检索结果-内蒙古大学图书馆

HGFormer: Topology-Aware Vision Transformer with HyperGraph Learning

学校读者我要写书评

暂无评论

arXiv 2025年

作者： Wang, Hao Zhang, Shuo Leng, Biao School of Computer Science and Engineering Beihang University Beijing100191 China Beijing Key Laboratory of Traffic Data Analysis and Mining School of Computer Science & Technology Beijing100044 China

The computer vision community has witnessed an extensive exploration of vision transformers in the past two years. Drawing inspiration from traditional schemes, numerous works focus on introducing vision-specific inductive biases. However, the implicit modeling of permutation invariance and fully-connected interaction with individual tokens disrupts the regional context and spatial topology, further hindering higher-order modeling. This deviates from the principle of perceptual organization that emphasizes the local groups and overall topology of visual elements. Thus, we introduce the concept of hypergraph for perceptual exploration. Specifically, we propose a topology-aware vision transformer called HyperGraph Transformer (HGFormer). Firstly, we present a Center Sampling K-Nearest Neighbors (CS-KNN) algorithm for semantic guidance during hypergraph construction. Secondly, we present a topology-aware HyperGraph Attention (HGA) mechanism that integrates hypergraph topology as perceptual indications to guide the aggregation of global and unbiased information during hypergraph messaging. Using HGFormer as visual backbone, we develop an effective and unitive representation, achieving distinct and detailed scene depictions. Empirical experiments show that the proposed HGFormer achieves competitive performance compared to the recent SoTA counterparts on various visual benchmarks. Extensive ablation and visualization studies provide comprehensive explanations of our ideas and contributions. Copyright © 2025, The Authors. All rights reserved.

关键词： k-nearest neighbors

A knowledge graph constructed for job-related crimes

学校读者我要写书评

暂无评论

Procedia Computer Science 2022年 199卷 540-547页

作者： Yong Shi Wenlu An Jiayu Xue Yi Qu School of Economics and Management University of Chinese Academy of Sciences Beijing 100190 CHINA Research Center on Fictitious Economy & Data Science Chinese Academy of Sciences Beijing 100190 CHINA Key Laboratory of Big Data Mining and Knowledge Management Chinese Academy of Sciences Beijing 100190 CHINA College of Information Science and Technology University of Nebraska at Omaha NE 68182 USA People’s Procuratorate of Shanghai Pudong New District Shanghai 200135 CHINA School of Computer Science and Technology University of Chinese Academy of Sciences Beijing 100190 China

Since the 18th National Congress, the Party Central Committee has greatly enhanced its efforts to "fight corruption and advocate honesty". While achieving excellent results, the rising number of crime cases has also brought great challenges to the work of the prosecution organs. At the same time, the traditional relational database has become more and more disadvantageous in dealing with large-scale, unstructured and complex dynamic data, and can no longer meet the actual needs. In order to further improve the efficiency and quality of prosecutors’ work, alleviate the problem of "too many cases and too few people", and promote the construction of "smart prosecution", this paper uses knowledge extraction and other methods to identify the key entities and relationships in the job-related crimes indictments of the Shanghai Pudong New District Procuratorate. Then using Neo4j graph database to store the extracted information and build a knowledge graph for job-related crime cases, which realizes the visualization and deep mining of job-related crime, providing a new way and tool for prosecution work as well as prosecution personnel to analyze and handle job-related crime cases.

关键词： big data in prosecution knowledge graph job-related crimes Neo4j

Decision Tree and knowledge Graph Based on Grain Loss Prediction 6th

学校读者我要写书评

暂无评论

Decision Tree and Knowledge Graph Based on Grain Loss Predic...

6th International Conference on data Science, ICDS 2019

作者： Zhao, Lishan Li, Bingchan Mao, Bo Jiangsu Key Laboratory of Modern Logistics Jiangsu Key Laboratory of Grain Big Data Mining and Application College of Information Engineering Nanjing University of Finance and Economics NanjingJiangsu210023 China College of Electrical Engineering and Automation Jiangsu Maritime Institute No. 309 Gezhi Road NanjingJiangsu China

ISBN: (纸本)9789811528095

China is an agricultural country. Agricultural production is an import part of the Chinese economic system. With the advent of the information age, plenty of data have been produced in a series of links about harvest and after-harvest, such as harvest, processing, transportation, and consumption. With proper use of these data, we can dig out more and more valuable information from the data. In this paper, the relevant algorithm of machine learning is adopted and improved to predict the grain loss after extracting the data of harvesting link. Machine learning is the core of Artificial Intelligence, and its application covers all fields. In this paper, based on the traditional machine learning algorithm—decision tree, the knowledge graph is used to make appropriate improvements to predict the grain-loss after harvest. © Springer Nature Singapore Pte Ltd 2020.

关键词： Machine learning

Heterogeneous influence of individuals’ behavior on mask efficacy in gathering environments

学校读者我要写书评

暂无评论

Frontiers of engineering Management 2022年第4期9卷 550-562页

作者： Haochen SUN Xiaofan LIU Zhanwei DU Ye WU Haifeng ZHANG Xiaoke XU College of Information and Communication Engineering Dalian Minzu UniversityDalian 116600China Web Mining Laboratory Department of Media and CommunicationCity University of Hong KongHong KongChina WHO Collaborating Centre for Infectious Disease Epidemiology and Control School of Public HealthLi Ka Shing Faculty of MedicineThe University of Hong KongHong KongChina Laboratory of Data Discovery for Health Hong Kong Science and Technology ParkHong KongChina Computational Communication Research Center Beijing Normal University(Zhuhai)Zhuhai 519087China School of Journalism and Communication Beijing Normal UniversityBeijing 100875China Key Laboratory of Intelligent Computing and Signal Processing of Ministry of Education School of Mathematical ScienceAnhui UniversityHefei 230601China

Wearing masks is an easy way to operate and popular measure for preventing *** masks can slow down the spread of viruses,their efficacy in gathering environments involving heterogeneous person-to-person contacts remains ***,we aim to investigate the epidemic prevention effect of masks in different real-life gathering *** study uses four real interpersonal contact datasets to construct four empirical networks to represent four gathering *** transmission of COVID-19 is simulated using the Monte Carlo simulation *** heterogeneity of individuals can cause mask efficacy in a specific gathering environment to be different from the baseline efficacy in general ***,the heterogeneity of gathering environments causes the epidemic prevention effect of masks to *** masks can greatly reduce the probability of clustered epidemics and the infection scale in primary schools,high schools,and ***,the use of masks alone in primary schools and hospitals cannot control *** high schools with social distancing between classes and in workplaces where the interpersonal contact is relatively sparse,masks can meet the need for *** the heterogeneity of individual behavior,if individuals who are more active in terms of interpersonal contact are prioritized for mask-wearing,the epidemic prevention effect of masks can be ***,asymptomatic infection has varying effects on the prevention effect of masks in different *** effect can be weakened or eliminated by increasing the usage rate of masks in high schools and ***,the effect on primary schools and hospitals cannot be *** study contributes to the accurate evaluation of mask efficacy in various gathering environments to provide scientific guidance for epidemic prevention.

关键词： COVID-19 masks behavioral heterogeneity asymptomatic infection

Bloch Equation Enables Physics-informed Neural Network in Parametric Magnetic Resonance Imaging

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Cai, Qingrui Zhu, Liuhong Zhou, Jianjun Qian, Chen Guo, Di Qu, Xiaobo National Integrated Circuit Industry Education Integration Innovation Platform School of Electronic Science and Engineering National Model Microelectronics College Xiamen University Xiamen361102 China Fudan University Xiamen361015 China Department of Electronic Science Fujian Provincial Key Laboratory of Plasma and Magnetic Resonance Xiamen University Xiamen361102 China School of Computer and Information Engineering Fujian Engineering Research Center for Medical Data Mining and Application Xiamen University of Technology Xiamen361024 China

Magnetic resonance imaging (MRI) is an important non-invasive imaging method in clinical diagnosis. Beyond the common image structures, parametric imaging can provide the intrinsic tissue property thus could be used in quantitative evaluation. The emerging deep learning approach provides fast and accurate parameter estimation but still encounters the lack of network interpretation and enough training data. Even with a large amount of training data, the mismatch between the training and target data may introduce errors. Here, we propose one way that solely relies on the target scanned data and does not need a pre-defined training database. We provide a proof-of-concept that embeds the physical rule of MRI, the Bloch equation, into the loss of physics-informed neural network (PINN). PINN enables learning the Bloch equation, estimating the T2 parameter, and generating a series of physically synthetic data. Experimental results are conducted on phantom and cardiac imaging to demonstrate its potential in quantitative MRI. Copyright © 2023, The Authors. All rights reserved.

关键词： Magnetic resonance imaging

Image manipulation detection by multi-view multi-scale supervision

学校读者我要写书评

暂无评论

arXiv 2021年

作者： Chen, Xinru Dong, Chengbo Ji, Jiaqi Cao, Juan Li, Xirong MoE Key Lab of Data Engineering and Knowledge Engineering Renmin University of China AIMC Lab School of Information Renmin University of China Institute of Computing Technology Chinese Academy of Sciences State Key Laboratory of Media Convergence Production Technology and Systems

The key challenge of image manipulation detection is how to learn generalizable features that are sensitive to manipulations in novel data, whilst specific to prevent false alarms on authentic images. Current research emphasizes the sensitivity, with the specificity overlooked. In this paper we address both aspects by multi-view feature learning and multi-scale supervision. By exploiting noise distribution and boundary artifact surrounding tampered regions, the former aims to learn semantic-agnostic and thus more generalizable features. The latter allows us to learn from authentic images which are nontrivial to be taken into account by current semantic segmentation network based methods. Our thoughts are realized by a new network which we term MVSS-Net. Extensive experiments on five benchmark sets justify the viability of MVSS-Net for both pixel-level and image-level manipulation detection. Copyright © 2021, The Authors. All rights reserved.

关键词： Semantic Segmentation

Image Manipulation Detection by Multi-View Multi-Scale Supervision

学校读者我要写书评

暂无评论

Image Manipulation Detection by Multi-View Multi-Scale Super...

International Conference on Computer Vision (ICCV)

作者： Xinru Chen Chengbo Dong Jiaqi Ji Juan Cao Xirong Li MoE Key Lab of Data Engineering and Knowledge Engineering Renmin University of China AIMC Lab School of Information Renmin University of China Institute of Computing Technology Chinese Academy of Sciences State Key Laboratory of Media Convergence Production Technology and Systems

ISBN: (纸本)9781665428132

关键词： Representation learning Image segmentation Computer vision Sensitivity Costs Image edge detection Semantics

A Survey on Service Route and Time Prediction in Instant Delivery: Taxonomy, Progress, and Prospects

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Wen, Haomin Lin, Youfang Wu, Lixia Mao, Xiaowei Cai, Tianyue Hou, Yunfeng Guo, Shengnan Liang, Yuxuan Jin, Guangyin Zhao, Yiji Zimmermann, Roger Ye, Jieping Wan, Huaiyu The Beijing Key Laboratory of Traffic Data Analysis and Mining School of Computer and Information Technology Beijing Jiaotong University Beijing100044 China The Key Laboratory of Intelligent Passenger Service of Civil Aviation CAAC Beijing101318 China The School of Computing National University of Singapore Singapore College of Systems Engineering National University of Defense Technology Changsha China The School of Information Science and Engineering Yunnan University Kunming650091 China The Cainiao Network Hangzhou China The Alibaba Group Hangzhou China INTR Thrust and DSA Thrust The Hong Kong University of Science and Technology Guangzhou China

Instant delivery services, such as food delivery and package delivery, have achieved explosive growth in recent years by providing customers with daily-life convenience. An emerging research area within these services is service Route&Time Prediction (RTP), which aims to estimate the future service route as well as the arrival time of a given worker. As one of the most crucial tasks in those service platforms, RTP stands central to enhancing user satisfaction and trimming operational expenditures on these platforms. Despite a plethora of algorithms developed to date, there is no systematic, comprehensive survey to guide researchers in this domain. To fill this gap, our work presents the first comprehensive survey that methodically categorizes recent advances in service route and time prediction. We start by defining the RTP challenge and then delve into the metrics that are often employed. Following that, we scrutinize the existing RTP methodologies, presenting a novel taxonomy of them. We categorize these methods based on three criteria: (i) type of task, subdivided into only-route prediction, only-time prediction, and joint route&time prediction;(ii) model architecture, which encompasses sequence-based and graph-based models;and (iii) learning paradigm, including Supervised Learning (SL) and Deep Reinforcement Learning (DRL). Conclusively, we highlight the limitations of current research and suggest prospective avenues. We believe that the taxonomy, progress, and prospects introduced in this paper can significantly promote the development of this field. © 2023, CC BY.

关键词： Taxonomies

Component Fault Diagnosability of Hierarchical Cubic Networks

学校读者我要写书评

暂无评论

ACM Transactions on Design Automation of Electronic Systems 2021年第3期28卷 1-19页

作者： Huang, Yanze Wen, Kui Lin, Limei Xu, Li Hsieh, Sun-Yuan Fujian Provincial Key Laboratory of Big Data Mining and Applications School of Computer Science and Mathematics Fujian University of Technology No. 3 Xueyuan Road Fujian Fuzhou China College of Computer and Cyber Security Fujian Normal University No. 8 Xuefu South Road Fujian Fuzhou350117 China Department of Computer Science and Information Engineering National Cheng Kung University No. 1 University Road Tainan70101 Taiwan

The fault diagnosability of a network indicates the self-diagnosis ability of the network, thus it is an important measure of robustness of the network. As a neoteric feature for measuring fault diagnosability, the r-component diagnosability ctr(G) of a network G imposes the restriction that the number of components is at least r in the remaining network of G by deleting faulty set X, which enhances the diagnosability of G. In this article, we establish the r-component diagnosability for n-dimensional hierarchical cubic network HCNn, and we show that, under both PMC model and MM∗model, the r-component diagnosability of HCNn is rn-½(r-1)r+1 for n≥ 2 and 1≤ r≤ n-1. Moreover, we introduce the concepts of 0-PMC subgraph and 0-MM∗subgraph of HCNn. Then, we make use of 0-PMC subgraph and 0-MM∗subgraph of HCNn to design two algorithms under PMC model and MM∗model, respectively, which are practical and efficient for component fault diagnosis of HCNn. Besides, we compare the r-component diagnosability of HCNn with the extra conditional diagnosability, diagnosability, good-neighbor diagnosability, pessimistic diagnosability, and conditional diagnosability, and we verify that the r-component diagnosability of HCNn is higher than the other types of diagnosability. © 2023 held by the owner/author(s). Publication rights licensed to ACM.

关键词： Failure analysis