检索结果-内蒙古大学图书馆

IEEE Transactions on Artificial Intelligence 2025年第2期6卷 405-415页

作者： Cai, Zinuo Ma, Rongbo Fu, Yicheng Zhang, Weishan Ma, Ruhui Guan, Haibing Shanghai Jiao Tong University School of Electronic Information and Electrical Engineering Shanghai200240 China Qingdao Institute of Software College of Computer Science and Technology Qingdao266555 China

In recent years, the emergence of large-language models (LLMs) has profoundly transformed our production and lifestyle. These models have shown tremendous potential in fields, such as natural language processing, speech recognition, and recommendation systems, and are increasingly playing crucial roles in applications such as human-computer interaction and intelligent customer service. Efficient inference solutions for LLMs in data centers have been extensively researched, with a focus on meeting users' quality of service requirements. In this article, we focus on two additional requirements that responsible LLM inference should meet under QoS conditions: security throughout the model execution process and low maintenance requirements for the inference system. Therefore, we propose LLMaaS, a trusted model inference platform based on a serverless computing platform aimed at providing inference as a service for LLMs. First, we design a trusted serverless computing platform based on software guard extension (SGX), which includes distributed identity verification and SGX device plugins to ensure the security and trustworthiness of the inference process. Additionally, to reduce the maintenance requirements of the system, we enhance the SGX-based deep learning computing framework, including replacing PyTorch and using a greedy algorithm for graph partitioning. We conduct tests on four typical large models, and the experimental results demonstrate that, with minimal overhead and user code modifications, we can ensure the security of model execution. © 2020 IEEE.

关键词： Quality of service

来源：评论

学校读者我要写书评

暂无评论

Uncertainty-aware Correspondence Distillation for Deep Image Clustering

Uncertainty-aware Correspondence Distillation for Deep Image...

引用

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

作者： Chang, Luyao Chen, Leiting Zhou, Chuan School of Information and Software Engineering University of Electronic Science and Technology of China Chengdu China

ISBN: (纸本)9798350368741

Image clustering is a challenging task in computer vision, with performance heavily dependent on the quality of feature representations due to the inherent complexity of images. However, current image clustering methods overlook the underlying semantic information during representation learning, leading to low-quality feature representations. Moreover, the absence of ground-truth labels amplifies the detrimental effects of unreliable data on semantic guidance, steering the model towards incorrect learning directions. In this work, we propose a novel deep image clustering method named Uncertainty-aware Correspondence Distillation (UCD) to address these issues. Specifically, we introduce the concept of representation correspondence to establish cross-level connections between instances and semantics, which is further employed as a distillation target to improve the network's feature learning by complementing semantic information. To mitigate unnecessary similarity penalties arising from unreliable data, we develop robust dynamic weights for semantic guidance by modeling the uncertainty of image semantics. Extensive experiments on five benchmark datasets demonstrate the superiority of the proposed method. The code is available at https://***/YL616/UCD. © 2025 IEEE.

关键词： Image clustering Knowledge distillation Representation learning Semantic guidance

来源：评论

学校读者我要写书评

暂无评论

YGC-SLAM:A visual SLAM based on improved YOLOv5 and geometric constraints for dynamic indoor environments

引用

虚拟现实与智能硬件(中英文) 2025年第1期7卷 62-82页

作者： Juncheng ZHANG Fuyang KE Qinqin TANG Wenming YU Ming ZHANG Department of Automation University of Information Science&TechnologyNanjing 210044China Department of Software University of Information Science&TechnologyNanjing 210044China Wuxi Research Institute of Nanjing University of Information Engineering Wuxi 214101China Department of Rail Transport University of WuxiWuxi 214101China

Background As visual simultaneous localization and mapping(SLAM)is primarily based on the assumption of a static scene,the presence of dynamic objects in the frame causes problems such as a deterioration of system robustness and inaccurate position *** this study,we propose a YGC-SLAM for indoor dynamic environments based on the ORB-SLAM2 framework combined with semantic and geometric constraints to improve the positioning accuracy and robustness of the *** First,the recognition accuracy of YOLOv5 was improved by introducing the convolution block attention model and the improved EIOU loss function,whereby the prediction frame converges quickly for better *** improved YOLOv5 was then added to the tracking thread for dynamic target detection to eliminate dynamic ***,multi-view geometric constraints were used for re-judging to further eliminate dynamic points while enabling more useful feature points to be retained and preventing the semantic approach from over-eliminating feature points,causing a failure of map *** K-means clustering algorithm was used to accelerate this process and quickly calculate and determine the motion state of each cluster of pixel ***,a strategy for drawing keyframes with de-redundancy was implemented to construct a clear 3D dense static point-cloud *** Through testing on TUM dataset and a real environment,the experimental results show that our algorithm reduces the absolute trajectory error by 98.22%and the relative trajectory error by 97.98%compared with the original ORBSLAM2,which is more accurate and has better real-time performance than similar algorithms,such as DynaSLAM and *** The YGC-SLAM proposed in this study can effectively eliminate the adverse effects of dynamic objects,and the system can better complete positioning and map building tasks in complex environments.

关键词： Visual SLAM Dynamic SLAM Target detection Geometric constraints

来源：评论

学校读者我要写书评

暂无评论

Fairness-Aware Budgeted Edge Server Placement for Connected Autonomous Vehicles

引用

IEEE Transactions on Mobile Computing 2025年第6期24卷 4762-4776页

作者： Wu, Jintao Xu, Xiaolong Cui, Guangming Zhang, Yiwen Qi, Lianyong Dou, Wanchun Cai, Zhipeng Nanjing University of Information Science & Technology Jiangsu Province Engineering Research Center of Advanced Computing and Intelligent Services School of Software Nanjing210044 China Jilin University Key Laboratory of Symbolic Computation and Knowledge Engineering of Ministry of Education Changchun130012 China Nanjing University of Information Science & Technology Jiangsu Province Engineering Research Center of Advanced Computing and Intelligent Services School of Software China Nanjing University State Key Laboratory for Novel Software Technology China Anhui University School of Computer Science and Technology Anhui230031 China College of Computer Science and Technology Qingdao266580 China Nanjing University State Key Laboratory for Novel Software Technology Nanjing210023 China Georgia State University Department of Computer Science United States

Mobile edge computing (MEC) considerably enhances the capabilities and performance of connected autonomous vehicles (CAVs) by deploying edge servers (ESs) on roadside units (RSUs) near CAVs, thereby ensuring low-latency services. Given the constrained and costly nature of ES resources (computing, storage, and bandwidth), equitable ES utilization is critical for CAV operations. However, fairness considerations are often overlooked in current budgeted edge server placement (ESP) strategies, potentially worsening resource imbalances and compromising user experience. This paper investigates the fairness-aware budgeted edge server placement (FESP) problem within RSUs, proving its NP-hardness. To address FESP, we first propose FESP-O, an integer programming-based optimal approach for small-scale problems, followed by FESP-APX, an approximation approach for large-scale scenarios that provides near-optimal solutions. We analyze the time complexity and approximation ratio of our proposed algorithms and validate their efficacy through experiments on real-world datasets. Extensive experimental results demonstrate significant performance improvements over baseline and state-of-the-art methods, indicating practical suitability and efficiency. © 2002-2012 IEEE.

关键词： Integer linear programming

来源：评论

学校读者我要写书评

暂无评论

ViF-SD2E: a robust weakly-supervised framework for neural decoding

引用

Neural Computing and Applications 2025年第9期37卷 6645-6661页

作者： Feng, Jingyi Luo, Yong Song, Shuang Hu, Han National Engineering Research Center for Multimedia Software School of Computer Science Wuhan University Wuhan430072 China School of Information and Electronics Beijing Institute of Technology Beijing100081 China

Neural decoding plays a vital role in the interaction between the brain and the outside world. Our task in this paper is to decode the movement track of a finger directly based on the neural data. Existing neural decoding solutions primarily perform some preprocessing operations on neural data before feeding them into existing models (such as LSTM) for decoding. However, these solutions either are prone to overfitting or cannot well exploit the spatial and temporal information. In our previous observations, there is a symmetrical phenomenon between the unsupervised decoded trajectory and the ground truth trajectory within the activity space. This precisely motivates us to propose (or derive) a robust weakly-supervised framework (or model structure), called ViF-SD2E, for neural decoding. In particular, it consists of a space-division (SD) module and an exploration–exploitation (2E) strategy, to effectively exploit both the spatial information of the outside world and the temporal information of neural activity, where the SD2E output is analogized with the weak 0/1 vision feedback (ViF) label for training. Extensive experiments demonstrate the effectiveness of our method, which can sometimes be comparable to supervised counterparts. Therefore, we redirect our attention to the information (hidden in data) ViF-SD2E conveys to us. In other words, we believe that the advantage of ViF-SD2E lies in the fact that its processing steps are objectively determined by the inherent attributes (i.e., symmetry) of the neural data, or rather, the model structure is fixed. © The Author(s), under exclusive licence to Springer-Verlag London Ltd., part of Springer Nature 2025.

关键词： Space division multiple access

来源：评论

学校读者我要写书评

暂无评论

Joint classification of hyperspectral and lidar using multi-scale spatial adaptive calibration 6

Joint classification of hyperspectral and lidar using multi-...

引用

6th International Conference on Geoscience and Remote Sensing Mapping, GRSM 2024

作者： Yang, Zhichao Hao, Siyuan Qingdao University of Technology College of information and control engineering Qingdao China Beijing Jiaotong University College of software engineering Beijing China

ISBN: (纸本)9781510688018

In the field of land cover classification, the multimodal fusion of hyperspectral imagery (HSI) and light detection and ranging (LiDAR) data has become a key research direction in remote sensing. Hyperspectral imagery provides rich spectral information, enabling the identification of subtle material differences, while LiDAR data offers high-precision spatial geometric structures. However, the complementarity between these two data modalities faces challenges related to spatial resolution discrepancies and feature inconsistency. To address these challenges, this paper proposes a Multiscale Spatial Adaptive Calibration Network (MSACNet) for joint classification of hyperspectral and LiDAR data. The network extracts multiscale convolutional features and introduces a Spatial Adaptive Calibration Module (SACM) at each scale to adaptively calibrate the fused multimodal features, adjusting for discrepancies between spectral and spatial geometric feature distributions. Experimental results on the Houston2013 dataset demonstrate that the proposed method achieves superior classification performance compared to existing classification models. © 2025 SPIE.

关键词： Image resolution

来源：评论

学校读者我要写书评

暂无评论

Blockchain-enabled IoT access control model for sharing electronic healthcare data

引用

Multimedia Tools and Applications 2025年第10期84卷 8127-8148页

作者： Ilyas, Benkhaddra Kumar, Abhishek Ali, Setitra Mohamed Lei, Hang School of Information and Software Engineering University of Electronic Science and Technology of China Chengdu610054 China Chandigarh University Gharuan Mohali Punjab140413 India School of Computer Science and Engineering University of Electronic Science and Technology of China Sichuan Chengdu611731 China

Deploying the Internet of Things (IoT) in the transfer of enormous medical data often promotes challenges with the security, confidentiality, and privacy of the user’s sensitive data. In addition, the access control for prohibiting unauthorized access has been facing challenges with single-point-of-failure, collusion, and other security issues. To address these challenges associated with IoT access control, this research proposes a Blockchain-enabled IoT access control for sharing Electronic health records (EHR). The proposed authentic access control scheme transfers the data to the authenticated user without discrepancies. The proposed technique utilizes the hyperledger composer fabric blockchain that improves the transparency and traceability of the network, and the intelligent contract keeps track of the information, which reduces the possibility of unauthorized access. The proposed access control scheme validates the request effectively and transmits the data efficiently. The effectiveness of the proposed access control scheme is evaluated by analyzing the blocks in terms of metrics such as responsiveness of 185.47 secs, 95% Genuine User Detection (GUD), 96.50% Privacy, and 3.50% information loss, for 100 blocks and proposed access control scheme works more efficiently in transmitting the data. © The Author(s), under exclusive licence to Springer Science+Business Media, LLC, part of Springer Nature 2024.

关键词： Smart contract

来源：评论

学校读者我要写书评

暂无评论

RSM: Refined Saliency Map For Explainable 3D Object Tracking

RSM: Refined Saliency Map For Explainable 3D Object Tracking

引用

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

作者： Cheng, Riran Wang, Xupeng Sohel, Ferdous Lei, Hang School of Information and Software Engineering University of Electronic Science and Technology of China Chengdu China School of Information Technology Murdoch University Murdoch Australia

ISBN: (纸本)9798350368741

Saliency maps play a major role in understanding the decision-making process of 3D models by illustrating the importance of individual points from the input to model predictions. However, saliency maps typically suffer from inaccuracies due to not considering the potential classification of contributions made by a point. In this paper, a two-stage explainability method for 3D object tracking is proposed to generate a refined saliency map (RSM), which refines the contributions of points to positive and negative based on their actual effects on tracking performances. Specifically, in stage I, a point-wise growing downsampling algorithm is developed to generate subsets of the search area, under which the model's behavior is evaluated to precisely identify the points with negative contributions. Subsequently, a voxel-wise downsampling algorithm is performed along with the deviation metric to select points with positive contributions in stage II. Experiments demonstrate that RSM can generate high-quality explanations to popular 3D trackers. © 2025 IEEE.

关键词： 3D object tracking negative contribution positive contribution saliency map

来源：评论

学校读者我要写书评

暂无评论

Superpoints Guided Local Explanation For Deep 3D Trackers

Superpoints Guided Local Explanation For Deep 3D Trackers

引用

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

ISBN: (纸本)9798350368741

3D object tracking has become a popular research topic because of its broad application prospects. However, it remains a challenging task to advance the trustworthiness of deep trackers, caused by the complex network structure of black-box models. In this paper, a local explanation method for 3D object tracking is proposed, which trains an interpretable surrogate model to reveal the contribution of superpoints in the search area. Specifically, local points of the search area with comparable geometric features are aggregated as superpoints, which serve as the fundamentals of the explanation. In contrast to the commonly used voxels, superpoints capture semantic information of the search area, and facilitate an intuitive understanding of the predictions. In addition, a distance-aware masking strategy is proposed for generating the sample set to train a surrogate model, which corresponds to latent contributions of superpoints to predictions and improves the efficacy of the explanation. Experiments have demonstrated that the proposed explainability approach can effectively provide explanations to deep tracking models. © 2025 IEEE.

关键词： 3D object tracking local explainability method surrogate model

来源：评论

学校读者我要写书评

暂无评论

Integrated Communication and Control for Intelligent Formation Management of AAV Swarms: A Deep Reinforcement Learning Approach

引用

IEEE Wireless Communications Letters 2025年第5期14卷 1351-1355页

作者： Wei, Jiangting Zhao, Yizhe Yang, Kun Quzhou324000 China Nanjing University State Key Laboratory of Novel Software Technology Nanjing210008 China University of Electronic Science and Technology of China School of Information and Communication Engineering Chengdu611731 China

Thanks to the comprehensive ability of information collection, integration and processing, autonomous aerial vehicles (AAV) swarm is playing a crucial role for remote monitoring or task executing in various fields. In this letter, the formation management of AAV swarms is studied with the aid of integrated communication and control (ICAC), where the leading AAV is responsible for controlling the following AAVs wirelessly in order to achieve the desired flight states. The real-time control signals' generation, subcarrier, allocation, and data rate optimization are obtained with the aid of the deep deterministic policy gradient (DDPG) algorithm, by avoiding the potential collisions among AAVs. Simulation results demonstrate that our scheme is able to not only ensures collision avoidance but also reduce the control mean maximum square error (MMSE) with a better convergence compared to other benchmarks. © 2012 IEEE.

关键词： Deep reinforcement learning

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：