检索结果-内蒙古大学图书馆

computer engineering and Intelligent Control (ICCEIC) International Conference on

作者： Hao Sun Xiaoyan Qiao Yantai Key Laboratory of Big Data Modeling and Intelligent Computing Immersion School of Computer Science and Technology Shandong Technology and Business University Technology and Evaluation Shandong Engineering Research Center Yantai Shandong

ISBN: (数字)9798331507992

ISBN: (纸本)9798331508005

In the image restoration task, how to make full use of spatial and channel feature information to improve the reconstruction quality of the model without significantly increasing the computational complexity is an important research issue. To address this challenge, this paper proposes a CS module (Channel Compression and Split-Attention) specifically for optimizing image denoising tasks. The module first compresses the features through a preliminary convolution operation, then introduces the split attention convolution mechanism to split the features by channel and dynamically weight them, thereby enhancing the model's adaptive attention to different feature channels and improving feature expression capabilities. Through experiments on multiple image denoising datasets, the results show that the CS module significantly improves the image reconstruction quality, especially in terms of peak signal-to-noise ratio (PSNR). At the same time, the introduction of the CS module does not lead to a significant increase in computational complexity, maintaining a high computational efficiency, which verifies the practicality and superiority of the module in image denoising tasks.

关键词： Image coding PSNR Convolution Computational modeling Refining Image restoration Computational efficiency Computational complexity Image reconstruction Image denoising

来源：评论

学校读者我要写书评

暂无评论

Scalable Federated Learning for Fingerprint Recognition Algorithm

Scalable Federated Learning for Fingerprint Recognition Algo...

引用

IEEE International Conference on Trust, Security and Privacy in Computing and Communications (TrustCom)

作者： Chenzhuo Wang Yanrong Lu Athanasios V. Vasilakos School of Computer Science and Technology Civil Aviation University of China Tianjin China School of Safety Science and Engineering Civil Aviation University of China Tianjin China Center for AI Research University of Agder Grimstad Norway

ISBN: (数字)9798350381993

ISBN: (纸本)9798350382006

Fingerprint recognition technology is widely used in various terminal devices and serves as a powerful and effective method for authentication. Existing research relies on centralized training models based on datasets, overlooking the privacy and heterogeneity of the data itself, resulting in the leakage of user information and decreased recognition accuracy. In order to solve the problem of data security and privacy protection, this paper proposes a federated learning-based architecture called FedFR(Federated Learning-Fingerprint Recognition). The parameters from each endpoint are iteratively aggregated through federated learning to improve the performance of the global model under privacy constraints. Moreover, to solve the client-side unfairness issue in traditional federated learning caused by randomly selecting aggregation weights, a client selection method based on reservoir sampling is proposed, increasing the diversity of data distribution. Using the real-world databses, the effectiveness of FedFR is compared and analyzed through simulation experiments. The results show that FedFR exhibits good performance in terms of privacy protection levels, evaluation accuracy, and scalability. Distinct from traditional fingerprint recognition algorithms, FedFR improves the security and scalability of the model from the data source, providing a reference for the application of federated learning in biometric technology.

关键词： Training Privacy data privacy Federated learning Scalability Soft sensors Fingerprint recognition

来源：评论

学校读者我要写书评

暂无评论

AccelES: Accelerating Top-K SpMV for Embedding Similarity via Low-bit Pruning

AccelES: Accelerating Top-K SpMV for Embedding Similarity vi...

引用

IEEE Symposium on High-Performance computer Architecture

作者： Jiaqi Zhai Xuanhua Shi Kaiyi Huang Chencheng Ye Weifang Hu Bingsheng He Hai Jin National Engineering Research Center for Big Data Technology and System/Services Computing Technology and System Lab/Cluster and Grid Computing Lab School of Computer Science and Technology Huazhong University of Science and Technology Wuhan China School of Computing National University of Singapore Singapore

ISBN: (数字)9798331506476

ISBN: (纸本)9798331506483

In the realm of recommendation systems, achieving real-time performance in embedding similarity tasks is often hindered by the limitations of traditional Top-K sparse matrix-vector multiplication (SpMV) methods, which suffer from high latency due to inefficient memory access patterns. This paper identifies these critical gaps and introduces AccelES, a novel approach that significantly enhances the efficiency of Top-K SpMV. Our method employs a two-stage calculation scheme: the first stage utilizes a compact, low-bit dataset to quickly identify the most relevant entries, while the second stage performs full-precision calculations solely on this pruned subset, thereby minimizing computational overhead. Furthermore, AccelES incorporates innovative matrix representations, Ultra-CSR and Random-CSR, which optimize memory bandwidth utilization. Experimental results demonstrate that AccelES accelerates performance, surpassing state-of-the-art FPGA, GPU, and CPU solutions by factors of 3.4×, 2.5×, and 153.3×, respectively, under controlled conditions. These advancements not only enhance processing speed but also significantly improve real-time performance in recommendation systems, establishing AccelES as a pivotal contribution to the field of Top-K sparse matrix-vector multiplication.

关键词： Quantization (signal) High dimensional data Memory management Graphics processing units Bandwidth Real-time systems Sparse matrices Recommender systems Field programmable gate arrays Optimization

来源：评论

学校读者我要写书评

暂无评论

Hard-Label Black-Box Attacks on 3D Point Clouds

arXiv

引用

arXiv 2024年

作者： Liu, Daizong Tao, Yunbo Zhou, Pan Hu, Wei Wangxuan Institute of Computer Technology Peking University No. 128 Zhongguancun North Street Beijing China The Hubei Engineering Research Center on Big Data Security School of Cyber Science and Engineering Huazhong University of Science and Technology Wuhan430074 China

With the maturity of depth sensors in various 3D safety-critical applications, 3D point cloud models have been shown to be vulnerable to adversarial attacks. Almost all existing 3D attackers simply follow the white-box or black-box setting to iteratively update coordinate perturbations based on back-propagated or estimated gradients. However, these methods are hard to deploy in real-world scenarios (no model details are provided) as they severely rely on parameters or output logits of victim models. To this end, we propose point cloud attacks from a more practical setting, i.e., hard-label black-box attack, in which attackers can only access the prediction label of 3D input. We introduce a novel 3D attack method based on a new spectrum-aware decision boundary algorithm to generate high-quality adversarial samples. In particular, we first construct a class-aware model decision boundary, by developing a learnable spectrum-fusion strategy to adaptively fuse point clouds of different classes in the spectral domain, aiming to craft their intermediate samples without distorting the original geometry. Then, we devise an iterative coordinate-spectrum optimization method with curvature-aware boundary search to move the intermediate sample along the decision boundary for generating adversarial point clouds with trivial perturbations. Experiments demonstrate that our attack competitively outperforms existing white/black-box attackers in terms of attack performance and adversary quality. Copyright © 2024, The Authors. All rights reserved.

关键词： Digital elevation model

来源：评论

学校读者我要写书评

暂无评论

Semantic-Based Heterogeneous Controller Collaboration for Space-Terrestrial Integrated Networks 23

Semantic-Based Heterogeneous Controller Collaboration for Sp...

引用

23rd IEEE International Conference on High Performance Computing and Communications, 7th IEEE International Conference on data science and Systems, 19th IEEE International Conference on Smart City and 7th IEEE International Conference on Dependability in Sensor, Cloud and Big data Systems and Applications, HPCC-DSS-SmartCity-DependSys 2021

作者： Bao, Yaru Tang, Feilong Li, Xu Chen, Long Liu, Jiacheng Yang, Yanqin Xu, Wenchao Cao, Lijun Han, Ping Shanghai Jiao Tong University Department of Computer Science & Engineering China School of Data Science & Engineering East China Normal University China School of Communication & Electronic Engineering East China Normal University China Innovation Resource Center Kedacom Co. Ltd China The Sci-Tech Information Office of Xuzhou Public Security Bureau China

ISBN: (纸本)9781665494571

In heterogeneous SDN networks, controllers deploying different protocols need to cooperate with each other and establish a global network view that can be passed to the network applications for unified management and end-to-end decision-making. Unfortunately, there is no standard northbound interface protocol to integrate heterogeneous SDN controllers. To address this issue in this paper, we propose an approach to find the mapping among controller ontologies in the SDN network with heterogeneous controllers in this paper. We regard these controller ontologies as a solution for discovering similar elements between local ontologies and global ontology. By mapping controller ontologies in the heterogeneous network together, we can form the complete network view to achieve centralized management. The idea behind the approach is to use ontology to represent the conceptual data of various heterogeneous controllers and then map similar semantic data together to form a consistent, global network knowledge. Evaluation results show that our approach has better accuracy than other algorithms and has an acceptable execution time. © 2021 IEEE.

关键词： Knowledge engineering Satellites Protocols Semantics Decision making Collaboration Ontologies

来源：评论

学校读者我要写书评

暂无评论

data Partition Optimization for High Energy Efficiency by Decoupling Local Dependence in Holographic Video Decoder 30

Data Partition Optimization for High Energy Efficiency by De...

引用

30th IEEE International Conference on Electronics, Circuits and Systems, ICECS 2023

作者： Liu, Xinzhe Luo, Jianwen Blinder, David Chen, Fupeng Yu, Heng Schelkens, Peter Catthoor, Francky Ha, Yajun ShanghaiTech University School of Information Science and Technology Shanghai China Shanghai Institute of Microsystem and Information Technology Chinese Academy of Sciences China University of Chinese Academy of Sciences China Belgium Leuven Belgium Silicon Realization Group Synopsys Shanghai China University of Nottingham Ningbo China School of Computer Science Ningbo China Leuven Belgium Shanghai Engineering Research Center of Energy Efficient and Custom AI IC Shanghai China

ISBN: (纸本)9798350326499

Holography has attracted considerable attention from researchers due to its ability to store and recreate the wavefront emanating from a three-dimensional object. However, holographic video requires enormous resolution (128 k × 128 k) at the same frame rates(60fps) as normal video to achieve acceptable visual effects. data compression is thus essential for its storage/transmission. When implementing its decompression pipeline on hardware for mobile scenarios, data dependency and energy consumption must be handled carefully. In this work, we present a novel design framework and a data partition optimization approach to optimize the overall energy consumption by tackling local dependence in the motion compensation module for holographic video codec, and exploring the design space of data partition layout. First, we propose a local data dependency propagation (LDDP) method that transforms one holographic frame with strong local dependence into multiple mutually independent virtual blocks without local dependence at all. Second, we formulate a model for the data partitioning problem, allowing us to analyze and optimize energy consumption by adjusting the layout of data partitions. Third, we provide a heuristic and efficient solution to the formulated model taking advantage of the target application scenarios. Experiment results in various scenarios show that our proposed optimization method achieves 2.94 3.91 × energy efficiency and 46.37% 63.63% area efficiency compared to baseline approaches. © 2023 IEEE.

关键词： Energy utilization

来源：评论

学校读者我要写书评

暂无评论

HYPERBOLIC HYPERGRAPH NEURAL NETWORKS FOR MULTI-RELATIONAL KNOWLEDGE HYPERGRAPH REPRESENTATION

arXiv

引用

arXiv 2024年

作者： Li, Mengfan Shi, Xuanhua Qiao, Chenqi Zhang, Teng Jin, Hai National Engineering Research Center for Big Data Technology and System Services Computing Technology and System Lab Cluster and Grid Computing Lab School of Computer Science and Technology Huazhong University of Science and Technology Wuhan430074 China

Knowledge hypergraphs generalize knowledge graphs using hyperedges to connect multiple entities and depict complicated relations. Existing methods either transform hyperedges into an easier-to-handle set of binary relations or view hyperedges as isolated and ignore their adjacencies. Both approaches have information loss and may potentially lead to the creation of sub-optimal models. To fix these issues, we propose the Hyperbolic Hypergraph Neural Network (H2GNN), whose essential component is the hyper-star message passing, a novel scheme motivated by a lossless expansion of hyperedges into hierarchies. It implements a direct embedding that consciously incorporates adjacent entities, hyper-relations, and entity position-aware information. As the name suggests, H2GNN operates in the hyperbolic space, which is more adept at capturing the tree-like hierarchy. We compare H2GNN with 15 baselines on knowledge hypergraphs, and it outperforms state-of-the-art approaches in both node classification and link prediction tasks. Copyright © 2024, The Authors. All rights reserved.

关键词： Knowledge graph

来源：评论

学校读者我要写书评

暂无评论

Multi-agent Traffic Prediction via Denoised Endpoint Distribution

Multi-agent Traffic Prediction via Denoised Endpoint Distrib...

引用

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

作者： Yao Liu Ruoyu Wang Yuanjiang Cao Quan Z. Sheng Lina Yao Key Laboratory of Intelligent Computing in Medical Image Ministry of Education Northeastern University Shenyang China School of Computer Science and Engineering Northeastern University Shenyang China National Frontiers Science Center for Industrial Intelligence and Systems Optimization Shenyang China School of Computing Macquarie University Sydney Australia School of Computer Science and Engineering University of New South Wales Sydney Australia Data 61 CSIRO & School of Computer Science and Engineering University of New South Wales Sydney Australia

ISBN: (数字)9798350377705

ISBN: (纸本)9798350377712

The exploration of high-speed movement by robots or road traffic agents is crucial for autonomous driving and navigation. Trajectory prediction at high speeds requires considering historical features and interactions with surrounding entities, a complexity not as pronounced in lower-speed environments. Prior methods have assessed the spatiotemporal dynamics of agents but often neglected intrinsic intent and uncertainty, thereby limiting their effectiveness. We present the Denoised Endpoint Distribution model for trajectory prediction, which distinctively models agents’ spatio-temporal features alongside their intrinsic intentions and un-certainties. By employing Diffusion and Transformer models to focus on agent endpoints rather than entire trajectories, our approach significantly reduces model complexity and enhances performance through endpoint information. Our experiments on open datasets, coupled with comparison and ablation studies, demonstrate our model’s efficacy and the importance of its components. This approach advances trajectory prediction in high-speed scenarios and lays groundwork for future developments.

关键词： Uncertainty Navigation Soft sensors Robot kinematics Predictive models Transformers Road traffic Trajectory Complexity theory Spatiotemporal phenomena

来源：评论

学校读者我要写书评

暂无评论

End-to-End Design of Webtoon-Style Portrait Stylization System for Real-World Demo Booth

引用

IEEE Access 2025年 13卷 102180-102193页

作者： Sojeong Kim Bong-Soo Sohn Jaesung Lee Department of Artificial Intelligence Chung-Ang University Dongjak-gu Seoul Republic of Korea School of Computer Science and Engineering Chung-Ang University Dongjak-gu Seoul Republic of Korea AI/ML Innovation Research Center Chung-Ang University Dongjak-gu Seoul Republic of Korea

Webtoon-style portrait stylization has gained prominence across various fields, including social media, virtual characters, and the Metaverse, with significant applications in demo booths for real-time audience interaction. However, achieving high-quality, real-time stylizations presents challenges, such as preserving facial identity while maintaining the webtoon aesthetics and ensuring robustness to diverse inputs. This study explores diffusion-based generative models for webtoon-style portrait stylization, focusing on real-world scenarios such as demo booths. We address challenges such as artifact reduction and adaptability to varying inputs, showcasing the potential of diffusion models to enhance interactive and artistic applications, particularly in demo booth settings.

关键词： Real-time systems Visualization Image restoration Diffusion models Electronic mail Adaptation models Semantics Robustness Image synthesis Image edge detection

来源：评论

学校读者我要写书评

暂无评论

DPMAC: Differentially Private Communication for Cooperative Multi-Agent Reinforcement Learning

arXiv

引用

arXiv 2023年

作者： Zhao, Canzhe Ze, Yanjie Dong, Jing Wang, Baoxiang Li, Shuai John Hopcroft Center for Computer Science Shanghai Jiao Tong University China Department of Computer Science and Engineering Shanghai Jiao Tong University China School of Data Science The Chinese University of Hong Kong Shenzhen China

Communication lays the foundation for cooperation in human society and in multi-agent reinforcement learning (MARL). Humans also desire to maintain their privacy when communicating with others, yet such privacy concern has not been considered in existing works in MARL. To this end, we propose the differentially private multi-agent communication (DPMAC) algorithm, which protects the sensitive information of individual agents by equipping each agent with a local message sender with rigorous (ϵ, δ)-differential privacy (DP) guarantee. In contrast to directly perturbing the messages with predefined DP noise as commonly done in privacy-preserving scenarios, we adopt a stochastic message sender for each agent respectively and incorporate the DP requirement into the sender, which automatically adjusts the learned message distribution to alleviate the instability caused by DP noise. Further, we prove the existence of a Nash equilibrium in cooperative MARL with privacy-preserving communication, which suggests that this problem is game-theoretically learnable. Extensive experiments demonstrate a clear advantage of DPMAC over baseline methods in privacy-preserving scenarios. Copyright © 2023, The Authors. All rights reserved.

关键词： Stochastic systems

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：