of Image Security Transmission Encryption Algori...

引用

5th Asia-Pacific conference on image processing, Electronics and Computers, IPEC 2024

作者： Tian, Hongmei Yuan, Zhijie Zhou, Jiao He, Rui Xi’an University of Technology Xi'an710054 China China Coal Technology & Engineering Group Xian Research Institute Xi'an710076 China

ISBN: (纸本)9781643685243

This study focuses on enhancing the security of image transmission in Networking systems of Artificial Intelligence (NSAI) by implementing an advanced encryption algorithm (AEA) based on chaotic algorithms. The research begins by exploring the fundamental concepts, structures, and practical applications of NSAI. It then introduces the development of the AEA, specifically designed to safeguard image data during transmission. The methodology involves integrating a chaotic algorithm into the encryption and decryption processes, thereby improving the confidentiality and integrity of the images. Additionally, an encryption protocol consistent with NSAI specifications is developed to further enhance the security of transmitted images. Through simulations, the AEA demonstrates exceptional performance, with minimal errors, high accuracy, and outstanding efficiency in encryption tasks. Overall, this study concludes that the AEA represents a significant advancement in securing image transmission within NSAI, providing robust protection for future applications. © 2024 The Authors.

关键词： Artificial intelligence

来源：评论

学校读者我要写书评

暂无评论

On image processing and Pattern Recognition for Thermograms of Watermarks in Manuscripts - A First Proof-of-Concept 18th

On Image Processing and Pattern Recognition for Thermograms ...

引用

18th International conference on Document Analysis and Recognition (ICDAR)

作者： Hauser, Dominik Beckmann, Matthias Koliander, Gunther Stiehl, H. Siegfried Univ Hamburg Dept Informat Hamburg Germany Univ Bremen Ctr Ind Math Bremen Germany Imperial Coll London Dept Elect & Elect Engn London England Austrian Acad Sci Acoust Res Inst Viennna Austria

ISBN: (纸本)9783031705427;9783031705434

Watermarks in historical manuscripts are figural shapes serving as tokens for provenance research (e.g. scribe identification, dating, papermill attribution, scribe-papermaker relation, trading, etc.) in Humanities such as Musicology. As of today, they come in a variety of formats: digitized handtracings and rubbings, X-ray based imagery and, more recently, thermograms acquired with infrared (IR) cameras - all of which have been made accessible via image data bases in libraries or archives like the watermark information system (WZIS). A key use case from a scholar's perspective is the search for similar or even equal watermarks in whatever digitized data collections. Non-surprisingly, the prerequisite is the availability of a versatile, reliable, and user-friendly tool comprising methods from digital image processing (IP) and pattern recognition (PR). In our paper, we focus on bridging the gap between digitized thermograms of music manuscripts and watermark classification for similarity-based search through (i) a state-of-the-art (SOTA) analysis, (ii) a resulting conceptual design based on well-understood SOTA as well as novel methods, (iii) an easy-to-use implementation, and (iv) an experimental validation as Proof-of-Concept (PoC). The current system performance is characterized using thermograms recently made openly available within the DRACMarkS project as well as WZIS. The experimental results clearly demonstrate success in bridging the existing gap hence also setting a baseline for an as yet lacking benchmark.

关键词： Historical Document Analysis image processing Document Analysis systems

来源：评论

学校读者我要写书评

暂无评论

Intelligent algorithms of digital processing of biomedical images in wavelet methods

Intelligent algorithms of digital processing of biomedical i...

引用

International conference on Artificial Intelligence, Blockchain, Computing and Security, ICABCS 2023

作者： Zaynidinov, H. Xuramov, L. Khodjaeva, D. Tashkent University of Information Technologies named after Muhammad al-Khwarizmi Uzbekistan Samarkand State University Samarkand Uzbekistan

ISBN: (纸本)9781032669663

To date, the use of computer vision in biomedicine with the use of artificial intelligent systems, which in turn receive information from images, and then give out new knowledge and final conclusions about the disease is the most relevant. images are obtained from different video sensors using them in different frequency ranges, which can be represented using two-dimensional brightness matrices and two-dimensional sensors. You can improve the image quality in several steps: preprocessing, highlighting the characteristic properties of the image (filtering, brightness equalization) classification and conclusion. © 2024, CRC Press/Balkema. All rights reserved.

关键词： Luminance

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 << < 26 27 28 29 30 31 32 33 34 35 > >>

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：