检索结果-内蒙古大学图书馆

17th Asian Conference on computer Vision, ACCV 2024

作者： Zhang, Lan Zhu, Xinshan He, Di Liao, Xin Sun, Biao School of Electrical and Information Engineering Tianjin University Tianjin China College of Computer Science and Electronic Engineering Hunan University Hunan China

ISBN: (纸本)9789819609628

Image inpainting technologies pose increasing threats to the security of image data through malicious use. Therefore, image inpainting forensics is crucial. The Segment Anything Model (SAM) is a powerful universal image segmentation model for various downstream tasks. However, the performance of SAM in inpainting forensics is significantly degraded due to the substantial disparity between natural and inpainted image domains. In this paper, we propose SAMIF, a SAM-based model for image inpainting forensics. First, based on SAM, a parallel convolutional neural network (CNN) branch is introduced to assist the SAM in extracting local noise information. Second, the cross-domain alignment fusion module (CAFM) is designed to better fuse the features of the two branches. Third, the artifact features generator (AFG) is designed between the encoder and decoder to disentangle the features extracted by the encoder. The auxiliary loss is introduced in AFG, which shortens the backpropagation path and guides the SAM branch to learn artifact features, thus enhancing the adaptability of SAM for the inpainting forensics task. Extensive experiments demonstrate that the proposed model achieves state-of-the-art results on five inpainting forensics datasets and exhibits excellent robustness and generalization capabilities. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Mortality prediction of COVID-19 patients using soft voting classifier

引用

International Journal of Cognitive Computing in engineering 2022年 3卷 172-179页

作者： Rai, Nishant Kaushik, Naman Kumar, Deepika Raj, Chandan Ali, Ahad Department of Computer Science & Engineering Bharati Vidyapeeth's College of Engineering New Delhi110063 India

COVID-19 is a novel coronavirus that spread around the globe with the initial reports coming from Wuhan, China, turned into a pandemic and caused enormous casualties. Various countries have faced multiple COVID spikes which put the medical infrastructure of these countries under immense pressure with third-world countries being hit the hardest. It can be thus concluded that determining the likeliness of death of a patient helps in avoiding fatalities which inspired the authors to research the topic. There are various ways to approach the problem such as past medical records, chest X-rays, CT scans, and blood biomarkers. Since blood biomarkers are most easily available in emergency scenarios, blood biomarkers were used as the features for the model. The data was first imputed and the training data was oversampled to avoid class imbalance in the model training. The model is composed of a voting classifier that takes in outputs from multiple classifiers. The model was then compared to base models such as Random Forest, XGBoost, and Extra Trees Classifier on multiple evaluation criteria. The F1 score was the concerned evaluation criterion as it maximizes the use of the medical infrastructure with the minimum possible casualties by maximizing true positives and minimizing false negatives. © 2022

关键词： Biomarkers

来源：评论

学校读者我要写书评

暂无评论

Speech-to-text Transfiguration in Language Numerals for Perpetual Deaf Patients 2

Speech-to-text Transfiguration in Language Numerals for Perp...

引用

2nd International Conference on Electrical, Electronics, Information and Communication Technologies, ICEEICT 2023

作者： Pradeep Kumar, B.P. Venkatesan, C. Suhas, A.R. Balamurugan, D. Sathiyapriya, V. HKBK College of Engineering Department of Electronics and Communication Engineering Bangalore India Sona College of Technology Department of Computer Science and Engineering Salem India Knowledge Institute of Technology Department of Computer Science and Engineering Salem India

ISBN: (纸本)9798350397635

This paper primarily designates the isolated words transfiguration in the Kannada language based on a few techniques like Mel Frequency Cepstral Coefficients (MFCCs), Euclidean distance measure, Wavelet Transforms and Vector Quantization (VQ) technique. The contiguous match to the test speech exclamation is found by comparing the Euclidean distance value of the MFCC coefficients with that of the utterances present in the training set. The matched sampled word is detected by the display of its text equivalent message trained during the test phase. MATLAB R2019b software is employed to build the framework. © 2023 IEEE.

关键词： Wavelet transforms

来源：评论

学校读者我要写书评

暂无评论

Looking Backwards (and Forwards): NSF Secure and Trustworthy Computing 20-Year Retrospective Panel Transcription

引用

IEEE Security and Privacy 2023年第2期21卷 32-42页

作者： Landwehr, Carl Reiter, Michael K. Williams, Laurie Tsudik, Gene Jaeger, Trent Kohno, Tadayoshi Kapadia, Apu University of Michigan Electrical Engineering Ann ArborMI48109-2122 United States Duke University Computer Science and Electrical and Computer Engineering DurhamNC27708 United States North Carolina State University Computer Science Department of the College of Engineering RaleighNC27513 United States University of California Computer Science Irvine United States The Pennsylvania State University Computer Science and Engineering University ParkPA16802 United States University of Washington Paul G. Allen School of Computer Science and Engineering SeattleWA98195 United States Indiana University Bloomington Department of Computer Science BloomingtonIN47408 United States

The U.S. National science Foundation (NSF) celebrated the 20th anniversary of its research funding programs in cybersecurity, and more generally, secure and trustworthy computing, with a panel session at its conference held in June, 2022. The panel members, distinguished researchers in different research areas of trustworthy computing, were asked to comment on what has been learned, what perhaps should be 'unlearned what still needs to be learned, and the status of education and training in their respective areas of expertise. Laurie Williams covered enterprise security and measuring security, Gene Tsudik commented on cryptographic security, Trent Jaeger addressed computing infrastructure security, Tadayoshi Kohno reviewed security in cyberphysical systems, and Apu Kapadia provided insights on human-centered security. Michael K. Reiter chaired the panel and moderated questions from the audience. This report provides a brief summary of NSF's research programs in the area and an edited transcript of the panel discussion. © 2003-2012 IEEE.

关键词： Personnel training

来源：评论

学校读者我要写书评

暂无评论

Biomechanical Evaluation of Fingers Repetitive Voluntary Tasks in Chronic Stroke Survivors

引用

IEEE Access 2023年 11卷 143649-143656页

作者： Adeel, Muhammad Peng, Chih-Wei Lee, I-Jung Lin, Bor-Shing National Taipei University Department of Computer Science and Information Engineering New Taipei City237303 Taiwan Taipei Medical University School of Biomedical Engineering College of Biomedical Engineering Taipei11031 Taiwan Taipei Medical University School of Gerontology and Long-Term Care College of Nursing Taipei11031 Taiwan National Taipei University College of Electrical Engineering and Computer Science New Taipei City237303 Taiwan

A chronic stroke affects hand mobility limiting the normal functioning of the finger joints. The voluntary tasks with a repetitive motion can identify the limitation in the range of motion (ROM) to enhance the hand functioning of stroke survivors. Therefore, we compared two voluntary tasks fast ball squeezing (FBS) and slow ball squeezing (SBS), and analyzed the variability of these tasks for finger pressure and ROM in chronic stroke survivors. An experimental study with 22 healthy and 39 chronic stroke participants was conducted. All of them wore an upper limb motion capture device (UMCD) to record the active (AROM) of finger joints during FBS and SBS tasks for 20 repetitions. The data were analyzed into the joint angle and pressure to compare these tasks and their variability. While comparing the FBS and SBS tasks, left-side pressure and both sides' ROM attained the level of significance (p © 2013 IEEE.

关键词： Joints (anatomy)

来源：评论

学校读者我要写书评

暂无评论

Revolutionizing Visual Artistry: Exploring the Transformative Power of Computational Photography 8

Revolutionizing Visual Artistry: Exploring the Transformativ...

引用

8th International Conference on Electronics, Communication and Aerospace Technology, ICECA 2024

作者： Annie Silviya, S.H. Sriman, B. Sathish Kumar, P. Adithyaa, A. Satyanarayanaa, H. Priyadharshini, K. Rajalakshmi Institute of Technology Computer Science Engineering Chennai India Vel Tech Rangarajan Dr Sagunthala R&d Institute of Science and Technology Computer Science Engineering Chennai India Vel Tech Multi Tech Dr.Rangarajan Dr.Sakunthala Engineering College Computer Science Engineering Chennai India Rajalakshmi Institute of Technology Computer and Communication Engineering Chennai India

ISBN: (纸本)9798350367904

In the past decade, there has been a significant shift in the way we consume and utilize visual media. The swift evolution in smartphone cameras has made photography and videography available to a large audience and the rise of social media has greatly boosted the influence of smartphone photography, making it an essential tool for amateurs and professionals alike. Computational photography - capture, enhancement and manipulation of images by digital computation, a field drawn from computer vision and image processing, lies at the core of this paradigm shift. This raises questions about whether smartphone cameras can truly rival traditional photography equipment. This paper reviews the field of Computational Photography, specifically its application in low-light imaging, dynamic range optimization, and bokeh effects, while drawing a comparison between photos captured by smartphones and DSLR. © 2024 IEEE.

关键词： Smartphones

来源：评论

学校读者我要写书评

暂无评论

A Survey of Punjabi Language Translation using OCR and ML 10

A Survey of Punjabi Language Translation using OCR and ML

引用

17th INDIACom;2023 10th International Conference on Computing for Sustainable Global Development, INDIACom 2023

作者： Khepra, Shaveta Kumari, Priya Gupta, Raj Abhishek Bramhe, Vijendra Singh School of Engineering and Technology Sharda University Department of Computer Science and Engineering Greater Noida India Shri Ramdeobaba College of Engineering and Management Department of Computer Science and Engineering Nagpur India

ISBN: (纸本)9789380544472

The use of Natural Language Processing (NLP) in machine translation has grown in significance as technologies as well as computers have become more prevalent in our daily lives. This essay's goal is to evaluate the work done in the field of natural language processing (NLP) to translate the Gurmukhi script, which is primarily used to represent the Punjabi language. Together with Hindi and Punjabi, the languages written throughout the Gurumukhi script has more than 1.5 billion native users, making it among the most used language worldwide. However, there is limited research available on the Gurmukhi script. The study presented in this paper focuses on using machine learning and AI techniques to translate written Gurmukhi text into Hindi and English languages. The input for the translation process will be in the form of machine-printed Gurmukhi text, while the output will be provided in both Hindi and English languages. The goal of this study is to enhance how well global languages absorb information and technology, making it easier and more accurate to translate from regional languages. In conclusion, the paper provides a comprehensive review of the work related to the translation of Gurmukhi script using NLP techniques, with a focus on the use of machine learning and AI. The findings of this study can contribute to the development of more advanced and accurate translation systems, making the exchange of information and knowledge more accessible for people who speak different languages. © 2023 Bharati Vidyapeeth, New Delhi.

关键词： Machine learning

来源：评论

学校读者我要写书评

暂无评论

Revolutionizing Road Maintenance: YOLO Based Pothole Detection System 10

Revolutionizing Road Maintenance: YOLO Based Pothole Detecti...

引用

10th International Conference on Advanced Computing and Communication Systems, ICACCS 2024

作者： Saranya, E. Nivetha, R. Abirami, S. Mohaideen Arsath, M. Dharaneesh, S. Sri Eshwar College of Engineering Department of Computer Science and Business Systems Coimbatore India

ISBN: (数字)9798350384369

ISBN: (纸本)9798350384369

Potholes on roadways pose a significant risk to public safety, leading to numerous accidents and fatalities annually. In this research, we present a custom-trained machine learning model for real-time pothole detection using the You Only Look Once (YOLO) version 7 object detection algorithm. Our study aims to address the critical issue of pothole-related accidents by evaluating the effectiveness of YOLO V7 in identifying potholes under various road conditions and lighting scenarios. We compare YOLO V7 with a sequential Convolutional Neural Network (CNN) algorithm and demonstrate that YOLO V7 outperforms in real-time pothole detection. The system incorporates a camera that captures live footage and highlights potholes in real time, enhancing road safety. Our research showcases the versatility of YOLO V7 in detecting potholes in both daylight and low-light conditions. Furthermore, we explore the feasibility of deploying YOLO V7 on edge devices for real-time pothole detection from moving vehicles. The results affirm YOLO V7's high accuracy and fast processing capabilities, making it a suitable solution for improving road safety by alerting drivers to road hazards. This research contributes to enhancing road safety and reducing accidents caused by potholes, ultimately saving lives and minimizing road infrastructure damage. © 2024 IEEE.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Intelligent Document Interaction with Advanced Vector Embeddings and FAISS-CPU Indexing 8

Intelligent Document Interaction with Advanced Vector Embedd...

引用

8th International Conference on Electronics, Communication and Aerospace Technology, ICECA 2024

作者： Sriman, B. Annie Silviya, S.H. Mouleesh, Y. Vinod, S. Nishanthini, S. Nikitha, Polimera Vel Tech Rangarajan Dr.Sagunthala R&d Institute of Science and Technology Computer Science and Engineering Chennai India Rajalakshmi Institute of Technology Computer Science and Engineering Chennai India Rajalakshmi Institute of Technology Computer and Communication Engineering Chennai India Vel Tech Multi Tech Dr Rangarajan Dr Sakunthala Engineering College Computer Science and Engineering Chennai India

ISBN: (纸本)9798350367904

Our research project aims to introduce an artificial intelligence (AI) conversational model that can be used to efficiently communicate with multiple PDF documents. Our solution uses natural language processing algorithms to enable users to have lively conversations with PDFs that have been uploaded. We have built a comprehensive platform that can interpret user queries and provide pertinent responses based on the content of uploaded documents by integrating Python with Streamlit for interface development, FAISSCPU for storage and similarity search, PyPDF2 for text extraction, ChromaDB, Langchain, and Google Gemini Generative AI for enhanced functionality. Our goals include developing a UI that is easy to use, processing documents correctly, and having strong conversational capabilities. © 2024 IEEE.

关键词： Conversational Model Google Gemini Generative AI Natural Language Processing

来源：评论

学校读者我要写书评

暂无评论

Frequency Attacks Based on Invertible Neural Networks

IEEE Transactions on Artificial Intelligence

引用

IEEE Transactions on Artificial Intelligence 2025年第2期6卷 292-300页

作者： Shao, Ming-Wen Yang, Jian-Xin Meng, Ling-Zhuang Hu, Zhi-Yong China University of Petroleum School of Computer Science and Technology East China Qingdao266580 China China University of Petroleum College of Control Science and Engineering East China Qingdao266580 China

Adversarial attacks reveal the vulnerability of classifiers based on deep neural networks to well-designed perturbations. Most existing attack methods focus on adding perturbations directly to the pixel space. However, the perturbations generated by these methods may be easily perceived by humans. To alleviate the aforementioned problem, we propose a novel high-frequency attack based on invertible neural networks (HA-INN) that relies on INNs to adds perturbations to the high-frequency space of the image instead of the pixel space. In this way, we can fool the classifier while the perturbations are not easily detected by humans. Specifically, we introduce INNs to separate the high-frequency and low-frequency components of the image. And the low-frequency components are guaranteed to be reconstructed as the original image, while the high-frequency components are replaced with resampled high-frequency latent variables with additional adversarial information. Then, the low-frequency components and the high-frequency components with adversarial information are inversely fed into the INN to generate effective adversarial examples. Extensive experiments on two datasets (CIFAR-10 and CIFAR-100) show that our method can generate misleading and transferable cross-architectural adversarial examples with greatly reduced computational resource requirements. Under the white-box setting, the attack success rate of CIFAR10 and CIFAR100 is 99.8% and 99.74%, respectively. Further, under the black-box setting, the adversarial examples generated by our method are more effective than the other methods. © 2020 IEEE.

关键词： Deep neural networks

来源：评论

学校读者我要写书评

暂无评论

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：

请选择收藏分类：

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

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：