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

3,635 篇 会议
251 册 图书
56 篇 期刊文献

馆藏范围

3,941 篇 电子文献
2 种 纸本馆藏

日期分布

学科分类号

2,872 篇 工学
- 2,240 篇 计算机科学与技术...
- 1,308 篇 软件工程
- 478 篇 信息与通信工程
- 463 篇 光学工程
- 307 篇 控制科学与工程
- 292 篇 电气工程
- 229 篇 生物工程
- 156 篇 机械工程
- 143 篇 生物医学工程（可授...
- 98 篇 电子科学与技术（可...
- 88 篇 仪器科学与技术
- 69 篇 化学工程与技术
- 67 篇 安全科学与工程
- 59 篇 交通运输工程
- 53 篇 土木工程
- 50 篇 建筑学
- 49 篇 材料科学与工程（可...
1,095 篇 理学
- 559 篇 数学
- 511 篇 物理学
- 241 篇 生物学
- 157 篇 统计学（可授理学、...
- 82 篇 化学
- 68 篇 系统科学
420 篇 医学
- 405 篇 临床医学
- 64 篇 基础医学(可授医学...
- 48 篇 药学(可授医学、理...
354 篇 管理学
- 201 篇 管理科学与工程(可...
- 154 篇 图书情报与档案管...
- 83 篇 工商管理
57 篇 法学
- 53 篇 社会学
43 篇 教育学
31 篇 经济学
31 篇 农学
28 篇 艺术学
9 篇 军事学
2 篇 文学

主题

450 篇 computer vision
174 篇 artificial intel...
127 篇 deep learning
102 篇 image processing...
101 篇 feature extracti...
95 篇 information syst...
95 篇 cameras
88 篇 image segmentati...
81 篇 object detection
81 篇 three-dimensiona...
75 篇 pattern recognit...
66 篇 face recognition
66 篇 machine learning
64 篇 computer applica...
63 篇 computer imaging...
61 篇 computational mo...
56 篇 computer archite...
56 篇 complexity theor...
55 篇 visualization
55 篇 3d reconstructio...

机构

11 篇 beijing jiaotong...
9 篇 tongji universit...
8 篇 chitkara univers...
7 篇 tsinghua univers...
7 篇 nanyang technolo...
7 篇 guangxi universi...
6 篇 indian statistic...
6 篇 computer enginee...
6 篇 tianjin universi...
6 篇 university of ca...
6 篇 lloyd law colleg...
5 篇 polytechnic inst...
5 篇 school of comput...
5 篇 school of electr...
5 篇 computer enginee...
5 篇 school of electr...
5 篇 university of so...
5 篇 chengdu institut...
5 篇 zhongshan instit...
4 篇 university of cr...

作者

13 篇 de-shuang huang
12 篇 sato jun
11 篇 sakaue fumihiko
10 篇 hellwich olaf
9 篇 josé braz
9 篇 woergoetter flor...
9 篇 saito hideo
8 篇 mario fedrizzi
8 篇 giulianella cole...
8 篇 salvatore greco
8 篇 stricker didier
8 篇 bernadette bouch...
8 篇 benedetto matara...
8 篇 ronald r. yager
8 篇 laurendeau denis
7 篇 telea alexandru
7 篇 tzovaras dimitri...
7 篇 constantine step...
6 篇 ando shigeru
6 篇 kruger norbert

语言

3,781 篇 英文
100 篇 中文
67 篇 其他
2 篇 俄文
1 篇 法文

检索条件"任意字段=3rd International Conference on Computer Vision Theory and Applications"

共 3942 条记录，以下是61-70 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：

Bridging the Gap: From Food Recognition to Accurate Weight Estimation

Bridging the Gap: From Food Recognition to Accurate Weight E...

引用

Disruptive Technologies (ICDT), international conference on

作者： Bhagyashree Maharana Mayank Kumar Goyal Ali Imam Abidi Department of Computer Science & Engineering Sharda School of Engineering & Technology Sharda University Greater Noida India

ISBN: (数字)9798331519582

ISBN: (纸本)9798331519599

Accurate estimation of food weight is of utmost importance in the assessment of diet in nutrition, healthcare, and wellness. Although great progress has been achieved with machine learning and computer vision in image-based food recognition, the task of accurate weight estimation is still a challenging one. This review summarizes the current methodologies that address the gap, focusing on the reduction of errors and novel innovations. The review compares 2D and 3D computational methods, emphasizes the advantages of hybrid multimodal models, and assesses their strengths and weaknesses. The role of datasets and annotation techniques is analyzed in detail, highlighting the importance of having diverse and accurate datasets for model improvement. Standard evaluation metrics and benchmarks are addressed to evaluate accuracy and comparability across methods. Realism emerging trends of self-supervised learning, multimodal data integration, and real-time edge computing applications are searched for as answers to these practical constraints found in reality: variability in food, occlusion, environmental factors all challenge; solution proposed here. This review is aimed at outlining future research guidance by summarizing recent innovations, addressing gaps, and providing a roadmap for practical, scalable, and accurate dietary assessment systems.

关键词： Technological innovation Image segmentation Accuracy Image recognition Three-dimensional displays Reviews Computational modeling Face recognition Estimation Real-time systems

来源：评论

学校读者我要写书评

暂无评论

A Review of Artificial Intelligence in Digital Watermarking Techniques

A Review of Artificial Intelligence in Digital Watermarking ...

引用

3rd IEEE international conference on Automation and Computation, AUTOCOM 2025

作者： Soni, Aayush Kaur, Kamalpreet Sharma, Chriag School of Computer Science Lovely professional university Phagwara India

ISBN: (纸本)9798331542375

In this era, watermarking has been considered to be the emerging technology in the digital world and an asset to various social economics domain which pin-pointing the concern in securing the data, privacy and intellectual property. In this review paper, 35 research papers have been reviewed which were published between 2020 and 2025 highlighting the major takeaways including usage and depth knowledge of watermarking techniques in different domain, its advantages and applications using machine learning. This research broader the vision in various sectors such as healthcare, meeting the challenge of securing and protecting the data. A comprehensive exploration of modern watermarking technologies in enhancing digital security through increased diversity in application and privacy. Consequently, this lesser the chances of illegal usage or distribution of intellectual properties and safeguards one's contribution. Thus, among the techniques of digital watermarking include frequency and spatial methods, with frequency domain offering better robustness. Also performance achieved through the deep learning-based methods considered to be highly adaptive, imperceptible, and highly secure watermarking solutions. © 2025 IEEE.

关键词： Deep learning

来源：评论

学校读者我要写书评

暂无评论

vision to Voice: An Advanced Blind Assistance System Integrating YOLOv3 and OCR Technologies for Enhanced Mobility

Vision to Voice: An Advanced Blind Assistance System Integra...

引用

Disruptive Technologies (ICDT), international conference on

作者： Gunjan Purushottam Kela Mokshada Girdhar Daga Richa Khandelwal Electronics And Computer Science Department Shri Ramdeobaba College Of Engineering And Management Nagpur India Department of Electronics Engineering Ramdeobaba University Nagpur India

ISBN: (数字)9798331519582

ISBN: (纸本)9798331519599

The rise in need for assistive technologies has led to the development of AI-empowered solutions for better accessibility for visually impaired persons. The proposed system is the use of a real-time object and text detection application using a combination of deep learning and speech synthesis techniques to enhance mobility and independence. The system utilizes Tesseract OCR for text recognition and pyttsx3 for TTS for better interfacing with the environment. YOLOv3-based object detection towards improving environmental awareness involves real-time identification of objects, with confidence thresholding and NMS serving to enhance robustness of the overall detection by curbing false positives. Further, the distance estimation module helps in mobility as it provides information on how far one is situated from an object. This architecture is a hardware-independent, lowlatency, and highly scalable solution compared to conventional assistive systems; thus, such systems are more harmonized for practical applications. Experimental findings exhibited its very high accuracy, confident standing across situations, and enhanced user experience rendering it with huge potential for granting enhanced independence and safety for the visually challenged user base.

关键词： YOLO Deep learning Text recognition Optical character recognition Text detection Assistive technologies Real-time systems User experience Text to speech Safety

来源：评论

学校读者我要写书评

暂无评论

Apple Leaf Disease Detection and Classification Using L1 Regularized Multi Head vision Transformer

Apple Leaf Disease Detection and Classification Using L1 Reg...

引用

Integrated Circuits and Communication Systems (ICICACS), IEEE international conference on

作者： Gayatri Math Vishwanath P Zayd Ajsan Balsem Supriya Suvendu Kumar Jena Department of Electronics and Communication Engineering PDA College of Engineering Kalaburagi India Affiliated to VTU Belagavi India Department of Electronics and Communication Engineering HKE Society's Sir M Visvesvaraya college of Engineering Raichur India Affiliated to VTU Belagavi Department of Computers Techniques Engineering College of Technical Engineering The Islamic University Al Diwaniyah Iraq Department of Information Science and Engineering Nitte Meenakshi Institute of technology Bengaluru India Department of computer science engineering and applications Indira Gandhi Institute of technology Sarang Dhenkanal India

ISBN: (数字)9798331508456

ISBN: (纸本)9798331508463

Timely identification of apple leaf diseases is important to avoid disease spread and ensure healthy growth of apple industry. Recent developments in digital cameras and electronic devices integrated with Machine Learning (ML) and Deep Learning (DL) based apple leaf disease detection has emerged as efficient to traditional visual inspection models. Therefore, this research proposes a L1 regularized Multi Head vision Transformer (L1-MHViT) for apple leaf disease detection and classification. The L1-MHViT utilized multi-head attention to capture complex patterns and improve classification performance. Furthermore, it incorporates advantages of convolution-based and transformer-based models to enhance the detection and classification accuracy. Furthermore, the Median Filter (MF) is applied for preprocessing which removes noise and enhance the image quality thereby helps to enhance the accuracy of the consequent steps. Then, EfficientNet is applied for feature extraction which is known for higher accuracy and effective scaling of model size. The effectiveness assessment of proposed L1-MHViT uses standard metrics which include precision (Pre), recall (Rec), F1 score (F1) and accuracy (Acc). The L1-MHViT achieved 99.46% pre, 99.54% rec, 99.50% F1 and 99.82% are for Apple dataset which is better than baseline models.

关键词： Image quality computer vision Accuracy Head Noise Transformers Feature extraction Magnetic heads Integrated circuit modeling Diseases

来源：评论

学校读者我要写书评

暂无评论

YOLOv8-Powered Real-Time Car Damage Detection

YOLOv8-Powered Real-Time Car Damage Detection

引用

Intelligent Data Communication Technologies and Internet of Things (IDCIoT), international conference on

作者： Yogeshwaran S Ramith Jagathese J R. Vasanthi CSE Department St. Joseph's Institute Of Technology Chennai Tamil Nadu India

ISBN: (数字)9798331527549

ISBN: (纸本)9798331527556

The increased interest in automated and precise vehicle damage detection tasks has influenced the advances of deep learning and computer vision technologies. This research presents a novel method for automatic vehicle damage assessment based on YOLOv8, one of the latest and powerfull detection models. The model's aim is to assist users in inspecting vehicles in cases where different category of damage such as broken lights, door and others are present. It is done by accurately identifying and classifying the damages without depending on manual effort which is produce issues like inaccurate and time consuming. For eight image damage categories extensive dataset has been prepared, that was used for modeling. To achieve good-quality models, the Roboflow tool was employed for the purpose of picture resizing and augmentation, which assures high-quality training and therefore enhances models. As the main tool for damage detection, YOLOv8 has also been trained over 5000 epochs to detect more complex images. The cumulated metrics include mean Average Precision, precision, and recall. From the data collected, it was established that the YOLOv8 model has been efficient in detecting damages in vehicles with enhanced ability than there was in previous versions of the model. This automated solution is particularly promising for use in the insurance and automobile damage assessment industries as it makes damage assessments more accurate and faster. There are future applications for this model and also made suggestions including increasing the dataset to account for more damage types and using techniques like transfer learning to increase the accuracy of the system.

关键词： Training Deep learning computer vision Accuracy Computational modeling Transfer learning Object detection Data models Real-time systems Automobiles

来源：评论

学校读者我要写书评

暂无评论

Underwater vision Enhancement: Adaptive White Balancing Combined with Nature-Inspired Algorithm Mechanisms

Underwater Vision Enhancement: Adaptive White Balancing Comb...

引用

Disruptive Technologies (ICDT), international conference on

作者： Gunjan Verma Divya Sharma Sanjeev Kumar Urvashi Garima Saini Taruna Chopra Master of Computer Applications G.L. Bajaj Institute of Technology and Management Greater Noida India School of Computer Applications Manav Rachna International Institute of Research and Studies Faridabad India Information Technology IINTM Janakpuri Guru Gobind Singh Indraprastha University Delhi India

ISBN: (数字)9798331519582

ISBN: (纸本)9798331519599

Underwater reconstructed images often suffer from color cast, low contrast, and reduced brightness due to absorption and scattering effects. Research has shown that underwater environments exhibit low-pass characteristics, leading to the loss of crucial image information and degradation in visual quality. Image enhancement techniques can help recover this lost information. Various underwater image enhancement methods have been proposed; however, existing approaches often introduce artefacts and produce unrealistic results. To address these challenges, we propose a novel adaptive white-balancing method specifically designed for underwater images. This method primarily focuses on correcting a color cast in underwater scenes. Following white balancing, both local and global contrast enhancements are applied to further improve image quality. The artificial bee colony algorithm is employed to significantly enhance contrast, while a Laplacian filter is used to refine local contrast. The proposed method effectively improves contrast and eliminates color cast, resulting in more natural-looking underwater images. Additionally, the integration of different algorithms enhances the quality of degraded images. Experimental results demonstrate that our method outperforms existing techniques, achieving the highest UIQM score (41.78 on RUIE, 44.82 on EUVP datasets) and the lowest BRISQUE score (2.8 on RUIE, 0.8 on EUVP), indicating superior contrast, color correction, and image naturalness.

关键词： Image quality Visualization Laplace equations Image resolution Image color analysis Lighting Scattering Image restoration Image enhancement Image reconstruction

来源：评论

学校读者我要写书评

暂无评论

Analysis of Tracking Algorithms for Multi-person Tracking 3rd

Analysis of Tracking Algorithms for Multi-person Tracking

引用

3rd international conference on Computing, Communication and Learning, CoCoLe 2024

作者： Anne, M. Evany Brindha, M. Department of Computer Science and Engineering National Institute of Technology TamilNadu Tiruchirappalli620015 India

ISBN: (纸本)9783031790409

Tracking humans using computer vision techniques is important in many surveillance applications. Apart from accuracy and speed, how tracking handles diverse settings such as normal and occluded scenarios also play a critical role. Detection-based tracking is discussed in this study. In this paper, the Multiple Object Tracker is implemented using the tracking-by-detection methodology. Detection is accomplished using the YOLOV8 model, and tracking is performed by various algorithms such as Centroid tracking, Kernelized Correlation Filter (KCF) tracking, CamShift tracking, and Channel and Spatial Reliability Tracker (CSRT) tracking. After performing the tracking by the different tracking algorithms, their performances are analyzed based on different videos. Moreover, in order to keep track of the number of people in the video, unique IDs are assigned to each person based on the IOU distance within the present and previous frames of the video. Besides that, in many edge cases such as occlusion scenarios, the system should be able to maintain the object identity efficiently to keep the count of the number of persons present in the video. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2025.

关键词： Object detection

来源：评论

学校读者我要写书评

暂无评论

A Review of Multi-modal and Multi-view applications in Hand-Drawn Sketch Images

A Review of Multi-modal and Multi-view Applications in Ha...

引用

28th international conference on Image Processing, computer vision, and Pattern Recognition, IPCV 2024, and 23rd international conference on Information and Knowledge Engineering, IKE 2024, held as part of the World Congress in computer Science, computer Engineering and Applied Computing, CSCE 2024

作者： Xu, Yunqi Suen, Ching Y. Gina Cody School of Engineering and Computer Science Concordia University MontrealQCH3G 1M8 Canada

ISBN: (纸本)9783031859328

Hand-drawn sketches have played a significant role throughout human history, from the ancient world to the present, influencing everything from early childhood education to human psychology. While humans can effortlessly recognize and understand varying abstractions in these sketches, machines find these tasks challenging. Recent advancements in multi-modal models have opened new possibilities for computer vision to interpret hand-drawn sketches more effectively. This survey provides a comprehensive review of the application of multi-modal approaches in the domain of hand-drawn sketches, with a particular focus on generation and recognition tasks. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2025.

关键词： computer vision

来源：评论

学校读者我要写书评

暂无评论

Modular Approaches to Complex Reasoning in Visual Question Answering Systems

Modular Approaches to Complex Reasoning in Visual Question A...

引用

international Symposium on Advanced Computing and Communication (ISACC)

作者： Akshay Bhosale Sujit Wandre Sagar Chavan Ketan Waje Sandeep Pande School of Computer Engineering MIT Academy of Engineering Pune India School of ENTC Engineering MIT Academy of Engineering Pune India School of Mechanical Engineering MIT Academy of Engineering Pune India

ISBN: (数字)9798331523893

ISBN: (纸本)9798331523909

Visual Question Answering is a challenging task requiring the integration of visual and textual information to answer questions about images. This research introduces a robust VQA system that combines advanced deep learning techniques, including Visual BERT, ViLT, cross-modal memory networks, memory-augmented attention mechanisms, and vision language pre-training models such as Flamingo and BLIP. These methods enable effective multimodal fusion, dynamic memory retrieval, and adaptation to novel question types using few-shot learning. Using the VQA v2.0 dataset, the system achieved 80% accuracy, outperforming traditional models such as LSTM-CNN and attention-only approaches. Enhanced BLEU scores and precision-recall metrics underscore its capability in handling complex, multi-step reasoning tasks. This work highlights significant improvements in VQA systems and establishes a scalable framework for advancing multimodal learning, paving the way for future research on larger datasets and real-world applications.

关键词： Visualization Adaptation models Accuracy Attention mechanisms Scalability Transportation Self-supervised learning Cognition Question answering (information retrieval) Data models

来源：评论

学校读者我要写书评

暂无评论

AI-Driven Thermal Imaging: A Comprehensive Web-Based Tool for Non-Invasive Medical Diagnostics

AI-Driven Thermal Imaging: A Comprehensive Web-Based Tool fo...

引用

international Symposium on Advanced Computing and Communication (ISACC)

作者： Aniruddha Ghosh Sayan Snigdha Pal Sumedha Das Spandan Bhattacharya Arijit Bhattacharya Nilanjana De Sudipta Sahana Computer Science and Engineering(Artificial Intelligence and Machine Learning) Institute of Engineering & Management Kolkata University of Engineering and Management Kolkata West Bengal India

ISBN: (数字)9798331523893

ISBN: (纸本)9798331523909

Thermography is an innovative technique that creates a heatmap of different portions of the human body by using infrared (IR) radiation where color scales vary for various temperature regions. This work's scope aims to extend thermal imaging applications with machine learning algorithms in conjunction with Azure API services to analyze thermal images and return a preliminary diagnosis. The project consists of generating heatmaps for better visualization results, analyzing them through image processing techniques, and feeding the information to Azure’s Custom vision API to detect anomalies and classify health conditions and finally producing a proper report. This research allows individuals and healthcare professionals to have a quick, non-invasive diagnostic tool that empowers health monitoring and preventive care. It combines the capabilities of contemporary technologies with uses directed toward health practice, leading to inimical patient outcomes and true practices.

关键词： Visualization Machine learning algorithms Image color analysis Infrared heating Infrared imaging Thermal analysis Medical diagnosis Predictive analytics Intelligent systems Monitoring

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395页 << < 3 4 5 6 7 8 9 10 11 12 > >>

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：