检索结果-内蒙古大学图书馆

A Novel Action Recognition Method Based on Attention Enhancement and Relative Entropy 1

2nd International Conference on Artificial Intelligence, Robotics, and Communication, ICAIRC 2022

作者： Liu, Xing-Sheng Liu, Shi-Jian Fujian Provincial Key Laboratory of Big Data Mining and Applications Fujian University of Technology Fujian Fuzhou350118 China

ISBN: (数字)9789819945542

ISBN: (纸本)9789819945535

Action recognition is a hotspot field in computer vision for video understanding. To achieve accurate and real-time action recognition, a novel skeleton-based method combined with attention enhancement and relative entropy is proposed. Firstly, the data normalization method is presented to reduce the recognition error caused by human body posture and scale differences. Secondly, a joint attention strategy is proposed considering the different contributions of joints in an action. Finally, a relative entropy based acceleration strategy is employed to avoid unnecessary matching and save time. Experiments carried out on the Microsoft Research Cambridge-12 dataset show that the accuracy of our method is 90.32% and the time cost is 31.58 ms on average, which outperforms the others. © 2023, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

关键词： Entropy

来源：评论

学校读者我要写书评

暂无评论

ieSTGCN:A mining Model of Skeleton Spatio-temporal Graph 5th

ieSTGCN:A Mining Model of Skeleton Spatio-temporal Graph

引用

5th China Conference on Intelligent Networked Things, CINT 2022

作者： Mao, Guojun Wang, Yijin Fujian University of Technology Fuzhou350118 China Key Laboratory of Big Data Mining and Application in Fujian Province Fuzhou350118 China

ISBN: (纸本)9789811989148

Traditional methods of human action recognition focus on internal links between human joints, that is, local neighbor connections. However, some external links that cannot exist in the skeleton graph are also important for identifying human behaviors, such as hands and feet in harmonious movement. To capture richer spatial features in a skeleton graph, it is necessary to add external links and distinguish internal links from external links in a skeleton graph. Therefore, this paper designs two different adjacency matrices to characterize the internal links and external links of the human body respectively, and set different edge weights and feature weights to them for autonomous learning during the convolution process. Furthermore, a spatio-temporal graph convolution network called ieSTGCN is proposed. It consists of two modules: graph convolution network supporting internal and external links (ieGCN) and temporal convolution network in human joints (joTCN). Experiments on the Kinetics and the NTU-RGB+D datasets demonstrate that our model can obtain better recognition accuracy than some benchmark models. © 2022, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

关键词： Convolution

来源：评论

学校读者我要写书评

暂无评论

Less Is More: Token Context-Aware Learning for Object Tracking 39

Less Is More: Token Context-Aware Learning for Object Tracki...

引用

39th Annual AAAI Conference on Artificial Intelligence, AAAI 2025

作者： Xu, Chenlong Zhong, Bineng Liang, Qihua Zheng, Yaozong Li, Guorong Song, Shuxiang Key Laboratory of Education Blockchain and Intelligent Technology Ministry of Education Guangxi Normal University Guilin541004 China Key Laboratory of Big Data Mining and Knowledge Management University of Chinese Academy of Sciences China

ISBN: (纸本)157735897X

Recently, several studies have shown that utilizing contextual information to perceive target states is crucial for object tracking. They typically capture context by incorporating multiple video frames. However, these naive frame-context methods fail to consider the importance of each patch within a reference frame, making them susceptible to noise and redundant tokens, which deteriorates tracking performance. To address this challenge, we propose a new token context-aware tracking pipeline named LMTrack, designed to automatically learn high-quality reference tokens for efficient visual tracking. Embracing the principle of Less is More, the core idea of LMTrack is to analyze the importance distribution of all reference tokens, where important tokens are collected, continually attended to, and updated. Specifically, a novel Token Context Memory module is designed to dynamically collect high-quality spatio-temporal information of a target in an autoregressive manner, eliminating redundant background tokens from the reference frames. Furthermore, an effective Unidirectional Token Attention mechanism is designed to establish dependencies between reference tokens and search frame, enabling robust cross-frame association and target localization. Extensive experiments demonstrate the superiority of our tracker, achieving state-of-the-art results on tracking benchmarks such as GOT-10K, TrackingNet, and LaSOT. Copyright © 2025, Association for the Advancement of Artificial Intelligence (***). All rights reserved.

关键词： Aircraft detection

来源：评论

学校读者我要写书评

暂无评论

ReFrame: A Resource-Friendly Cloud-Assisted On-Device Deep Learning Framework for Vision Services

引用

IEEE Transactions on Services Computing 2025年第3期18卷 1711-1723页

作者： Xie, Jianhang Ding, Chuntao Guan, Qingji Zhou, Ao Li, Yidong Beijing Jiaotong University Key Laboratory of Big Data & Artificial Intelligence in Transportation Ministry of Education School of Computer Science and Technology Beijing100044 China Beijing Normal University School of Artificial Intelligence Beijing100875 China Beijing Jiaotong University Beijing Key Laboratory of Traffic Data Analysis and Mining Beijing100044 China Beijing University of Posts and Telecommunications State Key Laboratory of Networking and Switching Technology Beijing100876 China

Cloud-assisted Internet of Things (IoT) device deployment of deep neural networks (DNNs) promotes On-device deep learning to provide users with ubiquitous high-quality services by solving the contradiction between insufficient IoT device resources and intensive demand for high-performance DNN resources. However, most existing methods optimize DNNs by considering one or two terms of transmission, computation, and storage resources, but do not consider all three terms at the same time in cloud-assisted IoT device deployment and updating DNNs. To this end, we propose a non-learnable module-based ResNet and a cloud-assisted on-device deep learning framework, ReFrame, based on the consideration of three indicators: model transmission parameters, computation resources, and storage resources. In the proposed method, we first specify that some parameters in DNNs are non-learnable and randomly initialized, so that, these parameters can be saved and reproduced with a few random seeds. By doing so, the cloud only transmits random seeds and learnable parameters to reduce the number of parameter transmissions. Second, we reduce the computation resource consumption of the model by introducing computation-friendly operators, such as pooling, to replace vanilla convolutions. Finally, since random seeds are used to save nonlearnable model parameters, on IoT devices we only need to store random seeds and learnable parameters to reproduce the welltrained model. Compared with saving the complete model, our method greatly reduces IoT device storage resource consumption. Experimental results on image classification, object detection, and semantic segmentation tasks demonstrate the effectiveness of the proposed method. Specifically, on the CIFAR-10, our proposed method reduces approximately 89% of FLOPs and 90% of transmitted data in the prototype system compared to ResNet-18. © 2008-2012 IEEE.

关键词： Cloud platforms

来源：评论

学校读者我要写书评

暂无评论

Spatial matching and flow in supply and demand of water provision services: A case study in Xiangjiang River Basin

引用

Journal of Mountain Science 2022年第1期19卷 228-240页

作者： DENG Chu-xiong ZHU Da-mei LIU Yao-jun LI Zhong-wu College of Resources and Environmental Sciences Hunan Normal UniversityChangsha 410081China Hunan Key Laboratory of Geospatial Big Data Mining and Application Changsha 410081China College of Environmental Science and Engineering Hunan UniversityChangsha 410082China

Global climate change and increased human consumption have aggravated the uneven spatiotemporal distribution of watershed water resources, affecting the water provision supply and demand state. However, this problem has often been ignored. The present study used the Xiangjiang River basin(XRB) as the study area, and the Integrated Valuation of Ecosystem Services and Trade-offs(InVEST) model, demand quantification model,supply–demand ratio, and water flow formula were applied to explore the spatial heterogeneity, flow, and equilibrium between water supply and demand. The results demonstrated significant spatial heterogeneity in the upstream, midstream, and downstream *** areas of water shortage were mainly located the downstream of the Changsha–Zhuzhou–Xiangtan urban agglomeration, and the Hengyang basin was the most scarcity area. Affected by terrain gradients and human needs, water flow varied from-16.33 × 10^(8) m^(3) to 13.69 × 10^(8) m^(3)from the upstream to the downstream area, which provided a possibility to reduce spatial heterogeneity. In the future, measures such as strengthening water resource system control,sponge city construction, and dynamic monitoring technology should be taken to balance the supply and demand of water in different river sections of the basin. This study can provide references for regulating water resources allocation in different reaches of the basin.

关键词： Water provision services Supply and demand Spatiotemporal dislocation Water flow Water management and saving policy Xiangjiang River basin

来源：评论

学校读者我要写书评

暂无评论

An efficient Quasi-Affine Transformation Evolutionary algorithm with fixed dimension updating and its application in UAV 3D path planning

引用

Journal of Intelligent and Fuzzy Systems 2024年第4期46卷 9755-9781页

作者： Sung, Tien-Wen Zhao, Baohua Zhang, Xin Lee, Chao-Yang Fang, Qingjun Fujian Provincial Key Laboratory of Big Data Mining and Applications College of Computer Science and Mathematics Fujian University of Technology Fuzhou China Department of Computer Science and Information Engineering National Yunlin University of Science and Technology Yunlin Taiwan

Quasi-Affine Transformation Evolutionary (QUATRE) algorithm is a kind of swarm-based collaborative optimization algorithm that solves the problem of a position deviation in a DE search by using the co-evolution matrix M instead of the cross-control parameter CR in the differential evolution algorithm (DE). However, QUATRE shares some of the same weaknesses as DE, such as premature convergence and search stagnation. Inspired by the artificial bee colony algorithm (ABC), we propose a new QUATRE algorithm to improve these problems that ranks all the individuals and evolves only the poorer half of the population. In an evolving population, individuals of different levels intersect with dimensions of different sizes to improve search efficiency and accuracy. In addition, we establish a better selection framework for the parent generation individuals and select more excellent parent individuals to complete the evolution for the individuals trapped in search stagnation. To verify the performance of the new QUATRE algorithm, we divide the comparison algorithm into three groups, including ABC variant group, DE variant group, and QUATRE variant group, and the CEC2014 test suite is used for the comparison. The experimental results show the new QUATRE algorithm performance is competitive. We also successfully apply the new QUATRE algorithm on the 3D path planning of UAV, and compared with the other famous algorithm performance it is still outstanding, which verifies the algorithm's practicability. © 2024 - IOS Press. All rights reserved.

关键词： Optimization

来源：评论

学校读者我要写书评

暂无评论

Fish freshness evaluation based on MobileNetV1 and attention mechanism 22

Fish freshness evaluation based on MobileNetV1 and attention...

引用

Proceedings of the 2022 6th International Conference on Electronic Information Technology and Computer Engineering

作者： Xin Guo Shenming Gu Dan Wei School of Information Engineering Zhejiang Ocean University China Key Laboratory of Oceanographic Big Data Mining & Application of Zhejiang Province Zhejiang Ocean University China Key Laboratory of Oceanographic Big Data Mining & Application of Zhejiang Province Key Laboratory of Oceanographic Big Data Mining & Application of Zhejiang Province China

ISBN: (纸本)9781450397148

Rapid acquisition of fish freshness is an important task. The traditional freshness detection of aquatic fish has the problems of damaging samples, complicated operation and long detection time. A convenient, rapid, nondestructive and accurate freshness detection method is urgently needed in production. In this study, the freshness of aquatic fish was evaluated nondestructively and rapidly by machine vision. Firstly, we select the appropriate data set, and add the attention mechanism module to the end of the MobileNetV1 with the default alpha value. Secondly, the alpha value of all models is reduced to compare the performance for subsequent deployment to the cloud and small embedded devices with limited resources. Finally, the network is trained by real data. The results show that the MobilenetV1 network with attention mechanism module can better evaluate the freshness of fish through the fisheye image. The convergence speed and accuracy of the network are improved compared with the original network, and it is more suitable for the task of determining the freshness of fish through fisheye.

关键词： image recognition attention mechanism freshness evaluation deep learning fisheye

来源：评论

学校读者我要写书评

暂无评论

DRL-Based Time-Varying Workload Scheduling With Priority and Resource Awareness

引用

IEEE Transactions on Network and Service Management 2025年第3期22卷 2838-2852页

作者： Liu, Qifeng Fan, Qilin Zhang, Xu Li, Xiuhua Wang, Kai Xiong, Qingyu Chongqing University School of Big Data and Software Engineering Key Laboratory of Dependable Service Computing in Cyber Physical Society of Ministry of Education Chongqing400044 China Nanjing University School of Electronic Science and Engineering Nanjing210023 China Chongqing University School of Big Data and Software Engineering Chongqing400044 China Haihe Laboratory of Information Technology Application Innovation Tianjin300072 China Harbin Institute of Technology School of Computer Science and Technology Weihai264209 China Shandong Key Laboratory of Industrial Network Security Weihai264209 China

With the proliferation of cloud services and the continuous growth in enterprises’ demand for dynamic multidimensional resources, the implementation of effective strategy for time-varying workload scheduling has become increasingly significant. In this paper, we propose a deep reinforcement learning (DRL)-based method for time-varying workload scheduling, aiming to allocate resources efficiently across servers in the cluster. Specifically, we integrate a classifier and queue scorer to construct a priority queue that exploits temporal resource utilization patterns across different workload classes. Then, we design parallel graph attention layers to capture the dimensional features and temporal dynamics of cloud server cluster. Moreover, we propose a DRL algorithm to generate scheduling strategies that can adapt to dynamic environments. Validation on real-world traces from Google cluster demonstrates that our method outperforms existing approaches in key metrics of cloud server cluster management. © 2004-2012 IEEE.

关键词： Cloud platforms

来源：评论

学校读者我要写书评

暂无评论

A Blind Batch Encryption and Public Ledger-Based Protocol for Sharing Sensitive data

引用

China Communications 2024年第1期21卷 310-322页

作者： Zhiwei Wang Nianhua Yang Qingqing Chen Wei Shen Zhiying Zhang School of Computer Sciences Nanjing University of Posts and TelecommunicationsNanjing 210023China Dept.of Intelligent Science and Information Law East China University of Political Science and LawShanghai 201620China Key Laboratory of Computational Science and Application of Hainan Province Hainan Normal UniversityHaikou 571158China State Key Laboratory of Public Big Data Guizhou UniversityGuizhou 550025China Yunnan Key Laboratory of Blockchain Application Technology Yunnan Innovation Research Institute of Beijing University of Aeronautics and AstronauticsKunming 650233

For the goals of security and privacy preservation,we propose a blind batch encryption-and public ledger-based data sharing protocol that allows the integrity of sensitive data to be audited by a public ledger and allows privacy information to be *** owners can tightly manage their data with efficient revocation and only grant one-time adaptive access for the fulfillment of the *** prove that our protocol is semanticallly secure,blind,and secure against oblivious requesters and malicious file *** also provide security analysis in the context of four typical attacks.

关键词： blind batch encryption data sharing onetime adaptive access public ledger security and privacy

来源：评论

学校读者我要写书评

暂无评论

Route Planning and Charging Navigation Strategy for Electric Vehicles Under the Mutual Assistance Trip System 12th

Route Planning and Charging Navigation Strategy for Electric...

引用

12th International Conference on Green Intelligent Transportation Systems and Safety, 2021

作者： Zeng, Zhaohui Wang, Jiangfeng Luo, Dongyu Yang, Guojun The MOT Key Laboratory of Transport Industry of Big Data Application Technologies for Comprehensive Transport Beijing Jiaotong University Beijing100044 China

ISBN: (纸本)9789811956140

Aiming at the range anxiety caused by battery capacity limitations on electric vehicles (EVs), a set of mutual assistance trip system was established, which used the mutual assistance information on EV drivers as a supplement to decision-making. The charging navigation and route selection optimization was carried out significantly, improving driver charging experience. The optimization model of the central control terminal aims at minimizing the total travel time costs of drivers, integrating real-time dynamic road conditions information, charging service information and EV mutual assistance information. It utilizes information entropy theory to quantify mutual assistance information on mutual assistance information risk factor θi, thus adjusts the weight of travel costs. The model is solved by the genetic algorithm based on the priority coding method. The results of the calculation example show that the mutual assistance trip system can significantly reduce the total travel costs of EV drivers. At the same time, the increase in mutual assistance information makes θi larger, which means the more reliable the corresponding travel cost ti, the greater the impact on the total time costs. © 2023, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

关键词： Genetic algorithms

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：