检索结果-内蒙古大学图书馆

arXiv 2024年

作者： Ye, Mang Chen, Shuoyi Li, Chenyue Zheng, Wei-Shi Crandall, David Du, Bo National Engineering Research Center for Multimedia Software School of Computer Science Hubei Luojia Laboratory Wuhan University Wuhan China School of Data and Computer Science Sun Yat-sen University Guangzhou China Luddy School of Informatics Computing and Engineering Indiana University United States

Object Re-identification (Re-ID) aims to identify specific objects across different times and scenes, which is a widely researched task in computer vision. For a prolonged period, this field has been predominantly driven by deep learning technology based on convolutional neural networks. In recent years, the emergence of Vision Transformers has spurred a growing number of studies delving deeper into Transformer-based Re-ID, continuously breaking performance records and witnessing significant progress in the Re-ID field. Offering a powerful, flexible, and unified solution, Transformers cater to a wide array of Re-ID tasks with unparalleled efficacy. This paper provides a comprehensive review and in-depth analysis of the Transformer-based Re-ID. In categorizing existing works into Image/Video-Based Re-ID, Re-ID with limited data/annotations, Cross-Modal Re-ID, and Special Re-ID Scenarios, we thoroughly elucidate the advantages demonstrated by the Transformer in addressing a multitude of challenges across these domains. Considering the trending unsupervised Re-ID, we propose a new Transformer baseline, UntransReID, achieving state-of-the-art performance on both single/cross modal tasks. For the under-explored animal Re-ID, we devise a standardized experimental benchmark and conduct extensive experiments to explore the applicability of Transformer for this task and facilitate future research. Finally, we discuss some important yet under-investigated open issues in the large foundation model era, we believe it will serve as a new handbook for researchers in this field. A periodically updated website will be available at https://***/mangye16/ ReID-Survey. Copyright © 2024, The Authors. All rights reserved.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Weak Random Feature Method for Solving Partial Differential Equations

arXiv

引用

arXiv 2025年

作者： Kuvakin, Mikhail Mei, Zijian Chen, Jingrun Moscow Institute of Physics and Technology Russia School of Artificial Intelligence and Data Science Suzhou Institute for Advanced Research University of Science and Technology of China Suzhou China School of Mathematical Sciences Suzhou Institute for Advanced Research University of Science and Technology of China Suzhou Big Data & AI Research and Engineering Center Suzhou China

The random feature method (RFM) has demonstrated great potential in bridging traditional numerical methods and machine learning techniques for solving partial differential equations (PDEs). It retains the advantages of mesh-free approaches while achieving spectral accuracy for smooth solutions, without the need for iterative procedures. However, the implementation of RFM in the identification of weak solutions remains a subject of limited comprehension, despite crucial role of weak solutions in addressing numerous applied problems. While the direct application of RFM to problems without strong solutions is fraught with potential challenges, we propose an enhancement to the original random feature method that is specifically suited for finding weak solutions and is termed as Weak RFM. Essentially, Weak RFM reformulates the original RFM by adopting the weak form of the governing equations and constructing a new linear system through the use of carefully designed test functions, ensuring that the resulting solution satisfies the weak form by default. To rigorously evaluate the performance of the proposed method, we conduct extensive experiments on a variety of benchmark problems, including challenging three-dimensional cases, and compare its performance with state of the art machine learning-based approaches. The results demonstrate that Weak RFM achieves comparable or superior accuracy while significantly reducing computational time and memory consumption, highlighting its potential as a highly efficient and robust tool for finding weak solutions to various PDE problems. Copyright © 2025, The Authors. All rights reserved.

关键词： Iterative methods

来源：评论

学校读者我要写书评

暂无评论

Fitness Landscape Optimization Makes Stochastic Symbolic Search By Genetic Programming Easier

引用

IEEE Transactions on Evolutionary Computation 2024年

作者： Huang, Zhixing Mei, Yi Zhang, Fangfang Zhang, Mengjie Banzhaf, Wolfgang Victoria University of Wellington Centre for Data Science and Artificial Intelligence School of Engineering and Computer Science Wellington6140 New Zealand Michigan State University BEACON Center for the Study of Evolution in Action and Ecology Evolution and Behavior Program Department of Computer Science and Engineering East LansingMI48864 United States

Searching for symbolic models plays an important role in a wide range of domains such as neural architecture search and automatic program synthesis. Genetic programming is a promising stochastic method for searching effective symbolic models within an acceptable time. The genetic programming performance is closely related to the hardness of the fitness landscape. A better fitness landscape with less local optima normally implies that it is easier to search for better solutions. In recent years, there have been many studies enhancing genetic programming performance by forming better fitness landscapes. However, the better design of the fitness landscape highly relies on specific domain knowledge and consumes a lot of expert effort. This paper proposes a fitness landscape optimization method to automatically design better fitness landscapes for genetic programming search than the manually designed ones. We optimize the landscapes by optimizing the neighborhood structures of symbolic solutions. We verify the effectiveness of the proposed method in both supervised learning and combinatorial optimization problems. The results show that the proposed method significantly reduces the hardness of fitness landscapes. By simply searching against the automatically optimized fitness landscapes, a genetic programming method can have a very competitive performance with state-of-the-art methods. © 1997-2012 IEEE.

关键词： Genetic programming

来源：评论

学校读者我要写书评

暂无评论

Modeling viral evolution:A novel SIRSVIDE framework with application to SARS-CoV-2 dynamics

引用

hLife 2024年第5期2卷 227-245页

作者： Kaichun Jin Xiaolu Tang Zhaohui Qian Zhiqiang Wu Zifeng Yang Tao Qian Chitin Hon Jian Lu State Key Laboratory of Protein and Plant Gene Research Center for BioinformaticsSchool of Life SciencesPeking UniversityBeijingChina NHC Key Laboratory of Systems Biology of Pathogens Institute of Pathogen BiologyChinese Academy of Medical Sciences and Peking Union Medical CollegeBeijingChina State Key Laboratory of Respiratory Disease National Clinical Research Center for Respiratory DiseaseGuangzhou Institute of Respiratory HealthThe First Affiliated Hospital of Guangzhou Medical UniversityGuangdongChina Respiratory Disease AI Laboratory on Epidemic and Medical Big Data Instrument Applications Department of Engineering ScienceFaculty of Innovation EngineeringMacao University of Science and TechnologyMacaoChina Guangzhou Key Laboratory for Clinical Rapid Diagnosis and Early Warning of Infectious Diseases KingMed School of Laboratory MedicineGuangzhou Medical UniversityGuangdongChina Macao Center for Mathematical Sciences Macao University of Science and TechnologyMacaoChina Department of Engineering Science Faculty of Innovation EngineeringMacao University of Science and TechnologyMacaoChina

Understanding evolutionary trends in emerging viruses,such as severe acute respiratory syndrome coronavirus 2(SARS-CoV-2),is crucial for effective public health management and ***,extensive debates have arisen concerning viral evolutionary trends,particularly the interplay between transmissibility,pathogenicity,and immune *** this context,we have developed a novel computational model named SIRSVIDE(Susceptible-Infected-Recovered-Susceptible-Variation-Immune Decay-Immune Escape)to simulate the transmission and evolutionary dynamics of viral *** simulation results indicate that under conditions of high mutation rates,elevated transmission rates,and larger susceptible host populations,viral populations exhibit prolonged increases in transmissibility and immune escape,accompanied by reductions in pathogenicity and noticeable short-term fluctua***,when the total susceptible population size and mutation rate decrease,substantial uncertainty in the evolutionary trends of viral populations becomes *** summary,the SIRSVIDE model establishes a comprehensive framework for generating both short-and long-term viral epidemiological and evolutionary *** simulation outcomes align with existing evidence indicating that SARS-CoV-2 is undergoing selection for heightened transmissibility,decreased pathogenicity,and enhanced immune ***,the model sheds light on the possible evolutionary dynamics of other viruses.

关键词： viral evolution severe acute respiratory syndrome coronavirus 2(SARS-CoV-2) transmissibility-pathogenicity trade-off immune escape

来源：评论

学校读者我要写书评

暂无评论

CLDG: Contrastive Learning on Dynamic Graphs 39

CLDG: Contrastive Learning on Dynamic Graphs

引用

39th IEEE International Conference on data engineering, ICDE 2023

作者： Xu, Yiming Shi, Bin Ma, Teng Dong, Bo Zhou, Haoyi Zheng, Qinghua Xi'an Jiaotong University Department of Computer Science and Technology China Xi'an Jiaotong University Shaanxi Provincial Key Laboratory of Big Data Knowledge Engineering China Xi'an Jiaotong University Department of Distance Education China Beihang University School of Software China Beihang University Advanced Innovation Center for Big Data and Brain Computing China

ISBN: (纸本)9798350322279

The graph with complex annotations is the most potent data type, whose constantly evolving motivates further exploration of the unsupervised dynamic graph representation. One of the representative paradigms is graph contrastive learning. It constructs self-supervised signals by maximizing the mutual information between the statistic graph's augmentation views. However, the semantics and labels may change within the augmentation process, causing a significant performance drop in downstream tasks. This drawback becomes greatly magnified on dynamic graphs. To address this problem, we designed a simple yet effective framework named CLDG. Firstly, we elaborate that dynamic graphs have temporal translation invariance at different levels. Then, we proposed a sampling layer to extract the temporally-persistent signals. It will encourage the node to maintain consistent local and global representations, i.e., temporal translation invariance under the timespan views. The extensive experiments demonstrate the effectiveness and efficiency of the method on seven datasets by outperforming eight unsupervised state-of-the-art baselines and showing competitiveness against four semi-supervised methods. Compared with the existing dynamic graph method, the number of model parameters and training time is reduced by an average of 2,001.86 times and 130.31 times on seven datasets, respectively. The code and data are available at: https://***/yimingxu24/CLDG. © 2023 IEEE.

关键词： Graph neural networks

来源：评论

学校读者我要写书评

暂无评论

A Multi-Modal Behavior Quantitative Analysis Model for Autism Early Screening

A Multi-Modal Behavior Quantitative Analysis Model for Autis...

引用

2023 IEEE International Conference on Systems, Man, and Cybernetics, SMC 2023

作者： Lei, Jiayi Zhang, E. She, Yingying Wang, Xin Liao, Yuhan Hu, Bin Wu, Hang Yang, Minqiang Tian, Jiajia Wang, Yong School of Informatics Xiamen University China University of Kansas Medical Center Department of Occupational Therapy Education United States School of Film National Institute for Data Science in Health and Medicine Xiamen University China School of Computer Science and Technology Beijing Institute of Technology China Together Education Institute China School of Information Science and Engineering Lanzhou University China Fujian Medical University Union Hospital Pediatric Department China

ISBN: (纸本)9798350337020

Human-computer Interaction (HCI) and Machine Learning (ML) technologies have potential for the behavioral screening of autistic children but how to design a tool and analyse behavior reliably is challenging. Based on psychophysiological computation, this paper proposes an interactive behavior perception analytical model for autism screening. We presented the multi-scenario reactive behavior paradigms that designed based on the atypical characteristics of autistic children. We recorded the eye movement data and facial data of 91 participants, and performed multi-modal feature extraction, used machine learning to train classification model. We conducted comparative experiments, and the experimental results verified the advantages of multi-scenario paradigms and multi-modal feature groups, which indicates that our analysis methods and screening models are effective and reliable and have real research significance. © 2023 IEEE.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Tackling data Sparsity and Combinatorial Challenges in Rare Disease Matching with Medical Informed Machine Learning

Tackling Data Sparsity and Combinatorial Challenges in Rare ...

引用

2024 IEEE International Conference on Big data, Bigdata 2024

作者： Berger, Armin Lagones, Tom Anglim Grigull, Lorenz Fendrich, Lara Bell, Thiago Högl, Henriette Ernst, Gundula Schmidt, Ralf Bascom, David Sifa, Rafet Lübbering, Max Fraunhofer Iais Department of Media Engineering Germany University of Bonn Department of Computer Science Germany West-AI - Federal Ministry of Education and Research Germany Department of Health Queensland Australia Griffith University School of Medicine Australia University Hospital Bonn Center for Rare Diseases Germany Children's Network for Chronic Illnesses and Disabilities Germany Medical School Hannover Department of Medical Psychology Germany

ISBN: (纸本)9798350362480

With over 7,000 known rare diseases and a prevalence of less than one in a thousand, rare diseases pose substantial challenges to advanced medical support networks. This study investigates the efficacy of ***, a novel social networking platform designed for individuals affected by rare diseases, including patients, their family members, and medical professionals, addressing data sparsity and combinatorial complexities in user matching. We demonstrate that simple matching heuristics already serve as a decent basis for collecting user feedback on match quality. Leveraging over 10,000 user matching feedback scores from more than 2,000 active users, we evaluate algorithms including collaborative filtering and user embedding similarity with state-of-the-art Large Language Models (LLMs). With a top-10 and top-5 hit-rate of 55% and 37%, respectively, we show that a combination of medical data augmentation and embeddings significantly enhances performance beyond the initial heuristic baseline. © 2024 IEEE.

关键词： Collaborative filtering

来源：评论

学校读者我要写书评

暂无评论

Position: Bayesian Deep Learning is Needed in the Age of Large-Scale ai 41

Position: Bayesian Deep Learning is Needed in the Age of Lar...

引用

41st International Conference on Machine Learning, ICML 2024

作者： Papamarkou, Theodore Skoularidou, Maria Palla, Konstantina aitchison, Laurence Arbel, Julyan Dunson, David Filippone, Maurizio Fortuin, Vincent Hennig, Philipp Hernández-Lobato, José Miguel Hubin, Aliaksandr Immer, Alexander Karaletsos, Theofanis Khan, Mohammad Emtiyaz Kristiadi, Agustinus Li, Yingzhen Mandt, Stephan Nemeth, Christopher Osborne, Michael A. Rudner, Tim G.J. Rügamer, David Teh, Yee Whye Welling, Max Wilson, Andrew Gordon Zhang, Ruqi Department of Mathematics The University of Manchester Manchester United Kingdom Eric and Wendy Schmidt Center Broad Institute of MIT and Harvard Cambridge United States Spotify London United Kingdom Computational Neuroscience Unit University of Bristol Bristol United Kingdom Centre Inria de l'Université Grenoble Alpes Grenoble France Department of Statistical Science Duke University United States Statistics Program KAUST Saudi Arabia Helmholtz AI Munich Germany Department of Computer Science Technical University of Munich Munich Germany Munich Center for Machine Learning Munich Germany Tübingen AI Center University of Tübingen Tübingen Germany Department of Engineering University of Cambridge Cambridge United Kingdom Department of Mathematics University of Oslo Oslo Norway Bioinformatics and Applied Statistics Norwegian University of Life Sciences Ås Norway Department of Computer Science ETH Zurich Switzerland Chan Zuckerberg Initiative CA United States Center for Advanced Intelligence Project RIKEN Tokyo Japan Vector Institute Toronto Canada Department of Computing Imperial College London London United Kingdom Department of Computer Science UC Irvine Irvine United States Department of Mathematics and Statistics Lancaster University Lancaster United Kingdom Department of Engineering Science University of Oxford Oxford United Kingdom Center for Data Science New York University New York United States Department of Statistics LMU Munich Munich Germany DeepMind London United Kingdom Department of Statistics University of Oxford Oxford United Kingdom Informatics Institute University of Amsterdam Amsterdam Netherlands Courant Institute of Mathematical Sciences Center for Data Science Computer Science Department New York University New York United States Department of Computer Science Purdue University West Lafayette United States

In the current landscape of deep learning research, there is a predominant emphasis on achieving high predictive accuracy in supervised tasks involving large image and language datasets. However, a broader perspective reveals a multitude of overlooked metrics, tasks, and data types, such as uncertainty, active and continual learning, and scientific data, that demand attention. Bayesian deep learning (BDL) constitutes a promising avenue, offering advantages across these diverse settings. This paper posits that BDL can elevate the capabilities of deep learning. It revisits the strengths of BDL, acknowledges existing challenges, and highlights some exciting research avenues aimed at addressing these obstacles. Looking ahead, the discussion focuses on possible ways to combine large-scale foundation models with BDL to unlock their full potential. Copyright 2024 by the author(s)

关键词： Contrastive Learning

来源：评论

学校读者我要写书评

暂无评论

SELF-CLUSTERING GRAPH TRANSFORMER APPROACH TO MODEL RESTING STATE FUNCTIONAL BRaiN ACTIVITY

arXiv

引用

arXiv 2025年

作者： Thapaliya, Bishal Akbas, Esra Sapkota, Ram Ray, Bhaskar Calhoun, Vince Liu, Jingyu Department of Computer Science Georgia State University Atlanta United States Tri-Institutional Center for Translational Research in Neuroimaging and Data Science United States School of Electrical and Computer Engineering Georgia Institute of Technology Atlanta United States

Resting-state functional magnetic resonance imaging (rs-fMRI) offers valuable insights into the human brain’s functional organization and is a powerful tool for investigating the relationship between brain function and cognitive processes as it allows for the functional organization of the brain to be captured without relying on a specific task or stimuli. In this study, we introduce a novel attention mechanism for graphs with subnetworks, named Self Clustering Graph Transformer (SCGT), designed to handle the issue of uniform node updates in graph transformers. By using static functional connectivity (FC) correlation features as input to the transformer model, SCGT effectively captures the sub-network structure of the brain by performing cluster-specific updates to the nodes unlike uniform node updates like vanilla graph transformers, further allowing us to learn and interpret the subclusters. We validate our approach on the Adolescent Brain Cognitive Development (ABCD) dataset, comprising 7,957 participants, for the prediction of total cognitive score and gender classification. Our results demonstrate that SCGT outperforms the vanilla graph transformer method, and other recent models, offering a promising tool for modeling brain functional connectivity and interpreting the underlying subnetwork structures. © 2025, CC BY.

关键词： Distribution transformers

来源：评论

学校读者我要写书评

暂无评论

DACAD: Domain Adaptation Contrastive Learning for Anomaly Detection in Multivariate Time Series

引用

IEEE Transactions on Knowledge and data engineering 2025年

作者： Darban, Zahra Zamanzadeh Yang, Yiyuan Webb, Geoffrey I. Aggarwal, Charu C. Wen, Qingsong Pan, Shirui Salehi, Mahsa Monash University Department of Data Science and AI Melbourne Australia University of Oxford Department of Computer Science OxfordOX1 3SA United Kingdom Monash University Department of Data Science and AI Australia IBM T. J. Watson Research Center Yorktown Heights United States Squirrel Ai Learning Bellevue United States Griffith University School of ICT Australia

In time series anomaly detection (TSAD), the scarcity of labeled data poses a challenge to the development of accurate models. Unsupervised domain adaptation (UDA) offers a solution by leveraging labeled data from a related domain to detect anomalies in an unlabeled target domain. However, existing UDA methods assume consistent anomalous classes across domains. To address this limitation, we propose a novel Domain Adaptation Contrastive learning model for Anomaly Detection in multivariate time series (DACAD), combining UDA with contrastive learning. DACAD utilizes an anomaly injection mechanism that enhances generalization across unseen anomalous classes, improving adaptability and robustness. Additionally, our model employs supervised contrastive loss for the source domain and self-supervised contrastive triplet loss for the target domain, ensuring comprehensive feature representation learning and domain-invariant feature extraction. Finally, an effective center-based Entropy Classifier (CEC) accurately learns normal boundaries in the source domain. Extensive evaluations on multiple real-world datasets and a synthetic dataset highlight DACAD's superior performance in transferring knowledge across domains and mitigating the challenge of limited labeled data in TSAD. © 1989-2012 IEEE.

关键词： Self-supervised 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：