检索结果-内蒙古大学图书馆

R-Bench: Are your Large Multimodal Model Robust to Real-world Corruptions?

IEEE Journal on Selected Topics in Signal Processing 2025年

作者： Li, Chunyi Zhang, Jianbo Zhang, Zicheng Wu, Haoning Tian, Yuan Sun, Wei Lu, Guo Min, Xiongkuo Liu, Xiaohong Lin, Weisi Zhang, Xiao-Ping Zhai, Guangtao Shanghai Jiao Tong University Institute of Image Communication and Network Engineering Shanghai200240 China Nanyang Technological University College of Computing and Data Science 639798 Singapore Shanghai AI Lab Shanghai200232 China East China Normal University School of Communication and Electronic Engineering Shanghai200240 China Shanghai Jiao Tong University John Hopcroft Center Shanghai200240 China Toronto Metropolitan University Department of Electrical Computer and Biomedical Engineering TorontoONM5B 2K3 Canada

The outstanding performance of Large Multimodal Models (LMMs) has made them widely applied in vision-related tasks. However, various corruptions in the real world mean that images will not be as ideal as in simulations, presenting significant challenges for the practical application of LMMs. To address this issue, we introduce R-Bench, a benchmark focused on the Real-world Robustness of LMMs. Specifically, we: (a) model the complete link from user capture to LMMs reception, comprising 33 corruption dimensions, including 7 steps according to the corruption sequence, and 7 groups based on low-level attributes;(b) collect reference/distorted image dataset before/after corruption, including 2,970 question-answer pairs with human labeling;(c) propose comprehensive evaluation for absolute/relative robustness and benchmark 20 mainstream LMMs. Results show that while LMMs can correctly handle the original reference images, their performance is not stable when faced with distorted images, and there is a significant gap in robustness compared to the human visual system. We hope that R-Bench will inspire improving the robustness of LMMs, extending them from experimental simulations to the real-world application. © 2007-2012 IEEE.

关键词： AI-Generated Content Image Compression Perceptual Quality Ultra-Low Bitrate

来源：评论

学校读者我要写书评

暂无评论

Deep Learning based Defect Detection Algorithm for Solar Panels

Deep Learning based Defect Detection Algorithm for Solar Pan...

引用

WRC Symposium on Advanced Robotics and Automation (WRC SARA)

作者： Jiaqi Li Hongxu Li Yifan Wu Hailiang Zhou Luigi Manfredi Peng Li Hong Zhang Department of Key Lab of Industrial Computer Control Engineering Hebei Province Yanshan University Qinhuangdao China Department of Computing Science University of Alberta Edmonton AB Canada Hebei Baoding Jiasheng Photovoltaic Technology Co. Ltd. Department of Institute for Medical Science and Technology (IMSaT) University of Dundee United Kingdom Department of Electronic and Electrical Engineering Southern University of Science and Technology Shenzhen China

Defect detection of solar panels plays an essential role in guaranteeing product quality within automated production lines. However, traditional manual inspection of solar panel defects suffers from low efficiency. This paper proposes an enhanced YOLOv5 algorithm (EL-YOLOv5) fused with the CBAM hybrid attention module to ensure product quality. The algorithm focuses on detecting five common types of defects that frequently appear on photovoltaic production lines, namely hidden cracks, scratches, broken grids, black spots, and short circuits. This study utilizes publicly available solar panel datasets, as well as datasets collected from actual photovoltaic production lines. These datasets are annotated accordingly and used to train the proposed algorithm. The experimental results demonstrate that the proposed algorithm achieves good performance on both the public and actual solar panel defect datasets. Particularly in actual datasets, where defect features are often less apparent and defects are smaller in size, the proposed algorithm can still detect even minor black spots.

关键词：

来源：评论

学校读者我要写书评

暂无评论

PARCIV: Recognizing physical activities having complex interclass variations using semantic data of smartphone

PARCIV: Recognizing physical activities having complex inter...

引用

作者： Usman Sarwar, Muhammad Rehman Javed, Abdul Kulsoom, Farzana Khan, Suleman Tariq, Usman Kashif Bashir, Ali Department of Computer Sciences Air University and ASET: Ambient Systems and Emerging Technologies Lab Islamabad Pakistan National Center for Cyber Security Air University and ASET: Ambient Systems and Emerging Technologies Lab Islamabad Pakistan Department of Electrical Computer and Biomedical Engineering University of Pavia Pavia Italy College of Computer Science Engineering Prince Sattam bin Abdulaziz University Al-Kharj Saudi Arabia School of Computing Mathematics and Digital Technology Manchester Metropolitan University Manchester United Kingdom

Smartphones are equipped with precise hardware sensors including accelerometer, gyroscope, and magnetometer. These devices provide real-time semantic data that can be used to recognize daily life physical activities for personalized smart health assessment. Existing studies focus on the recognition of simple physical activities but they lacked in providing accurate recognition of physical activities having complex interclass variations. Therefore, this research focuses on the accurate recognition of physical activities having complex interclass variations. We propose a two-layered approach called PARCIVthat first clusters similar activities based on semantic data and then recognize them using a machine learning classifier. Our two-layered approach first bounds the highly indistinguishable activities in clusters to avoid misclassification with other distinguishable activities and thereafter recognize them on a fine-grained level within each cluster. To evaluate our approach, we make an android application that collects labeled data by using smartphone sensors from 10 participants, while performing activities. PARCIV recognizes distinguishable as well as indistinguishable activities with high accuracy of 99% on the self-collected dataset. Furthermore, PARCIV achieve 95% accuracy on the publicly available dataset used by state-of-the-art studies. PARCIVoutperforms various state-of-the-art studies by 8%-17% for simple activities as well as complex activities. © 2020 John Wiley & Sons, Ltd.

关键词： Smartphones

来源：评论

学校读者我要写书评

暂无评论

Performance Analysis and Enhancement of Beamforming Training in 802.11ad

arXiv

引用

arXiv 2023年

作者： Wu, Wen Cheng, Nan Zhang, Ning Yang, Peng Aldubaikhy, Khalid Shen, Xuemin The Department of Electrical and Computer Engineering University of Waterloo WaterlooONN2L 3G1 Canada State Key Lab. of ISN The School of Telecommunications Engineering Xidian University Xian710071 China The Department of Computing Sciences Texas A&M University Corpus ChristiTX78412 United States The School of Electronic Information and Communications Huazhong University of Science and Technology Wuhan430074 China The Department of Electrical Engineering Qassim University Buraydah52571 Saudi Arabia

Beamforming (BF) training is crucial to establishing reliable millimeter-wave communication connections between stations (STAs) and an access point. In IEEE 802.11ad BF training protocol, all STAs contend for limited BF training opportunities, i.e., associated BF training (A-BFT) slots, which results in severe collisions and significant BF training latency, especially in dense user scenarios. In this paper, we first develop an analytical model to evaluate the BF training protocol performance. Our analytical model accounts for various protocol components, including user density, the number of A-BFT slots, and protocol parameters, i.e., retry limit and contention window size. We then derive the average successful BF training probability, the BF training efficiency and latency. Since the derived BF training efficiency is an implicit function, to reveal the relationship between system parameters and BF training performance, we also derive an approximate expression of BF training efficiency. Theoretical analysis indicates that the BF training efficiency degrades drastically in dense user scenarios. To address this issue, we propose an enhancement scheme which adaptively adjusts the protocol parameters in tune with user density, to improve the BF training performance in dense user scenarios. Extensive simulations are carried out to validate the accuracy of the developed analytical model. In addition, simulation results show that the proposed enhancement scheme can improve the BF training efficiency by 35% in dense user scenarios. © 2023, CC BY-NC-SA.

关键词： Analytical models

来源：评论

学校读者我要写书评

暂无评论

Block Hunter: Federated Learning for Cyber Threat Hunting in Blockchain-based IIoT Networks

arXiv

引用

arXiv 2022年

作者： Yazdinejad, Abbas Dehghantanha, Ali Parizi, Reza M. Hammoudeh, Mohammad Karimipour, Hadis Srivastava, Gautam The Cyber Science Lab University of Guelph Canada The College of Computing and Software Engineering Kennesaw State University GA United States Information & Computer Science Department King Fahd University of Petroleum & Minerals Saudi Arabia The School of Engineering Department of Electrical and Software Engineering The University of Calgary Alberta Canada The Department of Math and Computer Science Brandon University Manitoba Canada The Research Centre for Interneural Computing China Medical University Taichung Taiwan

Nowadays, blockchain-based technologies are being developed in various industries to improve data security. In the context of the Industrial Internet of Things (IIoT), a chain-based network is one of the most notable applications of blockchain technology. IIoT devices have become increasingly prevalent in our digital world, especially in support of developing smart factories. Although blockchain is a powerful tool, it is vulnerable to cyber attacks. Detecting anomalies in blockchain-based IIoT networks in smart factories is crucial in protecting networks and systems from unexpected attacks. In this paper, we use Federated Learning (FL) to build a threat hunting framework called Block Hunter to automatically hunt for attacks in blockchain-based IIoT networks. Block Hunter utilizes a cluster-based architecture for anomaly detection combined with several machine learning models in a federated environment. To the best of our knowledge, Block Hunter is the first federated threat hunting model in IIoT networks that identifies anomalous behavior while preserving privacy. Our results prove the efficiency of the Block Hunter in detecting anomalous activities with high accuracy and minimum required bandwidth. © 2022, CC BY.

关键词： Blockchain

来源：评论

学校读者我要写书评

暂无评论

Real-time Holistic Robot Pose Estimation with Unknown States

arXiv

引用

arXiv 2024年

作者： Ban, Shikun Fan, Juling Ma, Xiaoxuan Zhu, Wentao Qiao, Yu Wang, Yizhou Center on Frontiers of Computing Studies School of Computer Science Peking University China Inst. for Artificial Intelligence Peking University China Nat’l Eng. Research Center of Visual Technology Nat’l Key Lab of General Artificial Intelligence Department of Automation School of Electronics Information and Electrical Engineering Shanghai Jiao Tong University China

Estimating robot pose from RGB images is a crucial problem in computer vision and robotics. While previous methods have achieved promising performance, most of them presume full knowledge of robot internal states, e.g. ground-truth robot joint angles. However, this assumption is not always valid in practical situations. In real-world applications such as multi-robot collaboration or human-robot interaction, the robot joint states might not be shared or could be unreliable. On the other hand, existing approaches that estimate robot pose without joint state priors suffer from heavy computation burdens and thus cannot support real-time applications. This work introduces an efficient framework for real-time robot pose estimation from RGB images without requiring known robot states. Our method estimates camera-to-robot rotation, robot state parameters, keypoint locations, and root depth, employing a neural network module for each task to facilitate learning and sim-to-real transfer. Notably, it achieves inference in a single feed-forward pass without iterative optimization. Our approach offers a 12× speed increase with state-of-the-art accuracy, enabling real-time holistic robot pose estimation for the first time. Code and models are available at https: //***/Oliverbansk/Holistic-Robot-Pose-Estimation. Copyright © 2024, The Authors. All rights reserved.

关键词：

来源：评论

学校读者我要写书评

暂无评论

The impact of feature importance methods on the interpretation of defect classifiers

arXiv

引用

arXiv 2022年

作者： Rajbahadur, Gopi Krishnan Wang, Shaowei Oliva, Gustavo A. Kamei, Yasutaka Hassan, Ahmed E. The Centre for Software Excellence Huawei Canada School of Computing Queen’s University Canada The department of computer science University of Manitoba Canada Lab Graduate School and Faulty of Information Science and Electrical Engineering Kyushu University Japan

Classifier specific (CS) and classifier agnostic (CA) feature importance methods are widely used (often interchangeably) by prior studies to derive feature importance ranks from a defect classifier. However, different feature importance methods are likely to compute different feature importance ranks even for the same dataset and classifier. Hence such interchangeable use of feature importance methods can lead to conclusion instabilities unless there is a strong agreement among different methods. Therefore, in this paper, we evaluate the agreement between the feature importance ranks associated with the studied classifiers through a case study of 18 software projects and six commonly used classifiers. We find that: 1) The computed feature importance ranks by CA and CS methods do not always strongly agree with each other. 2) The computed feature importance ranks by the studied CA methods exhibit a strong agreement including the features reported at top-1 and top-3 ranks for a given dataset and classifier, while even the commonly used CS methods yield vastly different feature importance ranks. Such findings raise concerns about the stability of conclusions across replicated studies. We further observe that the commonly used defect datasets are rife with feature interactions and these feature interactions impact the computed feature importance ranks of the CS methods (not the CA methods). We demonstrate that removing these feature interactions, even with simple methods like CFS improves agreement between the computed feature importance ranks of CA and CS methods. In light of our findings, we provide guidelines for stakeholders and practitioners when performing model interpretation and directions for future research, e.g., future research is needed to investigate the impact of advanced feature interaction removal methods on computed feature importance ranks of different CS methods. © 2022, CC BY-NC-ND.

关键词： Defects

来源：评论

学校读者我要写书评

暂无评论

Encryption with Image Steganography Based Data Hiding Technique in IIoT Environment

引用

computers, Materials & Continua 2022年第7期72卷 1323-1338页

作者： Mahmoud Ragab Samah Alshehri Hani A.Alhadrami Faris Kateb Ehab Bahaudien Ashary SAbdel-khalek Information Technology Department Faculty of Computing and Information TechnologyKing Abdulaziz UniversityJeddah21589Saudi Arabia Centre of Artificial Intelligence for Precision Medicines King Abdulaziz UniversityJeddah21589Saudi Arabia Department of Mathematics Faculty of ScienceAl-Azhar UniversityNaser City11884CairoEgypt Department of Pharmacy Practice Faculty of PharmacyKing Abdulaziz UniversityJeddah21589Saudi Arabia Department of Medical Laboratory Technology Faculty of Applied Medical SciencesKing Abdulaziz UniversityJeddah21589Saudi Arabia Molecular Diagnostic Lab King Abdulaziz University HospitalKing Abdulaziz UniversityJeddah21589Saudi Arabia Special Infectious Agent Unit King Fahd Medical Research CenterKing Abdulaziz UniversityJeddah21589Saudi Arabia Electrical and Computer Engineering Department Faculty of EngineeringKing Abdulaziz UniversityJeddah21589Saudi Arabia Department of Mathematics Faculty of ScienceTaif UniversityTaif21944Saudi Arabia Department of Mathematics Faculty of ScienceSohag UniversitySohag82524Egypt

Rapid advancements of the Industrial Internet of Things(IIoT)and artificial intelligence(AI)pose serious security issues by revealing secret ***,security data becomes a crucial issue in IIoT communication where secrecy needs to be guaranteed in real ***,AI techniques can be utilized to design image steganographic techniques in *** addition,encryption techniques act as an important role to save the actual information generated from the IIoT devices to avoid unauthorized *** order to accomplish secure data transmission in IIoT environment,this study presents novel encryption with image steganography based data hiding technique(EISDHT)for IIoT *** proposed EIS-DHT technique involves a new quantum black widow optimization(QBWO)to competently choose the pixel values for hiding secrete data in the cover *** addition,the multi-level discrete wavelet transform(DWT)based transformation process takes ***,the secret image is divided into three R,G,and B bands which are then individually encrypted using Blowfish,Twofish,and Lorenz Hyperchaotic *** last,the stego image gets generated by placing the encrypted images into the optimum pixel locations of the cover *** order to validate the enhanced data hiding performance of the EIS-DHT technique,a set of simulation analyses take place and the results are inspected interms of different *** experimental outcomes stated the supremacy of the EIS-DHT technique over the other existing techniques and ensure maximum security.

关键词： IIoT security data hiding technique image steganography encryption secure communication

来源：评论

学校读者我要写书评

暂无评论

The Age of Synthetic Realities: Challenges and Opportunities

arXiv

引用

arXiv 2023年

作者： Cardenuto, João Phillipe Yang, Jing Padilha, Rafael Wan, Renjie Moreira, Daniel Li, Haoliang Wang, Shiqi Andaló, Fernanda Marcel, Sébastien Rocha, Anderson Artificial Intelligence Lab. Recod.ai Institute of Computing University of Campinas SP Campinas Brazil Department of Computer Science Hong Kong Baptist University Hong Kong Department of Computer Science Loyola University Chicago ChicagoIL United States Department of Electrical Engineering City University of Hong Kong Hong Kong Department of Computer Science City University of Hong Kong Hong Kong Idiap Research Institute Martigny Switzerland University of Lausanne Lausanne Switzerland

Synthetic realities are digital creations or augmentations that are contextually generated through the use of Artificial Intelligence (AI) methods, leveraging extensive amounts of data to construct new narratives or realities, regardless of the intent to deceive. In this paper, we delve into the concept of synthetic realities and their implications for Digital Forensics and society at large within the rapidly advancing field of AI. We highlight the crucial need for the development of forensic techniques capable of identifying harmful synthetic creations and distinguishing them from reality. This is especially important in scenarios involving the creation and dissemination of fake news, disinformation, and misinformation. Our focus extends to various forms of media, such as images, videos, audio, and text, as we examine how synthetic realities are crafted and explore approaches to detecting these malicious creations. Additionally, we shed light on the key research challenges that lie ahead in this area. This study is of paramount importance due to the rapid progress of AI generative techniques and their impact on the fundamental principles of Forensic Science. Copyright © 2023, The Authors. All rights reserved.

关键词： Digital forensics

来源：评论

学校读者我要写书评

暂无评论

Reversible Graph Neural Network-based Reaction Distribution Learning for Multiple Appropriate Facial Reactions Generation

arXiv

引用

arXiv 2023年

作者： Xu, Tong Spitale, Micol Tang, Hao Liu, Lu Gunes, Hatice Song, Siyang The School of Computing and Mathematical Sciences University of Leicester LeicesterLE2 7RH United Kingdom The AFAR Lab Department of Computer Science and Technology University of Cambridge CambridgeCB3 0FT United Kingdom The Department of Information Technology and Electrical Engineering ETH Zurich Zurich8092 Switzerland

Generating facial reactions in a human-human dyadic interaction is complex and highly dependent on the context since more than one facial reactions can be appropriate for the speaker's behaviour. This has challenged existing machine learning (ML) methods, whose training strategies enforce models to reproduce a specific (not multiple) facial reaction from each input speaker behaviour. This paper proposes the first multiple appropriate facial reaction generation framework that re-formulates the one-to-many mapping facial reaction generation problem as a one-to-one mapping problem. This means that we approach this problem by considering generating a distribution of listeners' appropriate facial reactions instead of multiple different appropriate facial reactions, i.e.,'many' appropriate facial reaction labels are summarised as'one' distribution label during training. Our model consists of a perceptual processor, a cognitive processor, and a motor processor. The motor processor is implemented with a novel Reversible Multi-dimensional Edge Graph Neural Network (REGNN). This allows us to obtain a distribution of appropriate real facial reactions during the training process, enabling the cognitive processor to be trained to predict the appropriate facial reaction distribution. At the inference stage, the REGNN decodes an appropriate facial reaction by using the predicted distribution as input. Experimental results demonstrate that our approach outperforms existing models in generating more appropriate, realistic, and synchronized facial reactions. The improved performance is largely attributed to the proposed appropriate facial reaction distribution learning strategy and the use of a REGNN. The code will be made publicly available at https://***/TongXu-05/*** Codes 68T40 © 2023, CC0.

关键词： Mapping

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：