检索结果-内蒙古大学图书馆

39th Annual AAAI Conference on Artificial Intelligence, AAAI 2025

作者： Zhang, Zhi Liu, Yan Zhong, Sheng-Hua Chen, Gong Yang, Yu Cao, Jiannong The Hong Kong Polytechnic University Department of Computing 999077 Hong Kong Shenzhen University College of Computer Science and Software Engineering Guangdong Shenzhen518052 China The Education University of Hong Kong Centre for Learning Teaching and Technology 999077 Hong Kong

ISBN: (纸本)157735897X

Literature reviews play a crucial role in scientific research for understanding the current state of research, identifying gaps, and guiding future studies on specific topics. However, the process of conducting a comprehensive literature review is yet time-consuming. This paper proposes a novel framework, collaborative knowledge minigraph agents (CKMAs), to automate scholarly literature reviews. A novel prompt-based algorithm, the knowledge minigraph construction agent (KMCA), is designed to identify relations between concepts from academic literature and automatically constructs knowledge minigraphs. By leveraging the capabilities of large language models on constructed knowledge minigraphs, the multiple path summarization agent (MPSA) efficiently organizes concepts and relations from different viewpoints to generate literature review paragraphs. We evaluate CKMAs on three benchmark datasets. Experimental results show the effectiveness of the proposed method, further revealing promising applications of LLMs in scientific research. © 2025, Association for the Advancement of Artificial Intelligence (***). All rights reserved.

关键词： Knowledge engineering

来源：评论

学校读者我要写书评

暂无评论

High-Order Structure Embedding for Knowledge Hypergraph Completion

SSRN

引用

SSRN 2022年

作者： Wang, Peijie Chen, Jianrui Hao, Fei Wang, Zhihui Key Laboratory of Modern Teaching Technology Ministry of Education Xi’an China School of Computer Science Shaanxi Normal University Xi’an China

Knowledge hypergraph (KHG) completion aims to identify and predict new relations from existing data and perform filling task, thereby providing knowledge services for many downstream tasks. Recently, neural network methods have been introduced into KHG and achieved good research results. However, there exist some problems with neural network methods on KHG: (i) they only consider the influence of the direct neighbor nodes information, (ii) ignoring the more complex interaction information widely existing inside high- order facts. To address these limitations, we propose a novel method based on High-order HyerGraph Convolutional Network(HyperGCN) and Feature Fusion ,termed HoGCNF^2 , to efficiently learn high-order neighbor information and interactive information. On one hand, a dual-channel HyperGCN including important information aggregation HyperGCN (I-HGCN) and high-order information aggregation HyperGCN (H-HGCN) is developed. I-HGCN considers information aggregation of entities with greater influence, while H-HGCN considers high-order information aggregation of entities and relations. On the other hand, different types of high-order structure features existing inside the facts are further integrated by feature fusion strategy. In addition, this work also incorporates an attention mechanism to adaptively assign different weights to the learned embeddings. Finally, to verify the effectiveness of the algorithm, we perform ablation analysis, parameter sensitivity analysis and comparation experiment with state-of-the-art KHG completion algorithms over the FB-AUTO, JF17K and WikiPeople datasets. Extensive experiments demonstrate the superiority of the proposed approach on unfixed datasets and fixed datasets. Particularly, the MRR result of HoGCNF 2 for unfixed datset FB-AUTO is up to 0.897 and for fixed dataset WikiPeople-4 is up to 0.429, which outperform the best method currently available in the literature. The significance and influence of each parameter on the mo

关键词： Embeddings

来源：评论

学校读者我要写书评

暂无评论

Automated Arabic Text Classification Using Hyperparameter Tuned Hybrid Deep Learning Model

引用

computers, Materials & Continua 2023年第3期74卷 5447-5465页

作者： Badriyya B.Al-onazi Saud S.Alotaib Saeed Masoud Alshahrani Najm Alotaibi Mrim M.Alnfiai Ahmed S.Salama Manar Ahmed Hamza Department of Language Preparation Arabic Language Teaching InstitutePrincess Nourah bint Abdulrahman UniversityP.O.Box 84428Riyadh11671Saudi Arabia Department of Information Systems College of Computing and Information SystemUmm Al-Qura UniversitySaudi Arabia Department of Computer Science College of Computing and Information TechnologyShaqra UniversityShaqraSaudi Arabia Prince Saud AlFaisal Institute for Diplomatic Studies Saudi Arabia Department of Information Technology College of Computers and Information TechnologyTaif UniversityTaif P.O.Box 11099Taif21944Saudi Arabia Department of Electrical Engineering Faculty of Engineering&TechnologyFuture University in EgyptNew Cairo11845Egypt Department of Computer and Self Development Preparatory Year DeanshipPrince Sattam bin Abdulaziz UniversityAlKharjSaudi Arabia

The text classification process has been extensively investigated in various languages,especially *** classification models are vital in several Natural Language Processing(NLP)*** Arabic language has a lot of *** instance,it is the fourth mostly-used language on the internet and the sixth official language of ***,there are few studies on the text classification process in Arabic.A few text classification studies have been published earlier in the Arabic *** general,researchers face two challenges in the Arabic text classification process:low accuracy and high dimensionality of the *** this study,an Automated Arabic Text Classification using Hyperparameter Tuned Hybrid Deep Learning(AATC-HTHDL)model is *** major goal of the proposed AATC-HTHDL method is to identify different class labels for the Arabic *** first step in the proposed model is to pre-process the input data to transform it into a useful *** Term Frequency-Inverse Document Frequency(TF-IDF)model is applied to extract the feature ***,the Convolutional Neural Network with Recurrent Neural Network(CRNN)model is utilized to classify the Arabic *** the final stage,the Crow Search Algorithm(CSA)is applied to fine-tune the CRNN model’s hyperparameters,showing the work’s *** proposed AATCHTHDL model was experimentally validated under different parameters and the outcomes established the supremacy of the proposed AATC-HTHDL model over other approaches.

关键词： Hybrid deep learning natural language processing arabic language text classification parameter tuning

来源：评论

学校读者我要写书评

暂无评论

Generalizable Face Landmarking Guided by Conditional Face Warping

Generalizable Face Landmarking Guided by Conditional Face Wa...

引用

Conference on computer Vision and Pattern Recognition (CVPR)

作者： Jiayi Liang Haotian Liu Hongteng Xu Dixin Luo School of Computer Science and Technology Beijing Institute of Technology Beijing Gaoling School of Artificial Intelligence Renmin University of China Beijing Beijing Key Laboratory of Big Data Management and Analysis Methods Beijing Key Laboratory of Artificial Intelligence Ministry of Education Shanghai

ISBN: (数字)9798350353006

ISBN: (纸本)9798350353013

As a significant step for human face modeling, editing, and generation, face landmarking aims at extracting facial keypoints from images. A generalizable face landmarker is required in practice because real-world facial images, e.g., the avatars in animations and games, are often stylized in various ways. However, achieving generalizable face land-marking is challenging due to the diversity of facial styles and the scarcity of labeled stylized faces. In this study, we propose a simple but effective paradigm to learn a generalizable face landmarker based on labeled real human faces and unlabeled stylized faces. Our method learns the face landmarker as the key module of a conditional face warper. Given a pair of real and stylized facial images, the conditional face warper predicts a warping field from the real face to the stylized one, in which the face landmarker predicts the ending points of the warping field and provides us with high-quality pseudo landmarks for the corresponding stylized facial images. Applying an alternating optimization strategy, we learn the face landmarker to minimize i) the discrepancy between the stylized faces and the warped real ones and ii) the prediction errors of both real and pseudo landmarks. Experiments on various datasets show that our method outperforms existing state-of-the-art domain adaptation methods in face landmarking tasks, leading to a face landmarker with better generalizability. Code is available at https://***/project-face-landmarker.

关键词： computer vision Codes Zero-shot learning Face recognition Computational modeling Avatars Games

来源：评论

学校读者我要写书评

暂无评论

Modelling the Psychological Impact of COVID-19 in Saudi Arabia Using Machine Learning

引用

computers, Materials & Continua 2021年第5期67卷 2029-2047页

作者： Mohammed A.Aleid Khaled A.Z.Alyamani Mohieddine Rahmouni Theyazn H.H.Aldhyani Nizar Alsharif Mohammed Y.Alzahrani College of Education King Faisal UniversityAl-Ahsa31982Saudi Arabia Community College in Abqaiq King Faisal UniversityAl-Ahsa31982Saudi Arabia Department of Economics and Quantitative Methods ESSECTUniversity of TunisTunisTunisia Department of Computer Engineering and Science Al-Baha UniversityAl-BahahSaudi Arabia

This article aims to assess health habits,safety behaviors,and anxiety factors in the community during the novel coronavirus disease(COVID-19)pandemic in Saudi Arabia based on primary data collected through a questionnaire with 320 *** other words,this paper aims to provide empirical insights into the correlation and the correspondence between sociodemographic factors(gender,nationality,age,citizenship factors,income,and education),and psycho-behavioral effects on individuals in response to the emergence of this new *** focus on the interaction between these variables and their effects,we suggest different methods of analysis,comprising regression trees and support vector machine regression(SVMR)*** to the regression tree results,the age variable plays a predominant role in health habits,safety behaviors,and *** health habit index,which focuses on the extent of behavioral change toward the commitment to use the health and protection methods,is highly affected by gender and age *** average monthly income is also a relevant factor but has contrasting effects during the COVID-19 pandemic *** results of the SVMR model reveal a strong positive effect of income,with R^(2) values of 99.59%,99.93%and 99.88%corresponding to health habits,safety behaviors,and anxiety.

关键词： COVID-19 health habits safety behaviors anxiety support vector machine regression regression trees

来源：评论

学校读者我要写书评

暂无评论

Algorithm for globally identifiable reparametrizations of ODEs

arXiv

引用

arXiv 2024年

作者： Falkensteiner, Sebastian Ovchinnikov, Alexey Sendra, J. Rafael Max Planck Institute for Mathematics in The Sciences Leipzig Germany Department of Mathematics CUNY Queens College Ph.D. Programs in Mathematics and Computer Science CUNY Graduate Center New York United States Department of Quantitative Methods CUNEF-University Spain

Structural global parameter identifiability indicates whether one can determine a parameter’s value in an ODE model from given inputs and outputs. If a given model has parameters for which there is exactly one value, such parameters are called globally identifiable. Given an ODE model involving not globally identifiable parameters, first we transform the system into one with locally identifiable parameters. As a main contribution of this paper, then we present a procedure for replacing, if possible, the ODE model with an equivalent one that has globally identifiable parameters. We first derive this as an algorithm for one-dimensional ODE models and then reuse this approach for higher-dimensional *** Codes 93C15, 93B25, 93B30, 34A55, 14E08, 14M20, 14Q20, 12H05, 92B05 © 2024, CC BY-NC-SA.

关键词： Observability

来源：评论

学校读者我要写书评

暂无评论

A Two-Layer Trilateral Teleoperation Architecture for Mentoring in Surgical Training

引用

IFAC-PapersOnLine 2021年第19期54卷 267-274页

作者： Marco Minelli Filippo Loschi Federica Ferraguti Cristian Secchi Department of Sciences and Methods of Engineering University of Modena and Reggio Emilia Italy Department of Computer Science University of Verona Italy

In this paper we propose a novel trilateral dual-master-single-slave teleoperation control architecture that can be used for the training of novice surgeons in surgical procedures. Starting from the concept of energy tank, we propose a flexible and stable trilateral interconnection over a delayed communication channel between the masters and the slave. Exploiting the flexibility provided by the controller, we design a training strategy for novice surgeons. The proposed architecture is experimentally validated.

关键词： Teleoperation Stability of nonlinear systems Passivity-based control Telepresence Robots manipulators

来源：评论

学校读者我要写书评

暂无评论

Continual Test-Time Adaptation for Single Image Defocus Deblurring via Causal Siamese Networks

arXiv

引用

arXiv 2025年

作者： Cui, Shuang Li, Yi Li, Jiangmeng Tang, Xiongxin Su, Bing Xu, Fanjiang Xiong, Hui National Key Laboratory of Space Integrated Information System Institute of Software Chinese Academy of Sciences University of Chinese Academy of Sciences China Beijing Key Laboratory of Big Data Management and Analysis Methods Gaoling School of Artificial Intelligence Renmin University of China China Department of Computer Science & Engineering the Hong Kong University of Science and Technology Hong Kong

Single image defocus deblurring (SIDD) aims to restore an all-in-focus image from a defocused one. Distribution shifts in defocused images generally lead to performance degradation of existing methods during out-of-distribution inferences. In this work, we gauge the intrinsic reason behind the performance degradation, which is identified as the heterogeneity of lens-specific point spread functions. Empirical evidence supports this finding, motivating us to employ a continual test-time adaptation (CTTA) paradigm for SIDD. However, traditional CTTA methods, which primarily rely on entropy minimization, cannot sufficiently explore task-dependent information for pixel-level regression tasks like SIDD. To address this issue, we propose a novel Siamese networks-based continual test-time adaptation framework, which adapts source models to continuously changing target domains only requiring unlabeled target data in an online manner. To further mitigate semantically erroneous textures introduced by source SIDD models under severe degradation, we revisit the learning paradigm through a structural causal model and propose Causal Siamese networks (CauSiam). Our method leverages large-scale pre-trained vision-language models to derive discriminative universal semantic priors and integrates these priors into Siamese networks, ensuring causal identifiability between blurry inputs and restored images. Extensive experiments demonstrate that CauSiam effectively improves the generalization performance of existing SIDD methods in continuously changing domains. Copyright © 2025, The Authors. All rights reserved.

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

Assessor-Guided Learning for Continual Environments

arXiv

引用

arXiv 2023年

作者： Ma’sum, Muhammad Anwar Pratama, Mahardhika Lughofer, Edwin Ding, Weiping Jatmiko, Wisnu STEM University of South Australia Adelaide Australia The Institute of Mathematical Methods in Medicine and Databased Modeling Johannes Kepler University Linz Austria Nantong University China Faculty of Computer Science University of Indonesia Jakarta Indonesia

This paper proposes an assessor-guided learning strategy for continual learning where an assessor guides the learning process of a base learner by controlling the direction and pace of the learning process thus allowing an efficient learning of new environments while protecting against the catastrophic interference problem. The assessor is trained in a meta-learning manner with a meta-objective to boost the learning process of the base learner. It performs a soft-weighting mechanism of every sample accepting positive samples while rejecting negative samples. The training objective of a base learner is to minimize a meta-weighted combination of the cross entropy loss function, the dark experience replay (DER) loss function and the knowledge distillation loss function whose interactions are controlled in such a way to attain an improved performance. A compensated oversampling (COS) strategy is developed to overcome the class imbalanced problem of the episodic memory due to limited memory budgets. Our approach, Assessor-Guided Learning Approach (AGLA), has been evaluated in the class-incremental and task-incremental learning problems. AGLA achieves improved performances compared to its competitors while the theoretical analysis of the COS strategy is offered. Source codes of AGLA, baseline algorithms and experimental logs are shared publicly in https://***/anwarmaxsum/AGLA for further study. © 2023, CC BY-NC-SA.

关键词： Distillation

来源：评论

学校读者我要写书评

暂无评论

Multisensor Selection for Multitarget Tracking Based on Information Divergence 10

Multisensor Selection for Multitarget Tracking Based on Info...

引用

10th International Conference on Control, Automation and Information sciences, ICCAIS 2021

作者： Zhu, Yun Liang, Shuang Yang, Honghong Wu, Xiaojun School of Computer Science Shaanxi Normal University Key Laboratory of Modern Teaching Technology Ministry of Education Xi'an China Academy of Advanced Interdisciplinary Research Xidian University Xi'an China

ISBN: (纸本)9781665440295

This paper presents a novel information divergence based multisensor selection approach for multitarget tracking. Multitarget states are modelled as multi-Bernoulli random finite sets and multisensor selection is studied under the partially observed Markov decision process (POMDP) framework. Multisensor selection under POMDP is essentially a global combinatorial optimization problem that is challenging when the number of sensors is large. To avoid the complicated combinational optimization, the selection of multisensor is divided into sub-selection of each individual sensor. Informative sensors are selected sequentially from the candidates, and the Rényi divergence between prior and posterior multi-Bernoulli density is used as the selection criterion. Simulation results validate the effectiveness and efficiency of the proposed approach. © 2021 IEEE.

关键词： Markov processes

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：