检索结果-内蒙古大学图书馆

International Conference on Acoustics, Speech, and Signal Processing (ICASSP)

作者： Constantin Patsch Jinghan Zhang Yuankai Wu Marsil Zakour Driton Salihu Eckehard Steinbach Department of Computer Engineering Chair of Media Technology Munich Institute of Robotics and Machine Intelligence (MIRMI) School of Computation Information and Technology Technical University of Munich

In action anticipation, the model predicts the next future action after a certain observation period. In long-term action anticipation, this idea is further extended to predicting multiple actions and their respective duration. Thus, in this problem setting the model should not only capture relationships between past actions but also predict several future actions that fit into a certain context. Compared to autoregressive models, our model employs an encoder decoder structure to determine future actions and durations in parallel, which prevents the accumulation of prediction errors and reduces the inference time. Furthermore, it is ensured that the predicted actions are aligned with respect to a context representation, which resembles the way humans approach this task as the feasible action set is restricted by the respective context. We evaluate our model on the long-term anticipation benchmark datasets, Breakfast, and 50Salads, where we achieve state-of-the-art results.

关键词：

来源：评论

学校读者我要写书评

暂无评论

NPRF: Neural Painted Radiosity Fields for Neural Implicit Rendering and Surface Reconstruction

NPRF: Neural Painted Radiosity Fields for Neural Implicit Re...

引用

International Conference on Acoustics, Speech, and Signal Processing (ICASSP)

作者： Driton Salihu Adam Misik Yuankai Wu Constantin Patsch Eckehard Steinbach Department of Computer Engineering Chair of Media Technology Munich Institute of Robotics and Machine Intelligence (MIRMI) Technical University of Munich School of Computation Information and Technology Siemens Technology

In recency, neural signed distance fields have become more popular for reconstructing 3D indoor environments. While great improvements have been made due to missing incident radiance and materials in the surface estimation, current methods cannot reconstruct high-quality surfaces. To address this issue, we propose Neural Painted Radiosity Fields (NPRF), consisting of Neural Radiosity Fields for volumetric surface representation and Neural Painted Scenes for novel view synthesis. Neural Radiosity Fields combine the radiative transfer equation with neural radiosity to estimate 3D surfaces, thus leveraging raytracing to improve the volumetric representation. Neural Painted Scenes employs sparsification and projection of 3D points into 2D images in conjunction with a generative, context-aware inpainting network to produce high-quality novel views. We show that NPRF leads to overall improvements in F-score on the popular ScanNet dataset. Finally, we show that NPRF improves novel view synthesis by a significant margin, giving improvements of up to 25% on PSNR, 53% on LPIPS, and 3% on SSIM.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Evaluation of Three Different Operators for Object Highlighting in Medical RGB Images: Canny, Roberts, and LoG in Independent Color Spaces 25

Evaluation of Three Different Operators for Object Highlight...

引用

25th International Arab Conference on information technology, ACIT 2024

作者： Ababneh, Jafar Abu-Jassar, Amer Abuowaida, Suhaila Liubchenko, Valentyn Lyashenko, Vyacheslav Zarqa University Faculty of Information Technology Cyber Security Department Zarqa Jordan University of Business and Technology College of Engineering Jeddah21448 Saudi Arabia Amman Arab University College of of Computer Sciences and Information Amman Jordan Al Al-Bayt University Faculty of Information Technology Department of Computer Science Al-Mafraq Jordan Kharkiv National University of Radio Electronics Department of Informatics Kharkiv Ukraine Kharkiv National University of Radio Electronics Department of Media Systems and Technology Kharkiv Ukraine

ISBN: (纸本)9798331540012

The research presents a comparative analysis of the selection of objects of interest in color medical cytology images. For these purposes, the individual edge detection operators studied are Canny, Roberts, and LoG. The comparison contrasts the standard method of assessing color photographs with a technique that incorporates supplementary information. Data from individual color channels, derived from the breakdown of a color image in RGB format, serve as supplementary information. The following individual cases for potential examination are emphasized: Image processing with a complete level of reuse of edge detection operators;with a partial level of reuse of edge detection operators. The results are displayed through an array of tables, graphs, and images. Metrics of visual perception of images are utilized for comparative analysis. Compared with traditional edge detection methods, the proposed approach yields better results, which can exceed the estimates of the classical approach by 20%. © 2024 IEEE.

关键词： Color photography

来源：评论

学校读者我要写书评

暂无评论

Optimal Deep Learning Model Enabled Secure UAV Classification for Industry 4.0

引用

computers, Materials & Continua 2023年第3期74卷 5349-5367页

作者： Khalid A.Alissa Mohammed Maray Areej A.Malibari Sana Alazwari Hamed Alqahtani Mohamed K.Nour Marwa Obbaya Mohamed A.Shamseldin Mesfer Al Duhayyim SAUDI ARAMCO Cybersecurity Chair Networks and Communications DepartmentCollege of Computer Science and Information TechnologyImam Abdulrahman bin Faisal UniversityP.O.Box 1982Dammam31441Saudi Arabia Department of Information Systems College of Computer ScienceKing Khalid UniversityAbhaSaudi Arabia Department of Industrial and Systems Engineering College of EngineeringPrincess Nourah bint Abdulrahman UniversityP.O.Box 84428Riyadh11671Saudi Arabia Department of Information Technology College of Computers and Information TechnologyTaif UniversityTaif P.O.Box 11099Taif21944Saudi Arabia Department of Information Systems College of Computer ScienceCenter of Artificial IntelligenceUnit of CybersecurityKing Khalid UniversityAbhaSaudi Arabia Department of Computer Sciences College of Computing and Information SystemUmm Al-Qura UniversitySaudi Arabia Department of Biomedical Engineering College of EngineeringPrincess Nourah bint Abdulrahman UniversityP.O.Box 84428Riyadh11671Saudi Arabia Department of Mechanical Engineering Faculty of Engineering and TechnologyFuture University in EgyptNew Cairo11835Egypt Department of Computer Science College of Sciences and Humanities-AflajPrince Sattam bin Abdulaziz UniversitySaudi Arabia

Emerging technologies such as edge computing,Internet of Things(IoT),5G networks,big data,Artificial Intelligence(AI),and Unmanned Aerial Vehicles(UAVs)empower,Industry 4.0,with a progressive production methodology that shows attention to the interaction between machine and human *** the literature,various authors have focused on resolving security problems in UAV communication to provide safety for vital *** current research article presents a Circle Search Optimization with Deep Learning Enabled Secure UAV Classification(CSODL-SUAVC)model for Industry 4.0 *** suggested CSODL-SUAVC methodology is aimed at accomplishing two core objectives such as secure communication via image steganography and image ***,the proposed CSODL-SUAVC method involves the following methods such as Multi-Level Discrete Wavelet Transformation(ML-DWT),CSO-related Optimal Pixel Selection(CSO-OPS),and signcryption-based *** proposed model deploys the CSO-OPS technique to select the optimal pixel points in cover *** secret images,encrypted by signcryption technique,are embedded into cover ***,the image classification process includes three components namely,Super-Resolution using Convolution Neural Network(SRCNN),Adam optimizer,and softmax *** integration of the CSO-OPS algorithm and Adam optimizer helps in achieving the maximum performance upon UAV *** proposed CSODLSUAVC model was experimentally validated using benchmark datasets and the outcomes were evaluated under distinct *** simulation outcomes established the supreme better performance of the CSODL-SUAVC model over recent approaches.

关键词： Unmanned Aerial Vehicles Artificial Intelligence emerging technologies Deep Learning Industry 4.0 image steganography

来源：评论

学校读者我要写书评

暂无评论

LEMON: Localized Editing with Mesh Optimization and Neural Shaders

arXiv

引用

arXiv 2024年

作者： Algan, Furkan Mert Yazgan, Umut Salihu, Driton Eteke, Cem Steinbach, Eckehard Technical University of Munich Chair of Media Technology Munich Institute of Robotics and Machine Intelligence MIRMI School of Computation Information and Technology Department of Computer Engineering Germany

In practical use cases, polygonal mesh editing can be faster than generating new ones, but it can still be challenging and time-consuming for users. Existing solutions for this problem tend to focus on a single task, either geometry or novel view synthesis, which often leads to disjointed results between the mesh and view. In this work, we propose LEMON, a mesh editing pipeline that combines neural deferred shading with localized mesh optimization. Our approach begins by identifying the most important vertices in the mesh for editing, utilizing a segmentation model to focus on these key regions. Given multi-view images of an object, we optimize a neural shader and a polygonal mesh while extracting the normal map and the rendered image from each view. By using these outputs as conditioning data, we edit the input images with a text-to-image diffusion model and iteratively update our dataset while deforming the mesh. This process results in a polygonal mesh that is edited according to the given text instruction, preserving the geometric characteristics of the initial mesh while focusing on the most significant areas. We evaluate our pipeline using the DTU dataset, demonstrating that it generates finely-edited meshes more rapidly than the current state-of-the-art methods. We include our code and additional results in the supplementary material. © 2024, CC BY.

关键词： Mesh generation

来源：评论

学校读者我要写书评

暂无评论

SNCA:Semi-Supervised Node Classification for Evolving Large Attributed Graphs

引用

Big Data Mining and Analytics 2024年第3期7卷 794-808页

作者： Faima Abbasi Muhammad Muzammal Qiang Qu Farhan Riaz Jawad Ashraf Luxembourg Institute of Science and Technology and University of Luxembourg Esch-Sur-Alzette L-4362Luxembourg Department of Computer and Information Sciences Northumbria UniversityNewcastle NE18STUK Shenzhen Institute of Advanced Technology Chinese Academy of SciencesShenzhen 518055China School of Computer Science University of LincolnLincoln LN67TSUK Faculty of Computing Engineering and MediaDe Montfort UniversityLeicesterLE19BHUK

Attributed graphs have an additional sign vector for each ***,edge signs represent like or dislike relationship between the node *** has applications in domains,such as recommender systems,personalised search,***,limited availability of edge sign information in attributed networks requires inferring the underlying graph embeddings to fill-in the knowledge *** inference is performed by way of node classification which aims to deduce the node characteristics based on the topological structure of the graph and signed interactions between the *** study of attributed networks is challenging due to noise,sparsity,and class imbalance *** this work,we consider node centrality in conjunction with edge signs to contemplate the node classification problem in attributed *** propose Semi-supervised Node Classification in Attributed graphs(SNCA).SNCA is robust to underlying network noise,and has in-built class imbalance handling *** perform an extensive experimental study on real-world datasets to showcase the efficiency,scalability,robustness,and pertinence of the *** performance results demonstrate the suitability of the solution for large attributed graphs in real-world settings.

关键词： attributed networks node classification recommender systems

来源：评论

学校读者我要写书评

暂无评论

VLP-KAN: Low-Complexity and Interpretable RSS-Based VLP Using Kolmogorov-Arnold Networks

VLP-KAN: Low-Complexity and Interpretable RSS-Based VLP Usin...

引用

Annual Conference on Wireless On Demand Network Systems and Services (WONS)

作者： Fabian Seguel Driton Salihu Stefan Hägele Eckehard Steinbach Department of Computer Engineering Chair of Media Technology Munich Institute of Robotics and Machine Intelligence (MIRMI) Technical University of Munich School of Computation Information and Technology München Germany

ISBN: (数字)9783903176713

ISBN: (纸本)9798331522025

Received signal strength (RSS)-based Visible Light Positioning (VLP) has gained attention due to its relatively easy infrastructure deployment and high localization accuracy. Different low-complexity geometrical and machine learning (ML)-based models have been proposed for localization because of their robustness against the uncertainty produced by tilted devices, non-Lambertian sources, and the low dimensionality of RSS-vector. Inspired by the Kolmogorov-Arnold representation theorem, Kolmogorov-Arnold Networks (KANs) have been proposed as a promising alternative to Multi-Layer Perceptrons (MLPs). This paper evaluates the use and performance of KANs in VLP systems for the first time. Results show that in the proposed scenario, KANs achieve below cm-level accuracy. Moreover, symbolic regression (SR) can be implemented straightforwardly to find a function that relates RSS with distance. It is shown in this paper that both KANs and SR-KAN models outperform MLP and Weighted K-nearest neighbors based approaches.

关键词： Location awareness Wireless communication Performance evaluation Deep learning Accuracy Uncertainty Nearest neighbor methods Fingerprint recognition Robustness Network systems

来源：评论

学校读者我要写书评

暂无评论

IoT Devices Authentication Using Artificial Neural Network

引用

computers, Materials & Continua 2022年第2期70卷 3701-3716页

作者： Syed Shabih Ul Hasan Anwar Ghani Ikram Ud Din Ahmad Almogren Ayman Altameem Department of Computer Science and Software Engineering International Islamic University Islamabad45000Pakistan Department of Information Technology The University of Haripur22620HaripurPakistan Chair of Cyber Security Department of Computer ScienceCollege of Computer and Information SciencesKing Saud UniversityRiyadh11633Saudi Arabia Chair of Cyber Security Department of Natural and Engineering SciencesCollege of Applied Studies and Community ServicesKing Saud UniversityRiyadh11543Saudi Arabia

User authentication is one of the critical concerns of information *** tend to use strong textual passwords,but remembering complex passwords is hard as they often write it on a piece of paper or save it in their mobile *** passwords are slightly unprotected and are easily *** attacks include dictionary,shoulder surfing,and brute *** passwords overcome the shortcomings of textual passwords and are designed to aid memorability and ease of *** paper proposes a Process-based Pattern Authentication(PPA)system for Internet of Things(IoT)devices that does not require a server to maintain a static password of the login *** server stores user’s information,which they provide at the time of registration,i.e.,the R-code and the symbol,but the P-code,i.e.,the actual password,will change with every login attempt of *** this scheme,users may draw a pattern on the basis of calculation from the P-code and Rcode in the PPA pattern,and can authenticate themselves using their touch dynamic behaviors through Artificial Neural Network(ANN).The ANN is trained on touch behaviors of legitimate users reporting superior performance over the existing *** experimental purposes,PPA is implemented as a prototype on a computer system to carry out experiments for the evaluation in terms of memorability and *** experiments show that the system has an effect of 5.03%of the False Rejection Rate(FRR)and 4.36%of the False Acceptance Rate(FAR),respectively.

关键词： Implicit authentication behavioral authentication artificial neural network processed pattern authentication

来源：评论

学校读者我要写书评

暂无评论

SPUFChain: Permissioned Blockchain Lightweight Authentication Scheme for Supply Chain Management Using PUF of IoT

引用

IEEE Access 2025年 13卷 88662-88682页

作者： Assaqty, Mohammad Iqbal Saryuddin Gao, Ying Alqarni, Abeer D. Khan, Siraj Chakraborty, Mohuya Nur Siddiqi, Hafied Ahmad, Sadique South China University of Technology School of Computer Science and Engineering Guangzhou510006 China Universitas Nahdlatul Ulama Indonesia Faculty of Engineering and Computer Science Jakarta10320 Indonesia Princess Nourah bint Abdulrahman University College of Computer and Information Sciences Department of Information Technology P.O. Box 84428 Riyadh11671 Saudi Arabia Research Institute for Future Media Computing College of Computer Science and Software Engineering Shenzhen University Shenzhen518060 China University of Engineering and Management Cybersecurity Centre of Excellence Kolkata700160 India Riyadh12435 Saudi Arabia

The complexity of the entire process of supply chain management (SCM) is quite cumbersome and traditional way of handling it is devoid of proper authentication and security and very often suffers from human errors in dealing with flaws in quality control process of SCM. While it may have started with shipment tracking, the outcome of using IoT on supply chains has spread to every link in the chain. For instance, manufacturers are employing Internet-enabled sensors in production to find product faults, resulting in higher-quality production runs. Physical Unclonable Function (PUF) is a defense countermeasure that exploits the exclusive, unrepeatable features of hardware components to generate distinct cryptographic keys or identifiers, typically for a semiconductor device like an Internet of Things (IoT) device. The distinctive proof of identity of IoT devices in the supply chain is employed by means of PUFs as inviolable IDs. Blockchain, the distributed, immutable ledger, on the other hand is the disruptive technology that provides higher security as compared to traditional centralized systems. The integration of PUF and blockchain proves to be quite interesting while handling the above issues of authentication. A smart contract on the blockchain is a software code that executes spontaneously as and when the conditions of the contract or agreement are satisfied. Hence after authentication process the results are fed to blockchain smart contract for the final validation. This paper presents a novel permissioned blockchain smart contract-based lightweight authentication scheme for SCM using PUF of IoT known as SPUFChain. Informal and formal security analysis (using AVISPA and BAN logic) of the proposed framework show its efficiency to resist several threat scenarios like man-in-the middle, non-repudiation, impersonation, replay attacks and many other security features as compared to other related schemes. The processing time (~13.8ms) is better than existing lightweig

关键词： Supply chain management

来源：评论

学校读者我要写书评

暂无评论

Sim-to-Real Domain Shift in Online Action Detection

Sim-to-Real Domain Shift in Online Action Detection

引用

IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)

作者： Constantin Patsch Wael Torjmene Marsil Zakour Yuankai Wu Driton Salihu Eckehard Steinbach Department of Computer Engineering School of Computation Information and Technology Munich Institute of Robotics and Machine Intelligence (MIRMI) Chair of Media Technology Technical University of Munich Muenchen Germany

ISBN: (数字)9798350377705

ISBN: (纸本)9798350377712

Human reasoning comprises the ability to understand and reason about the current action solely based on past information. To provide effective assistance in an eldercare or household environment an assistive robot or intelligent assistive system has to assess human actions correctly. Based on this presumption, the task of online action detection determines the current action solely based on the past without access to future information. During inference, the performance of the model is largely impacted by the attributes of the underlying training dataset. However, as high costs and ethical concerns are associated with the real-world data collection process, synthetically created data provides a way to mitigate these problems while providing additional data for the training process of the underlying action detection model to improve performanceDue to the inherent domain shift between the synthetic and real data, we introduce a new egocentric dataset called Human Kitchen Interactions (HKI) to investigate the sim-to-real gap. Our dataset contains in total 100 synthetic and real videos in which 21 different actions are executed in a kitchen environment. The synthetic data is acquired in an egocentric virtual reality (VR) setup while capturing the virtual environment in a game engine. We evaluate state-of-the-art online action detection models on our dataset and provide insights into sim-to-real domain shift. Upon acceptance, we will release our dataset and the corresponding features at https://***/HKI/.

关键词： Training Solid modeling Visualization Data acquisition Video sequences Virtual environments Training data Data models Synthetic data Videos

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：