检索结果-内蒙古大学图书馆

Diff9D: Diffusion-Based Domain-Generalized Category-Level 9-DoF Object Pose Estimation

学校读者我要写书评

暂无评论

arXiv 2025年

作者： Liu, Jian Sun, Wei Yang, Hui Deng, Pengchao Liu, Chongpei Sebe, Nicu Rahmani, Hossein Mian, Ajmal National Engineering Research Center for Robot Visual Perception and Control Technology College of Electrical and Information Engineering School of Robotics State Key Laboratory of Advanced Design and Manufacturing for Vehicle Body Hunan University Changsha410082 China Institute of Artificial Intelligence and Robotics Xi’an Jiaotong University Xi’an710049 China Department of Information Engineering and Computer Science University of Trento Trento38123 Italy School of Computing and Communications Lancaster University LA1 4YW United Kingdom Department of Computer Science The University of Western Australia WA6009 Australia

Nine-degrees-of-freedom (9-DoF) object pose and size estimation is crucial for enabling augmented reality and robotic manipulation. Category-level methods have received extensive research attention due to their potential for generalization to intra-class unknown objects. However, these methods require manual collection and labeling of large-scale real-world training data. To address this problem, we introduce a diffusion-based paradigm for domain-generalized category-level 9-DoF object pose estimation. Our motivation is to leverage the latent generalization ability of the diffusion model to address the domain generalization challenge in object pose estimation. This entails training the model exclusively on rendered synthetic data to achieve generalization to real-world scenes. We propose an effective diffusion model to redefine 9-DoF object pose estimation from a generative perspective. Our model does not require any 3D shape priors during training or inference. By employing the Denoising Diffusion Implicit Model, we demonstrate that the reverse diffusion process can be executed in as few as 3 steps, achieving near real-time performance. Finally, we design a robotic grasping system comprising both hardware and software components. Through comprehensive experiments on two benchmark datasets and the real-world robotic system, we show that our method achieves state-of-the-art domain generalization performance. Our code will be made public at https://***/CNJianLiu/Diff9D. Copyright © 2025, The Authors. All rights reserved.

关键词： Augmented reality

Exploring The Impact Of Artificial Intelligence On visual Communication In Unmasking Deep Fake And Ensuring Public Trust

学校读者我要写书评

暂无评论

Exploring The Impact Of Artificial Intelligence On Visual Co...

Intelligent Systems and Machine Learning Conference (ISML)

作者： Jagendra Singh Neeraj Abbas Thajeel Rhaif Alsahlanee Abha Kiran Rajpoot Gaurav Agrawal Mohit Tiwari Computer Science Engineering Alliance School of Advanced Computing Alliance University Banglore India School of Computer Science Engineering and Technology Bennett University Greater Noida India Development and Continuous Education Center University of Thi-Qar Thi-Qar Iraq Department of CSE(AIML) KIET Group of Institution Ghaziabad India Department of CSE(AI) KIET Group of Institution Ghaziabad India Dept. of Computer Science & Engineering Bharati Vidyapeeth’s College of Engineering Delhi India

ISBN: (数字)9798350343878

ISBN: (纸本)9798350343885

In this groundbreaking study, we delve into the pivotal role of the Vision Transformer (V-iT) in the realm of deepfake detection, seeking to unravel its effectiveness in navigating the intricate landscape of manipulated visual content. As image-generating technologies advance, the proliferation of Dfakes poses profound challenges to the integrity of digital media, sparking concerns about misinformation and eroding trust in visual communication. Against this backdrop, V-iT emerges as a cutting-edge solution, leveraging its unique ability to comprehend intricate patterns in visual data. Our research is anchored in a meticulous methodology, involving comprehensive experiments designed to assess V-iT's performance in deepfake detection. The results, spanning 10 diverse samples, reveal consistently high accuracy, precision, recall, and F1 rate values. V-iT's capacity to achieve accurate classifications, minimize false positives, and sensitively detect manipulated content underscores its robustness in addressing the complexities of deceptive media practices. This paper goes beyond a mere validation of V-iT's capabilities, offering a nuanced understanding of its performance metrics. The high precision values emphasize V-iT's accuracy in identifying manipulated content, while exceptional recall values highlight its sensitivity in capturing true positive instances. The balanced F1 rate provides a harmonious measure of V-iT's overall effectiveness, demonstrating its potential as a dependable tool in upholding the authenticity of visual communication.

关键词： Deepfakes visualization computer vision Accuracy Sensitivity visual communication Weapons Resists Transformers Robustness

On the Effectiveness of Function-Level Vulnerability Detectors for Inter-Procedural Vulnerabilities

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Li, Zhen Wang, Ning Zou, Deqing Li, Yating Zhang, Ruqian Xu, Shouhuai Zhang, Chao Jin, Hai School of Cyber Science and Engineering Huazhong University of Science and Technology Wuhan China Department of Computer Science University of Colorado Colorado Springs Colorado SpringsCO United States Institute for Network Sciences and Cyberspace Tsinghua University Beijing China School of Computer Science and Technology Huazhong University of Science and Technology Wuhan China National Engineering Research Center for Big Data Technology and System Services Computing Technology and System Lab Hubei Key Laboratory of Distributed System Security Hubei Engineering Research Center on Big Data Security Cluster and Grid Computing Lab China JinYinHu Laboratory Wuhan China

Software vulnerabilities are a major cyber threat and it is important to detect them. One important approach to detecting vulnerabilities is to use deep learning while treating a program function as a whole, known as function-level vulnerability detectors. However, the limitation of this approach is not understood. In this paper, we investigate its limitation in detecting one class of vulnerabilities known as inter-procedural vulnerabilities, where the to-be-patched statements and the vulnerability-triggering statements belong to different functions. For this purpose, we create the first Inter-Procedural Vulnerability Dataset (InterPVD) based on C/C++ open-source software, and we propose a tool dubbed VulTrigger for identifying vulnerability-triggering statements across functions. Experimental results show that VulTrigger can effectively identify vulnerability-triggering statements and inter-procedural vulnerabilities. Our findings include: (i) inter-procedural vulnerabilities are prevalent with an average of 2.8 inter-procedural layers;and (ii) function-level vulnerability detectors are much less effective in detecting to-be-patched functions of inter-procedural vulnerabilities than detecting their counterparts of intra-procedural vulnerabilities. Copyright © 2024, The Authors. All rights reserved.

关键词： Open source software

Towards a Deep Learning Pain-Level Detection Deployment at UAE for Patient-Centric-Pain Management and Diagnosis Support: Framework and Performance Evaluation

学校读者我要写书评

暂无评论

Procedia computer science 2023年 220卷 339-347页

作者： Leila Ismail Muhammad Danish Waseem Clouds and Distributed Computing and Systems (CLOUDS) Lab School of Computing and Information Systems Faculty of Engineering and Information Technology The University of Melbourne Australia. Intelligent Distributed Computing and Systems (INDUCE) Research Laboratory Department of Computer Science and Software Engineering College of Information Technology United Arab Emirates University UAE. National Water and Energy Center United Arab Emirates University UAE.

The outbreak of the COVID-19 pandemic revealed the criticality of timely intervention in a situation exacerbated by a shortage in medical staff and equipment. Pain-level screening is the initial step toward identifying the severity of patient conditions. Automatic recognition of state and feelings help in identifying patient symptoms to take immediate adequate action and providing a patient-centric medical plan tailored to a patient's state. In this paper, we propose a framework for pain-level detection for deployment in the United Arab Emirates and assess its performance using the most used approaches in the literature. Our results show that a deployment of a pain-level deep learning detection framework is promising in identifying the pain level accurately.

关键词： computer Vision Deep Learning Image Processing Machine Learning Pain Detection Patient-Centric Smart healthcare eHealth

MGSTCN: A multi-graph spatio-temporal convolutional network for metro passenger flow prediction 7

学校读者我要写书评

暂无评论

MGSTCN: A multi-graph spatio-temporal convolutional network ...

7th International Conference on Big Data computing and Communications, BigCom 2021

作者： Yang, Jiahao Liu, Tong Li, Chengfan Tong, Weiqin Zhu, Yanmin Ai, Wenwei Shanghai University School of Computer Engineering and Science China Shanghai Engineering Research Center of Intelligent Computing System China Shanghai Jiao Tong University Department of Computer Science and Engineering China Shanghai Shentong Metro Co. Ltd. China

ISBN: (纸本)9781665442527

Short-term passenger flow forecasting is significantly important in the urban rail transit system. However, there are many factors that affect passenger flows, and traditional statistical prediction methods are unable to model these complex factors comprehensively. Emerging deep learning models have become effective methods to overcome this problem. In this study, we propose a new deep learning model MGSTCN (Multi-Graph Spatio-Temporal Convolutional Network) to predict short-term passenger flows for all stations in an urban subway network. Specifically, MGSTCN is composed of three modules with the same structure, which models the temporal dependencies of passenger flows in three different time scales, i.e., recent, daily and weekly periods respectively. Each module contains three main components: a multi-graph convolutional layer, a feature fusion layer, and a recurrent neural network. In addition, we construct three topological graphs based on the subway network, station attributes, and passenger flow trends, to extract spatial features from different perspectives through graph convolutional networks. Besides, we also employ some external factors such as weather conditions and holidays to enhance the forecasting accuracy of our proposed model. We conduct experiments based on two real-world passenger flow datasets in Shanghai and Hangzhou, respectively. The results show that our proposed model has superior performance compared to the baselines. © 2021 IEEE.

关键词： Forecasting

HPC-Coder: Modeling Parallel Programs using Large Language Models

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Nichols, Daniel Marathe, Aniruddha Menon, Harshitha Gamblin, Todd Bhatele, Abhinav Department of Computer Science University of Maryland College ParkMD United States Center for Applied Scientific Computing Lawrence Livermore National Laboratory LivermoreCA United States Livermore Computing Lawrence Livermore National Laboratory LivermoreCA United States

Parallel programs in high performance computing (HPC) continue to grow in complexity and scale in the exascale era. The diversity in hardware and parallel programming models make developing, optimizing, and maintaining parallel software even more burdensome for developers. One way to alleviate some of these burdens is with automated development and analysis tools. Such tools can perform complex and/or remedial tasks for developers that increase their productivity and decrease the chance for error. Until recently, such tools for code development and performance analysis have been limited in the complexity of tasks they can perform, especially for parallel programs. However, with recent advancements in language modeling, and the availability of large amounts of open-source code related data, these tools have started to utilize predictive language models to automate more complex tasks. In this paper, we show how large language models (LLMs) can be applied to tasks specific to high performance and scientific codes. We introduce a new dataset of HPC and scientific codes and use it to fine-tune several pre-trained models. We compare several pre-trained LLMs on HPC-related tasks and introduce a new model, HPC-Coder, fine-tuned on parallel codes. In our experiments, we show that this model can auto-complete HPC functions where generic models cannot, decorate for loops with OpenMP pragmas, and model performance changes in scientific application repositories as well as programming competition solutions. Copyright © 2023, The Authors. All rights reserved.

关键词： Modeling languages

A Systematic Literature Review on Blockchain Consensus Mechanisms’ Security: Applications and Open Challenges

学校读者我要写书评

暂无评论

computer Systems science & Engineering 2024年第6期48卷 1437-1481页

作者： Muhammad Muntasir Yakubu Mohd Fadzil B Hassan Kamaluddeen Usman Danyaro Aisha Zahid Junejo Muhammed Siraj Saidu Yahaya Shamsuddeen Adamu Kamal Abdulsalam Department of Computer and Information Science Universiti Teknologi PETRONASPerak32610Malaysia Department of Information Technology Faculty of ComputingFederal University Dutsin-MaKatsina5001Nigeria Institute of Autonomous Systems Universiti Teknologi PETRONASPerak32610Malaysia Institut für Luftfahrtsysteme Universität StuttgartStuttgart70569Germany Department of Computer Science Academic City University CollegeAgbogbaAccra421Ghana Department of Mathematical Sciences National University of the Center of the Province of Buenos AiresPintoTandil399Argentina

This study conducts a systematic literature review(SLR)of blockchain consensus mechanisms,an essential protocols that maintain the integrity,reliability,and decentralization of distributed ledger *** aim is to comprehensively investigate prominent mechanisms’security features and vulnerabilities,emphasizing their security considerations,applications,challenges,and future *** existing literature offers valuable insights into various consensus mechanisms’strengths,limitations,and security vulnerabilities and their real-world ***,there remains a gap in synthesizing and analyzing this knowledge *** this gap would facilitate a structured approach to understanding consensus mechanisms’security and vulnerabilities *** study adheres to Preferred Reporting Items for Systematic Reviews and Meta-Analyses(PRISMA)guidelines and computer science standards and reviewed 3749 research papers from 2016 to 2024,excluding grey literature,resulting in 290 articles for descriptive *** research highlights an increased focus on blockchain consensus security,energy efficiency,and hybrid mechanisms within 60%of research papers post-2019,identifying gaps in scalability,privacy,and interoperability for future *** synthesizing the existing research and identifying the key trends,this SLR contributes to advancing the understanding of blockchain consensus mechanisms’security and guiding future research and structured innovation in blockchain systems and applications.

关键词： Blockchain consensus mechanisms supply chain management proof of work(PoW) proof of stake(PoS) practical byzantine fault tolerance(PBFT)

A Systematic Review of Machine Learning Approaches for Detecting Deceptive Activities on Social Media: Methods, Challenges, and Biases

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Liu, Yunchong Shen, Xiaorui Zhang, Yeyubei Wang, Zhongyan Tian, Yexin Dai, Jianglai Cao, Yuchen School of Engineering and Applied Science University of Pennsylvania United States Khoury college of computer science Northeastern University United States Center for Data Science New York University United States Georgia Institute of Technology College of Computing United States Department of EECS University of California Berkeley United States

Social media platforms like Twitter, Facebook, and Instagram have facilitated the spread of misinformation, necessitating automated detection systems. This systematic review evaluates 36 studies that apply machine learning (ML) and deep learning (DL) models to detect fake news, spam, and fake accounts on social media. Using the Prediction model Risk Of Bias ASsessment Tool (PROBAST), the review identified key biases across the ML lifecycle: selection bias due to non-representative sampling, inadequate handling of class imbalance, insufficient linguistic preprocessing (e.g., negations), and inconsistent hyperparameter tuning. Although models such as Support Vector Machines (SVM), Random Forests, and Long Short-Term Memory (LSTM) networks showed strong potential, over-reliance on accuracy as an evaluation metric in imbalanced data settings was a common flaw. The review highlights the need for improved data preprocessing (e.g., resampling techniques), consistent hyperparameter tuning, and the use of appropriate metrics like precision, recall, F1 score, and AUROC. Addressing these limitations can lead to more reliable and generalizable ML/DL models for detecting deceptive content, ultimately contributing to the reduction of misinformation on social media. © 2024, CC BY.

关键词： Adversarial machine learning

Multirate Time-Integration based on Dynamic ODE Partitioning through Adaptively Refined Meshes for Compressible Fluid Dynamics

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Doehring, Daniel Schlottke-Lakemper, Michael Gassner, Gregor J. Torrilhon, Manuel Applied and Computational Mathematics RWTH Aachen University Schinkelstrasse 2 North Rhine-Westphalia Aachen52062 Germany University of Stuttgart Germany High-Performance Scientific Computing Center for Advanced Analytics and Predictive Sciences University of Augsburg Germany Department of Mathematics and Computer Science Center for Data and Simulation Science University of Cologne Germany

In this paper, we apply the Paired-Explicit Runge-Kutta (P-ERK) schemes by Vermeire et. al. [1, 2] to dynamically partitioned systems arising from adaptive mesh refinement. The PERK schemes enable multirate time-integration with no changes in the spatial discretization methodology, making them readily implementable in existing codes that employ a method-of-lines approach. We show that speedup compared to a range of state of the art Runge-Kutta methods can be realized, despite additional overhead due to the dynamic re-assignment of flagging variables and restricting nonlinear stability properties. The effectiveness of the approach is demonstrated for a range of simulation setups for viscous and inviscid convection-dominated compressible flows for which we provide a reproducibility repository. In addition, we perform a thorough investigation of the nonlinear stability properties of the Paired-Explicit Runge-Kutta schemes regarding limitations due to the violation of monotonicity properties of the underlying spatial discretization. Furthermore, we present a novel approach for estimating the relevant eigenvalues of large Jacobians required for the optimization of stability *** Codes 65L06, 65M20, 76Mxx, 76Nxx © 2024, CC BY.

关键词： Runge Kutta methods