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

149 篇 会议
1 篇 期刊文献

馆藏范围

150 篇 电子文献
0 种 纸本馆藏

日期分布

学科分类号

110 篇 工学
- 99 篇 计算机科学与技术...
- 33 篇 软件工程
- 15 篇 电气工程
- 14 篇 控制科学与工程
- 10 篇 光学工程
- 9 篇 信息与通信工程
- 8 篇 机械工程
- 8 篇 电子科学与技术（可...
- 7 篇 交通运输工程
- 6 篇 生物工程
- 5 篇 安全科学与工程
- 4 篇 动力工程及工程热...
- 4 篇 环境科学与工程（可...
- 3 篇 冶金工程
- 3 篇 土木工程
- 3 篇 化学工程与技术
- 3 篇 石油与天然气工程
- 3 篇 生物医学工程（可授...
74 篇 理学
- 60 篇 物理学
- 10 篇 数学
- 6 篇 生物学
- 5 篇 系统科学
- 4 篇 统计学（可授理学、...
- 3 篇 化学
14 篇 管理学
- 11 篇 管理科学与工程(可...
- 4 篇 工商管理
- 4 篇 图书情报与档案管...
- 2 篇 公共管理
7 篇 医学
- 5 篇 临床医学
- 2 篇 公共卫生与预防医...
1 篇 经济学
1 篇 法学
1 篇 农学
1 篇 军事学

主题

34 篇 machine vision
21 篇 computer vision
13 篇 deep learning
10 篇 image processing
8 篇 inspection
7 篇 cameras
7 篇 real-time system...
6 篇 convolutional ne...
5 篇 internet of thin...
5 篇 object detection
5 篇 application soft...
5 篇 artificial intel...
4 篇 computational mo...
4 篇 feature extracti...
4 篇 hardware
4 篇 accuracy
4 篇 prolog
3 篇 scalability
3 篇 quantum computin...
3 篇 interactive imag...

机构

2 篇 univ. of michiga...
2 篇 univ wales coll ...
2 篇 univ. of wales c...
1 篇 tashkent univers...
1 篇 acuity imaging i...
1 篇 gitam university...
1 篇 department of co...
1 篇 royal mil acad a...
1 篇 transtec plc bir...
1 篇 vision systems l...
1 篇 st. martin's eng...
1 篇 rise sics väster...
1 篇 state key labora...
1 篇 vision systems l...
1 篇 casablanca moroc...
1 篇 mizoram aizawl
1 篇 centro singular ...
1 篇 instituto federa...
1 篇 department of co...
1 篇 univ calgary dep...

作者

6 篇 whelan pf
5 篇 batchelor bg
4 篇 hack r
3 篇 jones ac
2 篇 miller jwv
2 篇 mccorkell c
2 篇 batchelor b
2 篇 walker jn
2 篇 á. rodríguez-váz...
2 篇 regueiro carlos ...
2 篇 r. carmona-galán
2 篇 roberts jw
2 篇 j. fernández-ber...
2 篇 wang xj
1 篇 hajar bnouachir
1 篇 saeed aaqib
1 篇 kea-tiong tang
1 篇 james anne
1 篇 basterrech sebas...
1 篇 mohanavel v.

语言

139 篇 英文
11 篇 其他

检索条件"任意字段=Conference on Machine Vision Applications, Architectures, and Systems Integration V"

共 150 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：

Learning to Adapt CLIP for Few-Shot Monocular Depth Estimation

Learning to Adapt CLIP for Few-Shot Monocular Depth Estimati...

引用

IEEE/CvF Winter conference on applications of Computer vision (WACv)

作者： Hu, Xueting Zhang, Ce Zhang, Yi Hai, Bowen Yu, Ke He, Zhihai Southern Univ Sci & Technol Dept Elect & Elect Engn Shenzhen Peoples R China Pengcheng Lab Shenzhen Peoples R China Southern Univ Sci & Technol Ctr Computat Sci & Engn Shenzhen Peoples R China

ISBN: (纸本)9798350318920;9798350318937

Pre-trained vision-Language Models (vLMs), such as CLIP, have shown enhanced performance across a range of tasks that involve the integration of visual and linguistic modalities. When CLIP is used for depth estimation tasks, the patches, divided from the input images, can be combined with a series of semantic descriptions of the depth information to obtain similarity results. The coarse estimation of depth is then achieved by weighting and summing the depth values, called depth bins, corresponding to the pre-defined semantic descriptions. The zero-shot approach circumvents the computational and time-intensive nature of traditional fully-supervised depth estimation methods. However, this method, utilizing fixed depth bins, may not effectively generalize as images from different scenes may exhibit distinct depth distributions. To address this challenge, we propose a few-shot-based method which learns to adapt the vLMs for monocular depth estimation to balance training costs and generalization capabilities. Specifically, it assigns different depth bins for different scenes, which can be selected by the model during inference. Additionally, we incorporate learnable prompts to preprocess the input text to convert the easily human-understood text into easily model-understood vectors and further enhance the performance. With only one image per scene for training, our extensive experiment results on the NYU v2 and KITTI dataset demonstrate that our method outperforms the previous state-of-the-art method by up to 10.6% in terms of MARE(1).

关键词： Algorithms Algorithms Algorithms and algorithms formulations Image recognition and understanding machine learning architectures vision + language and/or other modalities

来源：评论

学校读者我要写书评

暂无评论

Emerging applications and Challenges in Quantum Computing: A Literature Survey 7

Emerging Applications and Challenges in Quantum Computing: A...

引用

7th International conference on Artificial Intelligence, Big Data, Computing and Data Communication systems (ICABCD)

作者： Garewal, Ishmeen Kaur Mahamuni, Chaitanya v. Jha, Shruti Fr C Rodrigues Inst Technol Dept Comp Engn Navi Mumbai India

ISBN: (纸本)9798350387919;9798350387902

Quantum computing is at the cutting edge of technological innovation, with the potential to transform a wide array of scientific and practical fields. This literature survey addresses the critical need for a structured understanding of recent advancements and identifies research gaps. It comprehensively reviews recent advancements in quantum computing, emphasizing non-standard architectures, applications in material sciences, and the integration of quantum and classical machine learning models. The survey also examines quantum algorithms for real-time systems, explores cryptographic protocols beyond Shor's algorithm, and discusses resource management in cloud computing. Key findings highlight significant progress in algorithm efficiency, practical applications in 2D materials and topological insulators, and the hybridization of quantum and classical models. Challenges such as scalability, resource optimization, and ethical concerns still remain. This paper guides future research to focus on optimizing algorithms, efficient resource allocation, and enhancing security measures. This work synthesizes current knowledge, guiding future research efforts and contributing to the advancement of the quantum computing research community.

关键词： Quantum computing Emerging Technologies Hybrid machine learning Quantum cryptography and cloud resource management Environmental monitoring

来源：评论

学校读者我要写书评

暂无评论

Human Activity Recognition a Comparison Between Residual Neural Network and Recurrent Neural Network 1

引用

International conference on Artificial Intelligence: Theory and applications (AITA)

作者： Anu, K. P. Benifa, J. v. Bibal Indian Inst Informat Technol Kottayam Kerala India

ISBN: (数字)9789819984794

ISBN: (纸本)9789819984787;9789819984794

Recognizing human activity is important for interpersonal interactions and human-to-human communication. It is challenging to extract since it contains details about a person's identity, personality, and psychological condition. One of the key research topics in the fields of computer vision and machine learning is the human capacity for activity recognition. This study has led to the need for a multimodal activity identification system in several applications, such as video surveillance systems, human-computer interaction, and robots for characterizing human behavior. In this study, Residual Neural Network (ResNet50) and Recurrent Neural Network (RNN) architectures for human activity recognition (HAR) are compared. Our assessment is based on a number of performance metrics, such as accuracy F1-score, recall, and computational effectiveness. Here we have the model accuracy of ResNet50 at 53% and RNN at 23% with epoch 10. Our objective is to evaluate how well the models can categorize various human activities. The outcomes demonstrate that ResNet50 outperformed RNN.

关键词： Computer vision HAR CNN ResNet50 RNN

来源：评论

学校读者我要写书评

暂无评论

machine learning algorithms are used to detect and track objects on video images 3

Machine learning algorithms are used to detect and track obj...

引用

3rd International conference on Optics, Computer applications, and Materials Science, CMSD 2023

作者： Beknazarova, S.S. Latipova, N.M. Maxmudova, M.J. Alekseeva, v.S. Turakulova, A.S. Tashkent University of Information Technologies Named by Muhammad Al-Khwarizmi 108 A. Timur Tashkent 100096 Uzbekistan National University of Uzbekistan Named after Mirzo Ulugbek Tashkent Uzbekistan

ISBN: (纸本)9781510674486

In recent years, the integration of machine learning algorithms has significantly advanced the field of computer vision, particularly in the domain of object detection and tracking in video images. This article explores the application of machine learning techniques to enhance the accuracy and efficiency of object detection and tracking systems. The article begins by providing an overview of the challenges associated with traditional methods of object detection and tracking, highlighting the limitations in handling complex scenarios and diverse object types. Subsequently, it delves into the methodology of employing machine learning algorithms, emphasizing their adaptability and capability to discern patterns and features crucial for accurate object recognition. various machine learning models, such as convolutional neural networks (CNNs) and recurrent neural networks (RNNs), are discussed in detail, elucidating their roles in extracting meaningful representations from video frames. The training process is explored, encompassing the use of labeled datasets to enable the algorithms to generalize and make informed predictions in real-world scenarios. Furthermore, the article investigates the integration of deep learning techniques, exploring the advantages of transfer learning and fine-Tuning pre-Trained models to optimize performance. The role of neural networks in handling object occlusion, scale variations, and pose changes is emphasized, showcasing the adaptability of machine learning algorithms to dynamic and unpredictable environments. The practical implementation of these algorithms in object detection and tracking systems is presented, highlighting real-world applications across industries such as surveillance, autonomous vehicles, and industrial automation. The article concludes by discussing ongoing research and potential future developments, addressing the evolving landscape of machine learning in computer vision and its implications for advancing object det

关键词： Feature extraction

来源：评论

学校读者我要写书评

暂无评论

A Robotic Manipulator with Conveyor System for visual Sorting of Work Pieces

A Robotic Manipulator with Conveyor System for Visual Sortin...

引用

2024 International conference on E-Mobility, Power Control and Smart systems, ICEMPS 2024

作者： Adarsh, v.S. Mathew, Jedin Jebi Thuruthiyil, Joseph Mathew Sunil, Sidharth Joseph, Georgina Binoy Toc H Institute of Science and Technology Robotics and Automation Kerala Ernakulum India

ISBN: (纸本)9798350394399

The proposed system for sorting work pieces integrates a four-degree-of-freedom robotic manipulator with computer vision and conveyor transportation capabilities for automated object handling and sorting. Utilizing a conveyor system and inverse kinematics, the robotic arm ensures efficient movements. Real-time images of work pieces are captured and processed using computer vision techniques, allowing for size and color-based sorting. The integration of machine learning with robotic control can ensure dynamic and accurate sorting. The integrated system reduces labor costs, minimizes errors, and finds applications in manufacturing, logistics, and assembly lines improving productivity and product quality. © 2024 IEEE.

关键词： Inverse kinematics

来源：评论

学校读者我要写书评

暂无评论

A Critical Study on Hybrid Computing and Its Current Influences and Future Challenges 3

A Critical Study on Hybrid Computing and Its Current Influen...

引用

3rd International conference on Intelligent and Innovative Technologies in Computing, Electrical and Electronics, IITCEE 2025

作者： Praveen, K.v. Joe Prathap, P.M. Beevi, L. Sherin Dani, W. vinil St. Peter's College of Engg. and Tech. Department of Information Technology Chennai India R.M.D. Engineering College Department of Computer Science and Engineering Kavaraipettai India St. Peter's College of Engg. and Tech. Department of Eee Chennai India

ISBN: (纸本)9798331515911

This research focuses on the evolving field of hybrid computing, which combines traditional computing architectures with advanced computational paradigms like quantum computing, neuromorphic computing, or cloud-edge computing. Hybrid computing involves integrating multiple computing models or systems to leverage their complementary strengths. For example, combining classical computing with quantum or neuromorphic approaches to solve complex problems more efficiently. The goal is to enhance computational power, increase efficiency, and tackle problems that are difficult for traditional computing models alone. Emerging technologies, including quantum computing, machine learning, and AI, are driving the need for hybrid systems. These technologies enable the handling of more complex computations that classical systems struggle with, such as optimization, simulation, and cryptography. The integration of cloud and edge computing is also central to hybrid computing, enabling decentralized computation and processing closer to data sources. Combining different computing paradigms requires seamless communication and integration between systems, which is a significant technical challenge. Main challenging areas are scalability, software and hardware compatibility, energy efficiency and security. There is a need for standard protocols and frameworks to enable smoother integration of various computing systems. New algorithms that can take advantage of hybrid architectures need to be developed. Depend on applications significant advancements in hardware, including quantum processors, neuromorphic chips, and integrated hybrid processors required. The rise of hybrid computing will also bring ethical concerns, such as the impact on jobs, privacy, and inequality in access to advanced technologies. The study concludes by emphasizing the transformative potential of hybrid computing while acknowledging the technical, economic, and societal hurdles that need to be overcome. It highlights

关键词： Quantum computers

来源：评论

学校读者我要写书评

暂无评论

Back to the Future: Models as Active Learning Surrogates for Next Generation ML Deployments

Back to the Future: Models as Active Learning Surrogates for...

引用

Intelligent systems conference

作者： Frickenstein, Lukas Thoma, Moritz Mori, Pierpaolo Sampath, Shambhavi Balamuthu Fasfous, Nael vemparala, Manoj-Rohit Frickenstein, Alexander Unger, Christian Passerone, Claudio Stechele, Walter BMW Autonomous Driving Unterschleissheim Germany Tech Univ Munich Munich Germany Politecn Torino Turin Italy

ISBN: (纸本)9783031663284;9783031663291

Rapid development of hardware goes hand-in-hand with the advancement of modern computer vision (Cv) algorithms. In a typical machine learning operations (MLOps) flow, this continuous evolution of hardware and software is coupled with an active growth in data collected for training. These three pillars of MLOps continue their parallel continuous integration and improvement after an iteration of the deployment has been released. Ideally, the data chosen to improve the next iteration of the deployment is tailored for the future software solution and the future hardware capabilities which enable it. However, here we have a causality problem, where data needs to be collected for a future algorithm from a fleet of deployments which are still running the last iteration of software and hardware. In this paper, we prove that models of previous MLOps iterations are capable surrogates for choosing data for future network architectures running on more capable hardware. We show that surrogate models for the DeepLabv3+ architecture using a ResNet-50 backbone provide a +3.2 p.p. mIoU improvement on average using uncertainty scores over randomly selecting data to train the deployment model on the CityScapes dataset. Further, we show that the type of surrogate has a huge impact on the prediction capability of the deployment model. For instance, the prediction capability of a deployment model, DeepLabv3+, using a MobileNetv3 backbone, can vary by up to +2.4 p.p. on the CityScapes dataset.

关键词： Active learning machine learning operations Computer vision

来源：评论

学校读者我要写书评

暂无评论

Artificial Intelligence in Drone and Anti-drone systems: Cutting-Edge Advances and applications 1st

Artificial Intelligence in Drone and Anti-drone Systems: Cut...

引用

1st International conference on Electrical systems and Smart Technologies, ICESST 2024

作者： Ghazlane, Yasmine Hajar, Bnouachir Hajar, El Maghraoui Saida, Haidrar Mourad, El Yadari Casablanca Morocco ENSAM Mohammed V University Rabat Rabat Morocco

ISBN: (纸本)9783031867040

With the increasing proliferation of drones, or Unmanned Aerial vehicles (UAvs), across various sectors, both opportunities and challenges arise, particularly concerning security and privacy. The misuse of drones for malicious activities has necessitated the development of advanced anti-drone systems to detect, identify, and neutralize these threats effectively. This article discusses the critical aspects of Artificial Intelligence (AI) in enhancing anti-drone systems, highlighting recent advances in AI applications for both drones and anti-drone technologies. The integration of AI techniques such as machine learning deep learning, computer vision, and multi-agent systems has significantly improved the detection, identification, tracking, and interception capabilities of anti-drone systems. This work provides an overview of the state-of-the-art AI technologies driving the evolution of both drones and counter-drone measures. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2025.

关键词： Deep learning

来源：评论

学校读者我要写书评

暂无评论

Crop Yield Prediction Using Deep Learning 5th

Crop Yield Prediction Using Deep Learning

引用

5th International conference on Data Science, machine Learning and applications

作者： Jeny, J. R. v. Divya, Phulari varsha, Kolanu Mrunalini, Anantha Irfan, S. K. M. Vignan Inst Technol & Sci Dept Comp Sci & Engn AI&ML Yadadri Bhuvanagiri India

ISBN: (纸本)9789819780334;9789819780310;9789819780303

In contemporary agriculture, the accurate prediction of crop yields remains a substantial challenge for farmers. Existing prediction systems are often rigid and tailored to specific crops and regions, leaving many farmers without critical information to make informed decisions in the face of unpredictable weather and environmental variations. Our core mission is to develop advanced models that can accurately forecast crop yields, enabling farmers to make well-informed choices each growing season. By considering factors like soil composition, fertility, weather fluctuations, and seasonal variations, we employ cutting-edge machine learning techniques, including some DL algorithms and architectures that handle sequential data effectively. Our data collection process encompasses a wide array of sources, including weather data, soil quality assessments, and specific crop details. To ensure consistency, we rigorously standardize this data. We further divide our dataset into subsets for assessing models' accuracy using some metrics. Our overarching goal is to bridge the gap in precise crop yield prediction, providing farmers with a practical tool to make informed decisions about crop selection in an ever-changing agricultural landscape. Through the use of advanced deep learning techniques and data integration from diverse sources, we strive to meet the evolving demands of agriculture in today's dynamic world.

关键词： Yield Prediction Deep Learning 1D-CNN LSTM GRU

来源：评论

学校读者我要写书评

暂无评论

Investigation of the effectiveness of the architecture of convolutional neural networks on satellite images 3

Investigation of the effectiveness of the architecture of co...

引用

3rd International conference on Optics, Computer applications, and Materials Science, CMSD 2023

作者： Dovgal, vladislav v. Gura, Dmitry A. Dyachenko, Roman A. Kuban State Technological University Moskovskaya Str Krasnodar350072 Russia Kuban State Agrarian University 13 Kalinina Str Krasnodar350044 Russia

ISBN: (纸本)9781510674486

To date, the problem of automating work with images taken using satellite systems has become relevant. This task concerns a wide range of human activities, including urban planning, transport logistics, ecology and environmental monitoring, etc. To solve these problems, there are many tools, of which solutions based on the use of machine learning algorithms are particularly effective. The complexity of this approach lies in the wide variety of computer vision models that exist today. The purpose of this research is to select the most popular neural network architectures and conduct a study that aims to identify the most effective architecture in terms of efficiency and quality of work performed. This study will help determine the machine learning model that is most suitable for further use in a software product aimed at working with satellite images, the main functions of which will be object detection and segmentation. © 2024 SPIE. All rights reserved.

关键词： Image segmentation

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15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：