检索结果-内蒙古大学图书馆

DIG: Improved DINO for Graffiti Detection

IEEE Transactions on Systems, Man, and Cybernetics: Systems 2025年第5期55卷 3557-3569页

作者： Wang, Bingshu Mao, Qianchen Liu, Aifei Chen, Long Chen, C. L. Philip Northwestern Polytechnical University School of Software Xi’an710129 China Shenzhen University Guangdong Key Laboratory of Intelligent Information Processing Shenzhen Key Laboratory of Media Security Shenzhen518060 China University of Macao Department of Computer and Information Science China South China University of Technology School of Computer Science and Engineering Guangzhou510641 China

Graffiti detection is essential in historic building protection and urban neighborhood management. Graffiti detection has made significant progress in recent years based on the development of deep learning. However, small-scale graffiti, interference from the background, and the false detection of word parts in graffiti make it a challenging problem. This article proposes a Transformer-based high-precision graffiti detection method, namely DIG. Precisely, it consists of three modules: 1) Spatial query selection (SQS), scale-aware IoU loss (SIL);2) Denoising Task with binary contrastive denoising (BCDN);and 3) IoU-guided box denoising (IBD) modules. To detect small-scale graffiti, this paper proposes SIL to help the loss function to perceive small-scale graffiti and large-scale graffiti fairly. To reduce the false detection of word parts, this article presents the SQS module, which integrates spatial information into the query selection process of the Encoder to filter out falsely detected bounding boxes within the graffiti. To reduce the interference from the background, this article introduces a denoising task with BCDN and IBD modules, improving the model’s ability to distinguish graffiti from the background and accurately select appropriate bounding boxes. A large number of experimental results on the STORM dataset show that our method achieves state-of-the-art results with an AP50 of 87.9%. Moreover, DIG achieved competitive results on the FineFM dataset for mask detection. This indicates that DIG can also be conveniently transferred to detect other scenarios. © 2013 IEEE.

关键词： Historic preservation

来源：评论

学校读者我要写书评

暂无评论

TruVRF: Toward Triple-Granularity Verification on Machine Unlearning

引用

IEEE Transactions on Information Forensics and Security 2025年 20卷 4844-4859页

作者： Zhou, Chunyi Gao, Yansong Fu, Anmin Chen, Kai Zhang, Zhi Xue, Minhui Dai, Zhiyang Ji, Shouling Zhang, Yuqing Zhejiang University College of Computer Science and Technology Hangzhou310027 China Nanjing University of Science and Technology College of Computer Science and Engineering Nanjing210094 China The University of Western Australia School of Computer Science and Software Engineering PerthWA6009 Australia Chinese Academy of Sciences Beijing100864 China Data61 CSIRO SydneyNSW2122 Australia Nanjing University of Science and Technology School of Cyber Science and Engineering Nanjing210094 China University of Chinese Academy of Sciences National Computer Network Intrusion Protection Center Beijing101408 China

The right to be forgotten has incentivized machine unlearning, but a key challenge persists: the lack of reliable methods to verify unlearning conducted by model providers. This gap facilitates dishonest model providers to deceive data contributors. Current approaches often rely on invasive methods like backdoor injection. However, it poses security concerns and is also inapplicable to legacy data—already released data. To tackle this challenge, this work initializes the first non-invasive unlearning verification framework which operates at triple-granularity (class-, volume-, sample-level) to assess the data facticity and volume integrity of machine unlearning. In this paper, we propose a framework, named TruVRF, encompasses three Unlearning-Metrics, each tailored to counter different types of dishonest model providers or servers (Neglecting Server, Lazy Server, Deceiving Server). TruVRF leverages non-invasive model sensitivity to enable multi-granularity verification of unlearning. Specifically, Unlearning-Metric-I checks if the removed class matches the data contributor’s unlearning request, Unlearning-Metric-II measures the amount of unlearned data, and Unlearning-Metric-III validates the correspondence of a specific unlearned sample with the requested deletion. We conducted extensive evaluations of TruVRF efficacy across three datasets, and notably, we also evaluated the effectiveness and computational overhead of TruVRF in real-world applications for the face recognition dataset. Our experimental results demonstrate that TruVRF achieves robust verification performance: Unlearning-Metric-I and -III achieve over 90% verification accuracy on average against dishonest servers, while Unlearning-Metric-II maintains an inference deviation within 4.8% to 8.2%. Additionally, TruVRF demonstrates generalizability across diverse conditions, including varying numbers of unlearned classes and sample volumes. Significantly, TruVRF is applied to two state-of-the-art unlearnin

关键词： Data models Servers Sensitivity Solid modeling Data privacy Computational modeling Context modeling Adaptation models Analytical models Volume measurement

来源：评论

学校读者我要写书评

暂无评论

TangibleMoments: Embedding XR Memories onto Physical Objects

TangibleMoments: Embedding XR Memories onto Physical Objects

引用

2025 IEEE Conference on Virtual Reality and 3D User Interfaces Abstracts and Workshops, VRW 2025

作者： Khan, Omar Ahmed, Zaid Nam, Hyeongil Kim, Kangsoo University of Calgary Department of Computer Science Canada Engineering University of Calgary Department of Electrical and Software Canada

ISBN: (纸本)9798331514846

The increasing prevalence of Extended Reality (XR) and head-mounted displays (HMDs), alongside rapid advancements in 3D reality capture technology, unlocks a new paradigm for capturing and reliving past memories/experiences through XR. Current methods for accessing and interacting with these "XR Memories"still lack the ability to fully leverage the range of capabilities afforded by XR and HMDs. We introduce TangibleMoments, a novel framework that enables users to embed XR memories onto physical objects, transforming those objects into "Moments"- tangible user interfaces for accessing and interacting with XR memories. We describe and illustrate five interaction methods as part of this framework: Creating Moments, Recalling Moments, Sharing Moments, Copying Moments, and Clearing Moments. We showcase an initial prototype and discuss possible extensions. © 2025 IEEE.

关键词： gaussian splatting Mixed reality spatial memory tangible user interfaces virtual reality

来源：评论

学校读者我要写书评

暂无评论

Optimizing auditory brainstem response detection through NSGA-II guided feature selection

引用

Neural Computing and Applications 2025年第15期37卷 8925-8943页

作者： Majidpour, Jafar Hassanzadeh, Hiwa Khezri, Edris Arabi, Hossein Department of Software Engineering University of Raparin Kurdistan Region Rania Iraq Department of Computer Science University of Raparin Kurdistan Region Rania Iraq Department of Computer Engineering Islamic Azad University Boukan Branch Boukan Iran Division of Nuclear Medicine and Molecular Imaging Department of Medical Imaging Geneva University Hospital Geneva1211 Switzerland

Hearing-impaired people undergo auditory brainstem response (ABR) testing to assess their peripheral auditory nerve system. Audiologists apply diagnostic labels to ABR data using reference-based indicators such as peak latency, waveform shape, amplitude, and others. ABR test scoring errors may invalidate auditory nerve system integrity results. Machine learning, especially deep learning, may reduce human error in ABR analysis. This work offers a complete methodology to handle ABR analysis problems. First, extract ABR test images from PDF reports to create a dataset. The next step uses Elastic Distortion approach to create high-quality ABR images while conserving data. ResNet-50 deep learning extracts ABR image characteristics in the third phase. The fourth step finds the most relevant features using a trainable multi-objective non-dominated sorting genetic algorithm II optimizer. Finally, ABR images are classified using machine learning algorithms. The proposed model achieved significant performance metrics: an accuracy of 99.46%, precision of 99.33%, specificity of 99.57%, sensitivity of 99.57%, F1-score of 99.43%, and a mean squared error of 0.0054 when using a support vector machine classifier with both augmented and original images. These findings demonstrate the effectiveness of trainable feature selection and high-quality ABR images in improving ABR analysis accuracy. © The Author(s), under exclusive licence to Springer-Verlag London Ltd., part of Springer Nature 2025.

关键词： Mean square error

来源：评论

学校读者我要写书评

暂无评论

ICCG:low-cost and efficient consistency with adaptive synchronization for metadata replication

引用

Frontiers of computer science 2025年第1期19卷 53-70页

作者： Chenhao ZHANG Liang WANG Jing SHANG Zhiwen XIAO Limin XIAO Meng HAN Bing WEI Runnan SHEN Jinquan WANG State Key Laboratory of Software Development Environment Beihang UniversityBeijing 100191China School of Computer Science and Engineering Beihang UniversityBeijing 100191China School of Cyberspace Security Hainan UniversityHaikou 570228China China Mobile Information Technology Center Beijing 100033China

The rapid growth in the storage scale of wide-area distributed file systems (DFS) calls for fast and scalable metadata management. Metadata replication is the widely used technique for improving the performance and scalability of metadata management. Because of the POSIX requirement of file systems, many existing metadata management techniques utilize a costly design for the sake of metadata consistency, leading to unacceptable performance overhead. We propose a new metadata consistency maintenance method (ICCG), which includes an incremental consistency guaranteed directory tree synchronization (ICGDT) and a causal consistency guaranteed replica index synchronization (CCGRI), to ensure system performance without sacrificing metadata consistency. ICGDT uses a flexible consistency scheme based on the state of files and directories maintained through the conflict state tree to provide an incremental consistency for metadata, which satisfies both metadata consistency and performance requirements. CCGRI ensures low latency and consistent access to data by establishing a causal consistency for replica indexes through multi-version extent trees and logical time. Experimental results demonstrate the effectiveness of our methods. Compared with the strong consistency policies widely used in modern DFSes, our methods significantly improve the system performance. For example, in file creation, ICCG can improve the performance of directory tree operations by at least 36.4 times.

关键词： metadata management metadata replication consistency directory tree replica index

来源：评论

学校读者我要写书评

暂无评论

Investigating Visual Guide Cues in VR: Impacts of Virtual Humans and Symbol-Based Navigation on Real-World Performance and Experience

Investigating Visual Guide Cues in VR: Impacts of Virtual Hu...

引用

2025 IEEE Conference on Virtual Reality and 3D User Interfaces Abstracts and Workshops, VRW 2025

作者： Khan, Omar Nguyen, Anh Nam, Hyeongil Kim, Kangsoo University of Calgary Department of Computer Science Canada University of Calgary Department of Electrical and Software Engineering Canada

ISBN: (纸本)9798331514846

Virtual experiences can significantly influence our perception and behavior in the real world, shaping how we interact with and navigate physical environments. In this paper, we examine the impact of learning navigation routes in an immersive virtual environment (IVE) on navigation performance and user experience in a corresponding real-world indoor setting. We developed a guide system with two distinct audiovisual representations: a human agent guide and a symbol-based guide. A preliminary user study (N = 10) was conducted to evaluate the system. While no significant differences were observed between the two guide conditions, the findings reveal valuable insights into user-perceived confidence and enjoyment during real-world navigation tasks. Contrary to our expectations, the symbol-based guide elicited slightly higher positive scores compared to the human agent guide. We discuss these findings and outline directions for future research. © 2025 IEEE.

关键词： confidence enjoyment navigation Real-Virtual influence task load virtual human visual cues

来源：评论

学校读者我要写书评

暂无评论

DKGV: A Dynamic Knowledge Graph Visualization Method Based on Force-Directed Layout 19

DKGV: A Dynamic Knowledge Graph Visualization Method Based o...

引用

19th ACM SIGGRAPH International Conference on Virtual-Reality Continuum and its Applications in Industry, VRCAI 2024

作者： Zhou, Hong Huang, Sunjie Zheng, Yushan Liu, Jinyan Chen, Yang Chen, Xiangyuan Li, Jun College of Computer Science and Software Engineering Shenzhen University Shenzhen China Shenzhen Academy of Inspection and Quarantine Shenzhen China Shenzhen University Shenzhen China

ISBN: (纸本)9798400713484

The dynamic knowledge graph is a data structure that adds temporal information to the nodes and edges of a traditional knowledge graph. It describes the changing processes of entities and relationships over time, thereby enriching and updating the expression of knowledge. The dynamic knowledge graph possesses characteristics such as time and labels;it is not only a knowledge graph but also a type of dynamic graph containing heterogeneous information. To address the issue that traditional dynamic graph visualization methods do not account for heterogeneous information in the layout, leading to a relatively random distribution of node labels in the visualization results, this paper proposes DKGV, a dynamic knowledge graph visualization method based on a force-directed layout. DKGV utilizes an improved GCN to generate the initial layout of the dynamic knowledge graph data, performs static force-directed layout iterative processing, and conducts dynamic force-directed layout calculations on the dynamic knowledge graph. Finally, it employs a force-directed layout with boundaries to support three-dimensional temporal display after view transformation. Experimental results show that DKGV can maintain the stability of the node layout during the evolution of the dynamic knowledge graph while making the overall layout more regular to better display the relationships between entities. © 2024 ACM.

关键词： Knowledge graph

来源：评论

学校读者我要写书评

暂无评论

FER-Former: Multimodal Transformer for Facial Expression Recognition

引用

IEEE Transactions on Multimedia 2025年 27卷 2412-2422页

作者： Li, Yande Wang, Mingjie Gong, Minglun Lu, Yonggang Liu, Li Lanzhou University School of Information Science and Engineering Lanzhou730000 China University of Guelph School of Computer Science GuelphONN1G 2W1 Canada University of Alberta Department of Electrical & Computer Engineering EdmontonABT6G 1H9 Canada Zhejiang Sci-Tech University School of Science Hangzhou310018 China Chongqing University School of Big Data and Software Engineering Chongqing401331 China

The ever-increasing demands for intuitive interactions in virtual reality have led to surging interests in facial expression recognition (FER). There are however several issues commonly seen in existing methods, including narrow receptive fields and homogenous supervisory signals. To address these issues, we propose in this paper a novel multimodal supervision-steering transformer for facial expression recognition in the wild, referred to as FER-former. Specifically, to address the limitation of narrow receptive fields, a hybrid feature extraction pipeline is designed by cascading both prevailing CNNs and transformers. To deal with the issue of homogenous supervisory signals, a heterogeneous domain-steering supervision module is proposed to incorporate text-space semantic correlations to enhance image features, based on the similarity between image and text features. Additionally, a FER-specific transformer encoder is introduced to characterize conventional one-hot label-focusing and CLIP-based text-oriented tokens in parallel for final classification. Based on the collaboration of multifarious token heads, global receptive fields with multimodal semantic cues are captured, delivering superb learning capability. Extensive experiments on popular benchmarks demonstrate the superiority of the proposed FER-former over the existing state-of-the-art methods. © 1999-2012 IEEE.

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

RPPFL: Robust and Privacy-Preserving Federated Learning via Trusted Execution Environments

RPPFL: Robust and Privacy-Preserving Federated Learning via ...

引用

2025 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2025

作者： Zhang, Xiaolei Chen, Zhaoyu Chen, Guangpu Feng, Xinyu Shen, Qingni Wu, Zhonghai School of Computer Science Peking University China School of Software and Microelectronics Peking University China National Engineering Research Center for Software Engineering Peking University China PKU-OCTA Laboratory for Blockchain and Privacy Computing Peking University China

ISBN: (纸本)9798350368741

Federated Learning (FL) is a distributed framework that enables multi-participant collaborative model training without the need for data sharing. Despite its advantages, FL is vulnerable to poisoning and inference attacks, which compromise model accuracy and data privacy. Trusted execution environments (TEEs) offer a potential solution by providing a secure and isolated execution space to address these security and privacy concerns in FL. However, existing TEE-based FL schemes often suffer from reduced training speed and compromised model accuracy. To mitigate these issues, we propose a robust and privacy-preserving framework for federated learning (RPPFL) that leverages TEE and pseudorandom masking. In our approach, a trusted local model is trained on a secure subset of local data within the client-side TEE, which is then used for anomaly detection to resist poisoning attacks. Additionally, we employ pseudorandom masking to obfuscate local updates and global parameters. Experimental results indicate that RPPFL effectively counters both poisoning and inference attacks, with only a minimal decrease in training speed and no adverse impact on model accuracy. Compared to full-TEE approaches, our method improved local training efficiency by 10×, with less than a 9% loss in model performance under poisoning attacks. © 2025 IEEE.

关键词： Data Obfuscation Federated Learning Privacy Preservation Robustness Trusted Execution Environments

来源：评论

学校读者我要写书评

暂无评论

An Empirical Study on Meta Virtual Reality Applications: Security and Privacy Perspectives

引用

IEEE Transactions on software engineering 2025年第5期51卷 1437-1454页

作者： Guo, Hanyang Dai, Hong-Ning Luo, Xiapu Xu, Gengyang He, Fengliang Zheng, Zibin Hong Kong Baptist University Department of Computer Science 999077 Hong Kong Sun Yat-sen University School of Software Engineering Zhuhai519082 China The Hong Kong Polytechnic University Department of Computing 999077 Hong Kong

Virtual Reality (VR) has accelerated its prevalent adoption in emerging metaverse applications, but it is not a fundamentally new technology. On the one hand, most VR operating systems (OS) are based on off-the-shelf mobile OS (e.g., Android OS). As a result, VR apps also inevitably inherit privacy and security deficiencies from conventional mobile apps. On the other hand, in contrast to traditional mobile apps, VR apps can achieve an immersive experience via diverse VR devices, such as head-mounted displays, body sensors, and controllers. However, achieving this requires the extensive collection of privacy-sensitive human biometrics (e.g., hand-tracking and face-tracking data). Moreover, VR apps have been typically implemented by 3D gaming engines (e.g., Unity), which also contain intrinsic security vulnerabilities. Inappropriate use of these technologies may incur privacy leaks and security vulnerabilities although these issues have not received significant attention compared to the proliferation of diverse VR apps. In this paper, we develop a security and privacy assessment tool, namely the VR-SP detector for VR apps. The VR-SP detector has integrated program static analysis tools and privacy-policy analysis methods. Using the VR-SP detector, we conduct a comprehensive empirical study on 900 popular VR apps. We obtain the original apps from the popular SideQuest app store and extract Android PacKage (APK) files via the Meta Quest 2 device. We evaluate the security vulnerabilities and privacy data leaks of these VR apps through VR app analysis, taint analysis, privacy policy analysis, and user review analysis. We find that a number of security vulnerabilities and privacy leaks widely exist in VR apps. Moreover, our results also reveal conflicting representations in the privacy policies of these apps and inconsistencies of the actual data collection with the privacy-policy statements of the apps. Further, user reviews also indicate their privacy concerns about rele

关键词： Differential privacy

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：