检索结果-内蒙古大学图书馆

arXiv 2020年

作者： Wang, Teng Zheng, Huicheng Yu, Mingjing School of Data and Computer Science Sun Yat-sen University Key Laboratory of Machine Intelligence and Advanced Computing Ministry of Education Guangdong Province Key Laboratory of Information Security Technology China

This technical report presents a brief description of our submission to the dense video captioning task of ActivityNet Challenge 2020. Our approach follows a two-stage pipeline: first, we extract a set of temporal event proposals;then we propose a multi-event captioning model to capture the event-level temporal relationships and effectively fuse the multi-modal information. Our approach achieves a 9.28 METEOR score on the test set. Copyright © 2020, The Authors. All rights reserved.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Reliable Multi-Modal Object Re-Identification via Modality-Aware Graph Reasoning

arXiv

引用

arXiv 2025年

作者： Wan, Xixi Zheng, Aihua Wang, Zi Jiang, Bo Tang, Jin Ma, Jixin Information Materials and Intelligent Sensing Laboratory of Anhui Province Anhui Provincial Key Laboratory of Security Artificial Intelligence School of Artificial Intelligence Anhui University Hefei230601 China School of Biomedical Engineering Anhui Medical University Key Laboratory of Intelligent Computing & Signal Processing Ministry of Education Anhui University Hefei China Anhui Provincial Key Laboratory of Multimodal Cognitive Computation School of Computer Science and Technology Anhui University Hefei230601 China School of Computing and Mathematical Sciences University of Greenwich LondonSE10 9LS United Kingdom

Multi-modal data provides abundant and diverse object information, crucial for effective modal interactions in Re-Identification (ReID) tasks. However, existing approaches often overlook the quality variations in local features and fail to fully leverage the complementary information across modalities, particularly in the case of low-quality features. In this paper, we propose to address this issue by leveraging a novel graph reasoning model, termed the Modality-aware Graph Reasoning network (MGRNet). Specifically, we first construct modality-aware graphs to enhance the extraction of fine-grained local details by effectively capturing and modeling the relationships between patches. Subsequently, the selective graph nodes swap operation is employed to alleviate the adverse effects of low-quality local features by considering both local and global information, enhancing the representation of discriminative information. Finally, the swapped modality-aware graphs are fed into the local-aware graph reasoning module, which propagates multimodal information to yield a reliable feature representation. Another advantage of the proposed graph reasoning approach is its ability to reconstruct missing modal information by exploiting inherent structural relationships, thereby minimizing disparities between different modalities. Experimental results on four benchmarks (RGBNT201, Market1501-MM, RGBNT100, MSVR310) indicate that the proposed method achieves state-of-the-art performance in multi-modal object ReID. The code for our method will be available upon acceptance. Copyright © 2025, The Authors. All rights reserved.

关键词： Modal analysis

来源：评论

学校读者我要写书评

暂无评论

Lightweight deep reinforcement learning for dynamic resource allocation in vehicular edge computing

引用

Digital Communications and networks 2025年

作者： Dapeng Wu Sijun Wu Yaping Cui Ailing Zhong Tong Tang Ruyan Wang Xinqi Lin School of Communications and Information Engineering Chongqing University of Posts and Telecommunications Chongqing 400065 China Advanced Network and Intelligent Connection Technology Key Laboratory of Chongqing Education Commission of China Chongqing 400065 China Chongqing Key Laboratory of Ubiquitous Sensing and Networking Chongqing 400065 China College of Computer and Cyber Security Fujian Normal University Fuzhou 350117 China

Vehicular Edge computing (VEC) enhances the quality of user services by deploying wealth of resources near vehicles. However, due to highly dynamic and complex nature of vehicular networks, centralized decision-making for resource allocation proves inadequate within VECs. Conversely, allocating resources via distributed decision-making consumes vehicular resources. To improve the quality of user service, we formulate a problem of latency minimization, further subdividing this problem into two subproblems to be solved through distributed decision-making. To mitigate the resource consumption caused by distributed decision-making, we propose Reinforcement Learning (RL) algorithm based on sequential alternating multi-agent system mechanism, which effectively reduces the dimensionality of action space without losing the informational content of action, achieving network lightweighting. We discuss the rationality, generalizability, and inherent advantages of proposed mechanism. Simulation results indicate that our proposed mechanism outperforms traditional RL algorithms in terms of stability, generalizability, and adaptability to scenarios with invalid actions, all while achieving network lightweighting.

关键词： Vehicular edge computing Resource allocation Reinforcement learning Lightweight

来源：评论

学校读者我要写书评

暂无评论

Energy efficiency evaluation based on QoS parameter specification for cloud systems 22

Energy efficiency evaluation based on QoS parameter specific...

引用

22nd IEEE International Conference on High Performance computing and Communications, 18th IEEE International Conference on Smart City and 6th IEEE International Conference on Data Science and Systems, HPCC-SmartCity-DSS 2020

作者： Long, Saiqin Yu, Hao Li, Zhetao Tian, Shujuan Li, Yun Xiangtan University Key Laboratory of Hunan Province for Internet of Things and Information Security Hunan Intl. Sci. and Technol. Cooperation Base of Intelligent Network School of Computer Science Xiangtan China Nanjing University of Posts and Telecommunications School of Computer Science and Technology Nanjing China

ISBN: (纸本)9781728176499

Energy efficiency evaluation (EEE) is a research difficulty in the field of cloud computing. The current research mainly considers the relevant energy efficiency indicators of cloud systems and weights the interrelationship between energy consumption, system performance and QoS requirements. However, it lacks a combination of subjective and objective, qualitative and quantitative evaluation method to accurately evaluate the energy efficiency of cloud systems. We propose a novel EEE method based on the QoS parameter specification for cloud systems (EEE-QoS). Firstly, it reduces the metric values that affect QoS requirements to the same dimension range and then establishes a belief rule base (BRB). The best-worst method is utilized to determine the initial weights of the premise attributes in the BRB model. Then, the BRB model parameters are optimized by the mean-square error, the activation weight is calculated, and the activation rules of the evidence reasoning algorithm are integrated to evaluate the belief of the conclusion. The quantitative and qualitative evaluation of the energy efficiency of cloud systems is realized. The experiments show that the proposed method can accurately and objectively evaluate the energy efficiency of cloud systems. © 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

Optimizing Two-way Partial AUC with an End-to-end Framework

arXiv

引用

arXiv 2022年

作者： Yang, Zhiyong Xu, Qianqian Bao, Shilong He, Yuan Cao, Xiaochun Huang, Qingming School of Computer Science and Technology University of Chinese Academy of Sciences Beijing100049 China The Key Laboratory of Intelligent Information Processing Institute of Computing Technology Chinese Academy of Sciences Beijing100190 China Institute of Information Engineering Chinese Academy of Sciences Beijing100093 China School of Cyber Security University of Chinese Academy of Sciences Beijing100049 China The Security Department of Alibaba Group Hangzhou311121 China School of Cyber Science and Technology Shenzhen Campus Sun Yat-sen University Shenzhen518107 China The School of Computer Science and Technology University of Chinese Academy of Sciences Beijing101408 China University of Chinese Academy of Sciences Beijing101408 China Peng Cheng Laboratory Shenzhen518055 China

The Area Under the ROC Curve (AUC) is a crucial metric for machine learning, which evaluates the average performance over all possible True Positive Rates (TPRs) and False Positive Rates (FPRs). Based on the knowledge that a skillful classifier should simultaneously embrace a high TPR and a low FPR, we turn to study a more general variant called Two-way Partial AUC (TPAUC), where only the region with TPR ≥ α, FPR ≤ β is included in the area. Moreover, a recent work shows that the TPAUC is essentially inconsistent with the existing Partial AUC metrics where only the FPR range is restricted, opening a new problem to seek solutions to leverage high TPAUC. Motivated by this, we present the first trial in this paper to optimize this new metric. The critical challenge along this course lies in the difficulty of performing gradient-based optimization with end-to-end stochastic training, even with a proper choice of surrogate loss. To address this issue, we propose a generic framework to construct surrogate optimization problems, which supports efficient end-to-end training with deep learning. Moreover, our theoretical analyses show that: 1) the objective function of the surrogate problems will achieve an upper bound of the original problem under mild conditions, and 2) optimizing the surrogate problems leads to good generalization performance in terms of TPAUC with a high probability. Finally, empirical studies over several benchmark datasets speak to the efficacy of our framework. © 2022, CC BY.

关键词： Stochastic systems

来源：评论

学校读者我要写书评

暂无评论

TVIDS: Trusted Virtual IDS With SGX

引用

China Communications 2019年第10期16卷 133-150页

作者： Juan Wang Shirong Hao Yi Li Zhi Hong Fei Yan Bo Zhao Jing Ma Huanguo Zhang Key Laboratory of Aerospace Information Security and Trust Computing Ministry of EducationSchool of Cyber Science and EngineeringWuhan UniversityWuhan 430072HubeiChina School of Cyber Science and Engineering Wuhan UniversityWuhan 430072China Science and Technology on Information Assurance Laboratory Beijing 100072China

network functions such as intrusion detection systems (IDS) have been increasingly deployed as virtual network functions or outsourced to cloud service providers so as to achieve the scalability and agility, and reducing equipment costs and operational cost. However, virtual intrusion detection systems (VIDS) face more serious security threats due to running in a shared and virtualized environment instead of proprietary devices. Cloud service providers or malicious tenants may illegally access and tamper with the policies, packet information, and internal processing states of intrusion detection systems, thereby violating the privacy and security of tenant’s networks. To address these challenges, we use Intel Software Guard Extensions (SGX) to build a Trusted Virtual Intrusion Detection System (TVIDS). For TVIDS, to prevent cloud service providers from accessing sensitive information about the users’ network, we build a trusted execution environment for security policy, packets processing, and internal state so that cloud service providers and other malicious tenants can’t access the protected code, policy, processing states, and packets information of the intrusion detection system. We implemented TVIDS on the basis of the Snort which is a famous open-source IDS and evaluated its results on real SGX *** results show that our method can protect the security of the virtual IDS and brings acceptable performance overhead.

关键词： network function virtualization intrusion detection system SGX trusted execution environment

来源：评论

学校读者我要写书评

暂无评论

A Dynamic Collaborative Filtering Algorithm based on Convolutional Neural networks and Multi-layer Perceptron

A Dynamic Collaborative Filtering Algorithm based on Convolu...

引用

International Conference on Ubiquitous computing and Communications and International Symposium on Cyberspace and security (IUCC-CSS)

作者： Qiang Sun Lei-lei Shi Lu Liu Zi-xuan Han Liang Jiang Yao Lu John Panneerselvam School of Computer Science and Telecommunication Engineering Jiangsu University China Jiangsu Key Laboratory of Security Tech. for Industrial Cyberspace Jiangsu University China School of Computing and Mathematical Sciences University of Leicester UK School of Computer Jiangsu University of science and technology China

ISBN: (纸本)9781665466684

In the current information era of enormous amount of data generation, recommendation systems are increasingly used as an efficient way to mitigate information overload in networks. The recommendation systems are used to provide more focused and personalized recommendation of relevant items based on user's historical preferences and constraints. An efficient recommendation system should enrich and improve end user experience. At present, recommendation systems commonly use traditional collaborative filtering algorithms to learn the hidden vectors from the user's commodity behavior matrix. Most of the traditional algorithms characterize data sparseness and cold start problems. Whilst deep learning is being utilized to accurately learn the auxiliary information to enhance the recommendation provided by collaborative filtering techniques, the implementation of deep learning should be fine-tuned in such a way that is satisfies specific application contexts. This paper intends to build a deep collaborative filtering model that integrates Convolutional Neural networks and Multi-layer Perceptron, addressing the specific requirements of movie recommendation systems. Our proposed model can accurately capture the characteristics of local correlation and explicit and implicit feedback information. In the explicit recommendation task, implicit feedback search is used to embed similar groups, and multi-layer perceptron is used to model user projects, user similar project groups and project similar user groups. Experiments conducted based on the MovieLens dataset for predicting the movie scores demonstrate that our proposed algorithm improves the accuracy of movie score prediction, and outperforms notable traditional collaborative filtering algorithms in terms of alleviating the data sparseness and cold start problems.

关键词： Deep learning Collaborative filtering Heuristic algorithms Filtering algorithms Prediction algorithms Motion pictures Ubiquitous computing

来源：评论

学校读者我要写书评

暂无评论

Sentiment Analysis of Web Text Based on Deep Learning with a Attention Mechanism

Sentiment Analysis of Web Text Based on Deep Learning with a...

引用

International Congress on Image and Signal Processing, BioMedical Engineering and Informatics (CISP-BMEI)

作者： Qing Yu Hui Zhao Kaiwen Jiang Tianjin Key Laboratory of Intelligence Computing and Network Security Tianjin University of Technology Tianjin China

The sentiment analysis of online commentary is a hot research topic in the field of network information mining. Traditional text sentiment analysis methods are mainly based on emotional dictionaries or machine learning. However, it relies on the structure of the sentiment dictionary and the artificial design and extraction features, which limits the generalization ability. In contrast, the deep learning model has a stronger ability to express complex mapping functions from data to emotional semantics. This paper proposes a model combining Bidirectional Gated Recurrent Unit(BGRU) neural network and Convolutional Neural network(CNN), and introduces attention mechanism for text sentiment analysis. The experimental results show that compared with the traditional method, the method effectively improves the accuracy of text sentiment classification.

关键词：

来源：评论

学校读者我要写书评

暂无评论

ON THE OPPORTUNITIES OF GREEN computing: A SURVEY

arXiv

引用

arXiv 2023年

作者： Zhou, You Lin, Xiujing Zhang, Xiang Wang, Maolin Jiang, Gangwei Lu, Huakang Wu, Yupeng Zhang, Kai Yang, Zhe Wang, Kehang Sui, Yongduo Jia, Fengwei Tang, Zuoli Zhao, Yao Zhang, Hongxuan Yang, Tiannuo Chen, Weibo Mao, Yunong Li, Yi Bao, De Li, Yu Liao, Hongrui Liu, Ting Liu, Jingwen Guo, Jinchi Zhao, Xiangyu Wei, Ying Qian, Hong Liu, Qi Wang, Xiang Chan, Wai Kin Li, Chenliang Li, Yusen Yang, Shiyu Yan, Jining Mou, Chao Han, Shuai Jin, Wuxia Zhang, Guannan Zeng, Xiaodong Tsinghua University China Shanghai Jiaotong University China University of Science and Technology of China China Key Laboratory of Aerospace Information Security and Trusted Computing Ministry of Education School of Cyber Science and Engineering Wuhan University China Huazhong University of Science and Technology China Shanghai Institute of AI for Education School of Computer Science and Technology East China Normal University China Xi’an Jiaotong University China College of Computer Science Nankai University China School of Computer Science China University of Geosciences China School of Information Science and Technology Beijing Forestry University China Engineering Research Center for Forestry-Oriented Intelligent Information Processing National Forestry and Grassland Administration China Guangzhou University China Nanyang Technological University Singapore City University of Hong Kong Hong Kong Wuhan University China State Key Laboratory for Novel Software Technology Nanjing University China Ant Group China

Artificial Intelligence (AI) has achieved significant advancements in technology and research with the development over several decades, and is widely used in many areas including computing vision, natural language processing, time-series analysis, speech synthesis, etc. During the age of deep learning, especially with the arise of Large Language Models, a large majority of researchers’ attention is paid on pursuing new state-of-the-art (SOTA) results, resulting in ever increasing of model size and computational complexity. The needs for high computing power brings higher carbon emission and undermines research fairness by preventing small or medium-sized research institutions and companies with limited funding in participating in research. To tackle the challenges of computing resources and environmental impact of AI, Green computing has become a hot research topic. In this survey, we give a systematic overview of the technologies used in Green computing. We propose the framework of Green computing and devide it into four key components: (1) Measures of Greenness, (2) Energy-Efficient AI, (3) Energy-Efficient computing Systems and (4) AI Use Cases for Sustainability. For each components, we discuss the research progress made and the commonly used techniques to optimize the AI efficiency. We conclude that this new research direction has the potential to address the conflicts between resource constraints and AI development. We encourage more researchers to put attention on this direction and make AI more environmental friendly. Copyright © 2023, The Authors. All rights reserved.

关键词： Carbon footprint

来源：评论

学校读者我要写书评

暂无评论

Channel Estimation for Irregular Subarrayed RIS-Aided mmwave Communications

引用

IEEE Transactions on Vehicular technology 2025年

作者： Yu, Xiao Liu, Heng Gong, Shiqi Shen, Wenqian Zhao, Junhui Xing, Chengwen Beijing Institute of Technology School of Information and Electronics Beijing100081 China Xi'an University of Posts and Telecommunications Shaanxi Key Laboratory of Information Communication Network and Security Shaanxi Xi'an710121 China Beijing Jiaotong University School of Electronic and Information Engineering Beijing100044 China

Channel estimation is essential for reconfigurable intelligent surface (RIS)-aided wireless communications. Irregular RIS structures can provide more design degrees of freedom to enhance system performance. In this paper, we investigate the channel estimation problem for an irregular subarrayed RIS-aided millimeter wave (mmWave) system. Specifically, we formulate the channel estimation problem as a sparse recovery problem by exploiting the sparsity of the mmWave channel, which can be effectively solved by the proposed two-stage algorithm. In the first stage, the common angles of arrival (AoAs) at the base station (BS) are estimated using the discrete Fourier transform (DFT) method. In the second stage, the estimated AoA information is used to decouple signals from different paths, thus leading to the user-specific subchannel estimation problem. Moreover, effective sparse angles are sampled within the sine and cosine domains to reduce the number of channel parameters. Then, we apply the expectation-maximization-based variational Bayesian inference (EM-VBI) method to estimate these parameters. Furthermore, taking into account practical calibration errors among sub-RISs, we propose to estimate channel parameters and auxiliary error parameters simultaneously, along with an effective method to extract the original error information from these auxiliary parameters. Simulation results demonstrate the superiority of the proposed algorithms over existing benchmark schemes in terms of the channel estimation accuracy and the calibration accuracy of intersubarray errors. © 1967-2012 IEEE.

关键词： Channel 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：