检索结果-内蒙古大学图书馆

arXiv 2024年

作者： Du, Bowei Liao, Zhixuan Zhang, Yanan Cai, Zhi Chen, Jiaxin Huang, Di State Key Laboratory of Software Development Environment Beihang University Beijing China School of Computer Science and Engineering Beihang University Beijing China Hangzhou Innovation Institute Beihang University Hangzhou China

Developing accurate and efficient detectors for drone imagery is challenging due to the inherent complexity of aerial scenes. While some existing methods aim to achieve high accuracy by utilizing larger models, their computational cost is prohibitive for drones. Recently, Knowledge Distillation (KD) has shown promising potential for maintaining satisfactory accuracy while significantly compressing models in general object detection. Considering the advantages of KD, this paper presents the first attempt to adapt it to object detection on drone imagery and addresses two intrinsic issues: (1) low foreground-background ratio and (2) small instances and complex backgrounds, which lead to inadequate training, resulting insufficient distillation. Therefore, we propose a task-wise Lightweight Mutual Lifting (Light-ML) module with a Centerness-based Instance-aware Distillation (CID) strategy. The Light-ML module mutually harmonizes the classification and localization branches by channel shuffling and convolution, integrating teacher supervision across different tasks during back-propagation, thus facilitating training the student model. The CID strategy extracts valuable regions surrounding instances through the centerness of proposals, enhancing distillation efficacy. Experiments on the VisDrone, UAVDT, and COCO benchmarks demonstrate that the proposed approach promotes the accuracies of existing state-ofthe- art KD methods with comparable computational requirements. Codes will be available upon acceptance. Copyright © 2024, The Authors. All rights reserved.

关键词： Drones

来源：评论

学校读者我要写书评

暂无评论

JKT: A joint graph convolutional network based Deep Knowledge Tracing

引用

INFORMATION SCIENCES 2021年 580卷 510-523页

作者： Song, Xiangyu Li, Jianxin Tang, Yifu Zhao, Taige Chen, Yunliang Guan, Ziyu [a]School of IT Faculty of Science Engineering and Built Environment Deakin University Geelong VIC 3220 Australia [b]China University of Geosciences China [c]State Key Lab of ISN School of Computer Science and Technology Xidian University Xi’an China

Knowledge Tracing (KT) aims to trace the student's state of evolutionary mastery for a particular knowledge or concept based on the student's historical learning interactions with the corresponding exercises. Taking the "exercise-to-concept" relationships as input, several existing methods have been developed to trace and model students' mastery states. However, these studies face two major shortcomings in KT: 1) they only consider "exercise-to-concept" relationships;2) the multi-hot embeddings lack interpretability. In order to address the above issues, we propose a Joint graph convolutional network based deep Knowledge Tracing (JKT) framework to model the multi-dimensional relationships of "exercise-to-exercise", and "concept-to-concept" into graph and fuse them with "exercise-to-concept" relationships. In JKT, it is not only possible to establish connections between exercises under cross-concepts, but also to help capture high-level semantic information and increase the model's interpretability. In addition, sufficient experiments conducted on four real-world datasets have demonstrated that JKT performs better than the other baseline models. We further illustrate a case study to demonstrate its interpretability for learning analysis (c) 2021 Elsevier Inc. All rights reserved.

关键词： Knowledge Tracing Graph neural network Learning analytics Intelligent tutoring systems Network representation learning

来源：评论

学校读者我要写书评

暂无评论

Bridging Trajectory-Aware Evolutionary Graph Learning and Large Language Models for Enhancing Navigability in Social Internet of Things

引用

IEEE Internet of Things Journal 2025年

作者： Bi, Xin Han, Zhubin Yao, Xin Zhao, Xiangguo Wang, Yu-Ping Yuan, Ye State Key Laboratory of Intelligent Deep Metal Mining and Equipment China Northeastern University School of Computer Science and Engineering Shenyang110819 China Northeastern University College of Software Shenyang110819 China Beijing Institute of Technology School of Computer Science and Technology Beijing100091 China

Social Internet of Things (SIoT) has emerged as a novel paradigm that enhances IoT service capabilities by leveraging device-level social relationships. However, the explosive growth of heterogeneous devices, the dynamic mobile device trajectories, and complex spatiotemporal interaction patterns severely hinder SIoT network navigability. Particularly, the device mobility and contextual diversity pose significant challenges to social relation classification, a critical task for efficient routing and service discovery. Existing approaches, primarily designed for static or homogeneous networks, fail to adequately capture the evolving contextual dependencies and the spatiotemporal heterogeneity in SIoT. To address these challenges, we propose Trajectory-Aware Graph LLM (TAGLLM), a novel framework that enhances SIoT navigability through context-aware relation classification. TAGLLM introduces a multi-feature fusion trajectory evolutionary graph encoder to jointly model complex device attributes, social relations, and dynamic trajectories. Furthermore, a structural graph-text token alignment strategy is designed to exploit the generalization ability and contextual understanding capabilities of Large Language Models (LLMs), enabling more effective modeling of heterogeneous and dynamic SIoT scenarios. Extensive experiments on real-world SIoT datasets demonstrate that TAGLLM outperforms state-of-the-art baselines across multiple evaluation metrics, highlighting its potential to push the frontier of graph learning and LLM integration in SIoT applications. © 2014 IEEE.

关键词： Network theory (graphs)

来源：评论

学校读者我要写书评

暂无评论

Meta Computing-Driven Optimization of AoI in Industrial IoT: A Hybrid Scheme with Self-Organizing Maps and Reinforcement Learning

引用

IEEE Internet of Things Journal 2025年

作者： Wang, Min Wang, Yike Wang, Nuanlai Pang, Shanchen Sun, Xiaobing Li, Ming Yangzhou University School of Information Engineering Yangzhou225127 China College of Computer Science and Technology Qingdao China College of Computer Science and Technology China State Key Laboratory of Chemical Safety Shandong Key Laboratory of Intelligent Oil and Gas Industrial Software China Shandong Inspur Database Technology Co. Ltd Jinan250101 China

In the domain of Industrial Internet of Things (IIoT) applications, methodologies such as meta computing are essential for ensuring timely and efficient data acquisition within intricate environments characterized by multiple edge devices and isolated sensor networks. The Age of Information (AoI), a key metric for evaluating data timeliness and relevance, has emerged as a focal point for improving decision-making and system responsiveness. However, managing these systems in resourcelimited edge environments is challenging, as traditional methods struggle to link sink node selection with data collection path planning, leading to inefficiency and poor AoI performance. This paper develops a collaborative optimization framework based on meta computing, which dynamically coordinates distributed computational resources as a unified virtual system. It combines self-organizing mapping (SOM) with reinforcement learning (RL) to optimize sink node selection and data collection paths using AoI metrics. Experimental results show the method significantly reduces AoI, improves data freshness, and optimizes energy use, highlighting meta computing's potential for scalable, efficient IIoT solutions. © 2014 IEEE.

关键词： Self organizing maps

来源：评论

学校读者我要写书评

暂无评论

Graph Contrastive Learning with Cohesive Subgraph Awareness

arXiv

引用

arXiv 2024年

作者： Wu, Yucheng Han, Xiao Wang, Leye Ye, Han-Jia Key Lab of High Confidence Software Technologies Peking University Ministry of Education School of Computer Science Peking University Beijing China School of Information Management and Engineering Shanghai University of Finance and Economics Shanghai China National Key Laboratory for Novel Software Technology Nanjing University School of Artificial Intelligence Nanjing University Nanjing China

Graph contrastive learning (GCL) has emerged as a state-of-the-art strategy for learning representations of diverse graphs including social and biomedical networks. GCL widely uses stochastic graph topology augmentation, such as uniform node dropping, to generate augmented graphs. However, such stochastic augmentations may severely damage the intrinsic properties of a graph and deteriorate the following representation learning process. We argue that incorporating an awareness of cohesive subgraphs during the graph augmentation and learning processes has the potential to enhance GCL performance. To this end, we propose a novel unified framework called CTAug, to seamlessly integrate cohesion awareness into various existing GCL mechanisms. In particular, CTAug comprises two specialized modules: topology augmentation enhancement and graph learning enhancement. The former module generates augmented graphs that carefully preserve cohesion properties, while the latter module bolsters the graph encoder’s ability to discern subgraph patterns. Theoretical analysis shows that CTAug can strictly improve existing GCL mechanisms. Empirical experiments verify that CTAug can achieve state-of-the-art performance for graph representation learning, especially for graphs with high degrees. The code is available at https://***/10.5281/zenodo.10594093, or https://***/wuyucheng2002/CTAug. Copyright © 2024, The Authors. All rights reserved.

关键词： Topology

来源：评论

学校读者我要写书评

暂无评论

Fidelity-Preserved Reversible Data Hiding in JPEG Images Based on Adaptive Position Selection 8th

Fidelity-Preserved Reversible Data Hiding in JPEG Images Bas...

引用

8th International Conference on Artificial Intelligence and Security , ICAIS 2022

作者： Yue, Zhen Ren, Hua Li, Ming Liang, Cun-liang Hai, Ben-zhai Li, Rui-ping Faculty of Education Henan Normal University Henan Xinxiang453007 China Beijing Key Lab of Intelligent Telecommunication Software and Multimedia School of Computer Beijing University of Posts and Telecommunications Beijing100876 China College of Computer and Information Engineering Henan Normal University Xinxiang453007 China

ISBN: (纸本)9783031067662

Reversible data hiding (RDH) in JPEG images has gained considerable attention from scholars in recent years. However, it is not easy for JPEG images to exploit the pixel redundancy for RDH design like uncompressed images. In this paper, we propose a fidelity-preserved RDH in JPEG images. The proposed scheme embeds the secret data using the histogram shifting method after considering different distortion costs of non-zero AC coefficients at different positions. Accord-ing to the block entropy obtained by summing the squares of all pixels of each 8 × 8 block, the quantified DCT blocks are divided into the smoothed blocks and texture blocks, and the obtained smoothed blocks are sorted in ascending order. The AC coefficients with values 1 and/or −1 in the smoother blocks are used for the embedding, the non-zero AC coefficients are shifted toward the right or the left at most by one, and the others remain invariant. Experiment results have verified the effectiveness of the proposed method. © 2022, The Author(s), under exclusive license to Springer Nature Switzerland AG.

关键词： Pixels

来源：评论

学校读者我要写书评

暂无评论

MEC-Enabled Cooperative Rendering in Metaverse: A Coalition Formation Game Approach

MEC-Enabled Cooperative Rendering in Metaverse: A Coalition ...

引用

IEEE International Conference on Communications (ICC)

作者： Mengzhen Cheng Zhou Su Yuan Wu Qichao Xu Minghui Dai Dongfeng Fang School of Mechatronic Engineering and Automation Shanghai University Shanghai China School of Cyber Science and Engineering Xi'an Jiaotong University Xi'an China State Key Laboratory of Internet of Things for Smart City University of Macau Macau China Department of Computer Science and Software Engineering California Polytechnic State University USA

ISBN: (数字)9781728190549

ISBN: (纸本)9781728190556

Virtual Reality (VR) paves the way to link Meta-verse and the real world, allowing users to enjoy immersive experiences. However, delivering high-quality full spherical VR service within limited rendering energy is a challenge. Mobile edge computing (MEC) is a promising paradigm to provide rendering computation services to users. It is widely held that the rendering of panoramic video presents a significant impediment in the VR system, with disregard for the importance of the data correlation leading to excessive energy consumption caused by repeated rendering. In this paper, we propose a cooperative rendering scheme in mm Wave-enabled wireless networks with MEC via a coalition formation game, among which we focus on the data correlation of the background environment of VR streams. Specifically, we first devise a multiple MEC servers rendering framework, and we formulate an optimization problem to maximize the system utility, which contains energy savings for MEC servers and users' quality of experience (QoE). Then, considering the overlap of the VR streams requested by users in Metaverse, a coalition formation game is employed to model the cooperations among MEC servers, such that the user's QoE is significantly improved. The simulation experiments show that our proposed algorithm is superior to benchmark algorithms in improving the users' QoE and reducing the total energy consumption of MEC servers.

关键词： Energy consumption Correlation Metaverse Wireless networks Games Virtual reality Rendering (computer graphics)

来源：评论

学校读者我要写书评

暂无评论

Sybil attack simulation on Enhanced IdAPoS protocol with different network topology

Sybil attack simulation on Enhanced IdAPoS protocol with dif...

引用

International Conference on Identification, Information and Knowledge in the Internet of Things (IIKI)

作者： Shengyu Chen Shenghao Jin Yigang Wei Hui Zhang State Key Laboratory of Complex & Critical Software Environment School of Computer Science & Engineering Beihang University Beijing People’s Republic of China School of economics and management Beihang University Beijing People’s Republic of China

ISBN: (数字)9798331510633

ISBN: (纸本)9798331510640

This study mainly focus on Sybil attacks with the Identity-Augmented Proof-of-Stake (IdAPoS) protocol under different network topologies, including random, scale-free, and hierarchical networks. The study finds that scale-free networks are more resistant to Sybil attacks, delaying their effects. Furthermore, the research improves the IdAPoS protocol by introducing active strategies for honest nodes, which improves the behaviours of this protocol, and by enabling them to dynamically assess and update their trusted and suspicious authority lists based on on-ledger data, which improves the completeness of this protocol.

关键词： Resistance Knowledge engineering Proof of stake Network topology Voting Particle measurements Topology Delays Internet of Things Electrical resistance measurement

来源：评论

学校读者我要写书评

暂无评论

Off-OAB: Off-Policy Policy Gradient Method with Optimal Action-Dependent Baseline

arXiv

引用

arXiv 2024年

作者： Meng, Wenjia Zheng, Qian Yang, Long Yin, Yilong Pan, Gang The School of Software Shandong University Jinan250000 China The School of Artificial Intelligence Peking University China The State Key Lab of Brain-Machine Intelligence College of Computer Science and Technology Zhejiang University Hangzhou310000 China

Policy-based methods have achieved remarkable success in solving challenging reinforcement learning problems. Among these methods, off-policy policy gradient methods are particularly important due to that they can benefit from off-policy data. However, these methods suffer from the high variance of the off-policy policy gradient (OPPG) estimator, which results in poor sample efficiency during training. In this paper, we propose an off-policy policy gradient method with the optimal action-dependent baseline (Off-OAB) to mitigate this variance issue. Specifically, this baseline maintains the OPPG estimator's unbiasedness while theoretically minimizing its variance. To enhance practical computational efficiency, we design an approximated version of this optimal baseline. Utilizing this approximation, our method (Off-OAB) aims to decrease the OPPG estimator's variance during policy optimization. We evaluate the proposed Off-OAB method on six representative tasks from OpenAI Gym and MuJoCo, where it demonstrably surpasses state-of-the-art methods on the majority of these tasks. Copyright © 2024, The Authors. All rights reserved.

关键词： Reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

Pseudo label Refinery for Unsupervised Domain Adaptation on Cross-Dataset 3D Object Detection

Pseudo Label Refinery for Unsupervised Domain Adaptation on ...

引用

Conference on computer Vision and Pattern Recognition (CVPR)

作者： Zhanwei Zhang Minghao Chen Shuai Xiao Liang Peng Hengjia Li Binbin Lin Ping Li Wenxiao Wang Boxi Wu Deng Cai State Key Lab of CAD&CG Zhejiang University Fabu Inc. School of Computer Sciene and Technology Hangzhou Dianzi University Alibaba Group School of Software Technology Zhejiang University Fullong Inc.

ISBN: (数字)9798350353006

ISBN: (纸本)9798350353013

Recent self-training techniques have shown notable improvements in unsupervised domain adaptation for 3D object detection (3D UDA). These techniques typically select pseudo labels, i.e., 3D boxes, to supervise models for the target domain. However, this selection process inevitably introduces unreliable 3D boxes, in which 3D points cannot be definitively assigned as foreground or background. Previous techniques mitigate this by reweighting these boxes as pseudo labels, but these boxes can still poison the training process. To resolve this problem, in this paper, we propose a novel pseudo label refinery framework. Specifically, in the selection process, to improve the reliability of pseudo boxes, we propose a complementary augmentation strategy. This strategy involves either removing all points within an unre-liable box or replacing it with a high-confidence box. More-over, the point numbers of instances in high-beam datasets are considerably higher than those in low-beam datasets, also degrading the quality of pseudo labels during the training process. We alleviate this issue by generating additional proposals and aligning RoI features across different domains. Experimental results demonstrate that our method effectively enhances the quality of pseudo labels and consistently surpasses the state-of-the-art methods on six autonomous driving benchmarks. Code will be available at https://***/Zhanwei-Z/PERE.

关键词： Training Solid modeling computer vision Three-dimensional displays Toxicology Codes Object detection

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：