检索结果-内蒙古大学图书馆

arXiv 2023年

作者： Wang, Xinshun Zhang, Wanying Wang, Can Gao, Yuan Liu, Mengyuan the National Key Laboratory of General Artificial Intelligence Peking University Shenzhen Graduate School China the School of Intelligent Systems Engineering Sun Yat-sen University China the Multimedia Information Processing Laboratory the Department of Computer Science Kiel University Germany Peking University China the Unit of Computing Sciences CS Faculty of Information Technology and Communication Sciences ITC Tampere University Finland

Graph Convolutional Networks (GCN) which typically follows a neural message passing framework to model dependencies among skeletal joints has achieved high success in skeleton-based human motion prediction task. Nevertheless, how to construct a graph from a skeleton sequence and how to perform message passing on the graph are still open problems, which severely affect the performance of GCN. To solve both problems, this paper presents a Dynamic Dense Graph Convolutional Network (DD-GCN), which constructs a dense graph and implements an integrated dynamic message passing. More specifically, we construct a dense graph with 4D adjacency modeling as a comprehensive representation of motion sequence at different levels of abstraction. Based on the dense graph, we propose a dynamic message passing framework that learns dynamically from data to generate distinctive messages reflecting sample-specific relevance among nodes in the graph. Extensive experiments on benchmark Human 3.6M and CMU Mocap datasets verify the effectiveness of our DD-GCN which obviously outperforms state-of-the-art GCN-based methods, especially when using long-term and our proposed extremely long-term protocol. Copyright © 2023, The Authors. All rights reserved.

关键词： Message passing

来源：评论

学校读者我要写书评

暂无评论

FEDCSD: A FEDERATED LEARNING BASED APPROACH FOR CODE-SMELL DETECTION

arXiv

引用

arXiv 2023年

作者： Alawadi, Sadi Alkharabsheh, Khalid Alkhabbas, Fahed Kebande, Victor Awaysheh, Feras M. Palomba, Fabio Awad, Mohammed Center for Applied Intelligent Systems Research School of Information Technology Halmstad University Halmstad Sweden Department of Software Engineering Prince Abdullah bin Ghazi Faculty of Information and Communication Technology Al-Balqa Applied University Jordan Internet of Things and People Research Center Malmö University Sweden Department of Computer Science Blekinge Institute of Technology Sweden Institute of Computer Science Delta Research Centre University of Tartu Estonia SeSa Lab University of Salerno Italy Arab American University Palestine Palestine

software quality is critical, as low quality, or "Code smell," increases technical debt and maintenance costs. There is a timely need for a collaborative model that detects and manages code smells by learning from diverse and distributed data sources while respecting privacy and providing a scalable solution for continuously integrating new patterns and practices in code quality management. However, the current literature is still missing such capabilities. This paper addresses the previous challenges by proposing a Federated Learning Code Smell Detection (FedCSD) approach, specifically targeting "God Class," to enable organizations to train distributed ML models while safeguarding data privacy collaboratively. We conduct experiments using manually validated datasets to detect and analyze code smell scenarios to validate our approach. Experiment 1, a centralized training experiment, revealed varying accuracies across datasets, with dataset two achieving the lowest accuracy (92.30%) and datasets one and three achieving the highest (98.90% and 99.5%, respectively). Experiment 2, focusing on cross-evaluation, showed a significant drop in accuracy (lowest: 63.80%) when fewer smells were present in the training dataset, reflecting technical debt. Experiment 3 involved splitting the dataset across 10 companies, resulting in a global model accuracy of 98.34%, comparable to the centralized model’s highest accuracy. The application of federated ML techniques demonstrates promising performance improvements in code-smell detection, benefiting both software developers and researchers. Copyright © 2023, The Authors. All rights reserved.

关键词： computer software selection and evaluation

来源：评论

学校读者我要写书评

暂无评论

Exploiting Rank-Based Filter Pruning for Real-Time Uav Tracking

SSRN

引用

SSRN 2022年

作者： Wang, Xucheng Zeng, Dan Zhao, Qijun Li, Shuiwang Guangxi Key Laboratory of Embedded Technology and Intelligent System Guilin University of Technology Guilin541001 China Research Institute of Trustworthy Autonomous Systems Department of computer science and engineering Southern University of Science and Technology Shenzhen518000 China Sichuan University Chengdu610000 China

UAV tracking is an emerging task and has wide potential applications in such as agriculture, navigation, entertainment and public security. However, the limitations of computing resources, battery capacity, and maximum load of UAV hinder the deployment of DL-based tracking algorithms on UAV. In contrast to deep learning trackers, discriminative correlation filters (DCF)-based trackers stand out in the UAV tracking community because of their high efficiency. However, their precision is usually much lower than trackers based on deep learning. Model compression is a promising way to narrow the gap (i.e., effciency, precision) between DCF- and deep learning- based trackers, which has not caught much attention in UAV tracking community. In this paper, We propose the P-SiamFC++ tracker, which is the first to use rank-based filter pruning to compress the SiamFC++ model, achieving a remarkable balance between efficiency and precision. Our method is general and may encourage further studies on UAV tracking with model compression in the future. Extensive experiments on four UAV benchmarks, including UAV123@10fps, DTB70, UAVDT and Vistrone2018, show that P-SiamFC++ tracker significantly outperforms state-of-the-art UAV tracking methods. © 2022, The Authors. All rights reserved.

关键词： Unmanned aerial vehicles (UAV)

来源：评论

学校读者我要写书评

暂无评论

Consistency and Diversity induced Human Motion Segmentation

arXiv

引用

arXiv 2022年

作者： Zhou, Tao Fu, Huazhu Gong, Chen Shao, Ling Porikli, Fatih Ling, Haibin Shen, Jianbing The PCA Lab The Key Laboratory of Intelligent Perception and Systems for High-Dimensional Information Ministry of Education School of Computer Science and Engineering Nanjing University of Science and Technology Nanjing210094 China Institute of High Performance Computing Agency for Science Technology and Research Singapore Riyadh Saudi Arabia The Research School of Engineering The Australian National University Australia The Department of Computer Science Stony Brook University Strony Brook NY United States The State Key Laboratory of Internet of Things for Smart City Department of Computer and Information Science University United States

Subspace clustering is a classical technique that has been widely used for human motion segmentation and other related tasks. However, existing segmentation methods often cluster data without guidance from prior knowledge, resulting in unsatisfactory segmentation results. To this end, we propose a novel Consistency and Diversity induced human Motion Segmentation (CDMS) algorithm. Specifically, our model factorizes the source and target data into distinct multi-layer feature spaces, in which transfer subspace learning is conducted on different layers to capture multi-level information. A multi-mutual consistency learning strategy is carried out to reduce the domain gap between the source and target data. In this way, the domain-specific knowledge and domain-invariant properties can be explored simultaneously. Besides, a novel constraint based on the Hilbert Schmidt Independence Criterion (HSIC) is introduced to ensure the diversity of multi-level subspace representations, which enables the complementarity of multi-level representations to be explored to boost the transfer learning performance. Moreover, to preserve the temporal correlations, an enhanced graph regularizer is imposed on the learned representation coefficients and the multi-level representations of the source data. The proposed model can be efficiently solved using the Alternating Direction Method of Multipliers (ADMM) algorithm. Extensive experimental results on public human motion datasets demonstrate the effectiveness of our method against several state-of-the-art approaches. Copyright © 2022, The Authors. All rights reserved.

关键词： Motion analysis

来源：评论

学校读者我要写书评

暂无评论

Domain adaptive person re-identification via homogeneous hierarchical progressive adaptation and multi-view consistency

引用

Advanced engineering Informatics 2025年 67卷

作者： Zhengyang Wang Xiufen Ye Xue Shang Shuxiang Guo College of Intelligent Systems Science and Engineering Harbin Engineering University Harbin 150001 China Department of Electrical Computer and Software Engineering University of Auckland Auckland 1142 New Zealand Department of Electronic and Electrical Engineering Southern University of Science and Technology Shenzhen 518055 China

Domain adaptive person re-identification (Re-ID) encounters significant challenges when models trained on one dataset are deployed in new environments. It is particularly critical in engineering applications where surveillance infrastructure must be rapidly adapted to new environments without compromising security system reliability. The problem represents a knowledge-intensive engineering task that requires sophisticated knowledge representation and transfer mechanisms to support automated system reconfiguration decisions. These challenges include preserving fine-grained visual details, handling camera-specific variations, generating reliable pseudo-labels, maintaining consistency across multiple camera views, and managing varying difficulty levels in domain transfer. To address these issues, we propose a novel framework that separates adaptation into intra-domain and cross-domain learning phases. Our approach introduces several key innovations: an adaptive fine-grained network that preserves spatial details while ensuring domain invariance, a memory-guided learning method for stable feature representation, and a hierarchical adaptation strategy for reliable intra-domain learning. Additionally, we incorporate a progressive learning strategy for gradual domain adaptation and a consistency reinforcement mechanism to resolve cross-camera identity conflicts. Experiments on the Market-1501, DukeMTMC-reID, and MSMT17 datasets across four domain adaptation tasks show that our method outperforms state-of-the-art approaches, significantly improving both mAP and CMC accuracy. This work contributes to engineering informatics by providing a reliable solution for automating knowledge-intensive tasks across diverse engineering domains, while also laying the foundation for advancements in intelligent surveillance systems and automated decision-making in engineering infrastructures.

关键词： Automatic identification

来源：评论

学校读者我要写书评

暂无评论

Cross View Capture for Distributed Image Compression with Decoder Side Information

Cross View Capture for Distributed Image Compression with De...

引用

IEEE International Conference on Robotics and Automation (ICRA)

作者： Yankai Yin Zhe Sun Peiying Ruan Feng Duan Ruidong Li Chi Zhu Tianjin Key Laboratory of Interventional Brain-Computer Interface and Intelligent Rehabilitation Nankai University Tianjin China Institute of Natural Sciences Kanazawa University Ishikawa Japan Faculty of Health Data Science and Graduate School of Medicine Juntendo University Chiba Japan NVIDIA AI Technology Center NVIDIA Japan Tokyo Japan Department of Systems Life Engineering Maebashi Institute of Technology Maebashi Japan

ISBN: (数字)9798350384574

ISBN: (纸本)9798350384581

Image compression is increasingly important in applications like intelligent driving and smart surveillance systems. This study presents a novel cross view capture distributed image compression network (CVCDIC) to improve the compression quality by using decoder side information. The CVCDIC’s decoder utilizes feature extraction networks to extract features from both the primary image and the side information. Furthermore, a multi-level cross view attention module is designed to capture interrelated details between images at multiple hierarchical levels. Finally, a spatial refinement module, constructed on the foundation of information distillation networks, is designed to further refine the quality of reconstructed images. The results show that CVCDIC can achieve an MS-SSIM of 0.978 at 0.15 bpp, surpassing DSIN (0.925), NDIC (0.956), and ATN (0.955) on the KITTI Stereo dataset.

关键词： Measurement Image coding Fuses Surveillance Rate-distortion Feature extraction Decoding

来源：评论

学校读者我要写书评

暂无评论

Runtime Permission Issues in Android Apps: Taxonomy, Practices, and Ways Forward

arXiv

引用

arXiv 2021年

作者： Wang, Ying Wang, Yibo Wang, Sinan Liu, Yepang Xu, Chang Cheung, Shing-Chi Yu, Hai Zhu, Zhiliang The Software College Northeasthern University China The Department of Computer Science and Engineering Guangdong Provincial Key Laboratory of Brain-inspired Intelligent Computation Southern University of Science and Technology Shenzhen China The State Key Lab for Novel Software Technology The Department of Computer Science and Technology Nanjing University China The Department of Computer Science and Engineering The Hong Kong University of Science and Technology Hong Kong Hong Kong

Android introduces a new permission model that allows apps to request permissions at runtime rather than at the installation time since 6.0 (Marshmallow, API level 23). While this runtime permission model provides users with greater flexibility in controlling an app’s access to sensitive data and system features, it brings new challenges to app development. First, as users may grant or revoke permissions at any time while they are using an app, developers need to ensure that the app properly checks and requests required permissions before invoking any permission-protected APIs. Second, Android’s permission mechanism keeps evolving and getting customized by device manufacturers. Developers are expected to comprehensively test their apps on different Android versions and device models to make sure permissions are properly requested in all situations. Unfortunately, these requirements are often impractical for developers. In practice, many Android apps suffer from various runtime permission issues (ARP issues). While existing studies have explored ARP issues, the understanding of such issues is still preliminary. To better characterize ARP issues, we performed an empirical study using 135 Stack Overflow posts that discuss ARP issues and 199 real ARP issues archived in popular open-source Android projects on GitHub. Via analyzing the data, we observed 11 types of ARP issues that commonly occur in Android apps. For each type of issues, we systematically studied: (1) how they can be manifested, (2) how pervasive and serious they are in real-world apps, and (3) how they can be fixed. We also analyzed the evolution trend of different types of issues from 2015 to 2020 to understand their impact on the Android ecosystem. Furthermore, we conducted a field survey and in-depth interviews among practitioners, to gain insights from industrial practices and learn practitioners’ requirements of tools that can help combat ARP issues. Finally, to understand the strengths and weaknesse

关键词： Android (operating system)

来源：评论

学校读者我要写书评

暂无评论

Implicit Multi-Scale Swin Transformer Network for Image Denoising

引用

IEEE Transactions on Consumer Electronics 2025年

作者： Zhang, Qi Ding, Yuwei Zhang, Weiqi Zhu, Yian Zhang, Bob Lin, Jerry Chun-Wei Harbin Institute of Technology at Weihai School of Economics and Management Weihai China Nanjing University State Key Laboratory for Novel Software Technology Nanjing China Northwestern Polytechnical University School of Computer Science Xi’an China Northwestern Polytechnical University Yangtze River Delta Research Institute Taicang China University of Macau PAMI Research Group Department of Computer and Information Science Taipa China Department of Distributed Systems and IT Devices Electrical Engineering and Mathematical Sciences Silesian university of technology Poland

Image denoising has been used in various edge computing scenarios such as consumer electronics to improve the image quality and user experience. Existing image denoising methods based on Convolutional Neural Networks (CNNs) and vision Transformers achieve good performance by empirically utilizing residual neural network (ResNet) as basic component. However, ResNet lacks interpretability in network design and also long-term memory of features, potentially restricting the performance of denoising networks. In this paper, we propose an Implicit Multi-scale Swin Transformer Network (IMSNet) for image denoising, which introduces the implicit Euler scheme from the feature memory perspective. Specifically, densely connected implicit feature extraction blocks (IFEBs) are designed to learn the residual mapping between noisy and clean images. The IFEB reformulates the initial skip connection of ResNet based on the implicit Euler discretization, providing both network interpretability and long-term memory. In IFEB, the multi-scale swin Transformer block (MSB) is designed as the implicit layer to capture spatial details and non-local contextual information at different scales. Additionally, a cross-layer feature fusion block (CLFF) is proposed to further improve feature reuse capabilities. Compared to existing denoising networks, the extensive experiments demonstrate the superior performance of our IMSNet in various image denoising tasks, and the flexibility in the practical applications with proposed light model on resource-restricted platforms such as consumer electronic devices. © 1975-2011 IEEE.

关键词： Image denoising

来源：评论

学校读者我要写书评

暂无评论

Atomistic Behavior of Deformed Au Thin Film during the Indentation Process

Atomistic Behavior of Deformed Au Thin Film during the Inden...

引用

Innovative Research in Applied science, engineering and Technology (IRASET),Conference on

作者： Abdelkarim Ou-khouya Hassane Mes-adi Meryem Taoufiki Imane Ait Ibrahim Amin El Harfouf Rachid Herbazi Mohamed Tahiri Process Engineering Computer Science and Mathematics Laboratory Khouribga National School of Applied Sciences Sultan Moulay Slimane University Khouribga Morocco Faculty of Sciences and Techniques Sustainable Development Laboratory Sultan Moulay Slimane University Beni-Mellal Morocco Departement of Physics Laboratory of Condensed Matter and interdisciplinary Sciences CNRST Labeled Research Unit Faculty of Sciences Mohamed V University Rabat Morocco Department of Physics Polydisciplinary Faculty of Khouribga University of Sultan Moulay Slimane Khouribga Morocco Intelligent Systems and Applications Laboratory (LSIA) EMSI Tangier Morocco

ISBN: (数字)9798350309508

ISBN: (纸本)9798350309515

In this study, we investigate the mechanical properties of gold (Au) materials using molecular dynamics simulations. In this simulation, the nanoindentation process was performed to analyze the deformation defects and hardness properties of Au under different indentation velocities. The results suggest that the deformation behavior of the Au specimen was affected by different indentation velocities. These findings were confirmed by examining the load-displacement curve, which indicated elastic deformation through the appearance of a linear load-displacement relationship at low indentation velocities. In contrast, plastic deformation was identified by the presence of intensified serrations in the load-displacement curve at higher indentation velocities. Under such conditions, the hardness exhibited minimal variation when the indenter velocity increased from 5 mls to 10 mls. However, a significant increase in hardness was noted when the indentation velocity was further raised to 15 mls.

关键词： Deformable models Gold Analytical models Deformation Dynamics Plastics Load modeling

来源：评论

学校读者我要写书评

暂无评论

A Novel Motion Accumulation and Selection Network for Rgb-Based Action Recognition

SSRN

引用

SSRN 2022年

作者： Wang, Huafeng Li, Hanlin Liu, Wanquan Gu, Xianfeng School of Information Technology North China University of Technology Beijing China School of Software Beihang University Beijing China School of Intelligent Systems Engineering Sun Yat-sen University Guangzhou China Department of Computer Science Stony BrookNY11794-2424 United States

A large number of existing methods have demonstrated the significance of motion information for action recognition in video. In the literature, most of the previous methods rely heavily on the temporal differences of features extracted by convolutional networks (CNN) to represent the motion. However, this type of motion representation approach may have two potential drawbacks: 1) The difference operation may cause the incompleteness of the extracted moving target contour;2) Treating all the extracted motion features equally may lead to situations where some motion features will not contribute to the classification or even produce negative incentives. Inspired by the fact that the human eye is often a cumulative and selective process of visual attention when observing a video sequence, we propose a motion accumulation and selection network (MAS-Net) based on a novel embedded 2D CNN. According to the experimental results on typical video datasets such as Something-Something V1&V2 and Kinetics-400, it is shown that MAS-Net has achieved the state-of-the-arts on Something-Something V1&V2 and the competitive results on Kinetics-400, while the computational load is kept at a relatively low level. © 2022, The Authors. All rights reserved.

关键词： Motion estimation

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：