检索结果-内蒙古大学图书馆

arXiv 2021年

作者： Deng, Yicheng Sun, Cheng Sun, Yongqi Zhu, Jiahui Key Lab of Big Data & Artificial Intelligence in Transportation Ministry of Education School of Computer and Information Technology Beijing Jiaotong University Beijing100044 China School of Information Science and Electrical Engineering Kyushu University Fukuoka8190395 Japan

3D human pose estimation from a single image is still a challenging problem despite the large amount of work that has been performed in this field. Generally, most methods directly use neural networks and ignore certain constraints (e.g., reprojection constraints, joint angle, and bone length constraints). While a few methods consider these constraints but train the network separately, they cannot effectively solve the depth ambiguity problem. In this paper, we propose a GAN-based model for 3D human pose estimation, in which a reprojection network is employed to learn the mapping of the distribution from 3D poses to 2D poses, and a discriminator is employed for 2D-3D consistency discrimination. We adopt a novel strategy to synchronously train the generator, the reprojection network and the discriminator. Furthermore, inspired by the typical kinematic chain space (KCS) matrix, we introduce a weighted KCS matrix and take it as one of the discriminator’s inputs to impose joint angle and bone length constraints. The experimental results on Human3.6M show that our method significantly outperforms state-of-the-art methods in most cases. © 2021, CC0.

关键词： Generative adversarial networks

来源：评论

学校读者我要写书评

暂无评论

Low-rank reduced biquaternion tensor ring decomposition and tensor completion

引用

Applied Mathematics and Computation 2025年 504卷

作者： Luo, Hui Liu, Xin Liu, Wei Zhang, Yang School of Computer Science and Engineering Faculty of Innovation Engineering Macau University of Science and Technology China Macau Institute of Systems Engineering Faculty of Innovation Engineering Macau University of Science and Technology China School of Artificial Intelligence at Sun Yat-sen University the Guangdong Key Laboratory of Big Data Analysis and Processing Guangzhou China Department of Mathematics University of Manitoba MB Canada

We define the reduced biquaternion tensor ring (RBTR) decomposition and provide a detailed exposition of the corresponding algorithm RBTR-SVD. Leveraging RBTR decomposition, we propose a novel low-rank tensor completion algorithm RBTR-TV integrating RBTR ranks with total variation (TV) regularization to optimize the process. Numerical experiments on color image and video completion tasks indicate the advantages of our method. © 2025 Elsevier Inc.

关键词： Numerical methods

来源：评论

学校读者我要写书评

暂无评论

Multi-view Point Cloud Registration based on Evolutionary Multitasking with Bi-Channel Knowledge Sharing Mechanism

arXiv

引用

arXiv 2022年

作者： Wu, Yue Liu, Yibo Gong, Maoguo Gong, Peiran Li, Hao Tang, Zedong Miao, Qiguang Ma, Wenping The School of Computer Science and Technology Key Laboratory of Big Data and Intelligent Vision Xidian University Xi’an710071 China The School of Electronic Engineering Key Laboratory of Intelligent Perception and Image Understanding Ministry of Education Xidian University Xi’an710071 China The School of Artificial Intelligence Key Laboratory of Intelligent Perception and Image Understanding Ministry of Education Xidian University Xi’an710071 China

Multi-view point cloud registration is fundamental in 3D reconstruction. Since there are close connections between point clouds captured from different viewpoints, registration performance can be enhanced if these connections be harnessed properly. Therefore, this paper models the registration problem as multi-task optimization, and proposes a novel bi-channel knowledge sharing mechanism for effective and efficient problem solving. The modeling of multi-view point cloud registration as multi-task optimization are twofold. By simultaneously considering the local accuracy of two point clouds as well as the global consistency posed by all the point clouds involved, a fitness function with an adaptive threshold is derived. Also a framework of the co-evolutionary search process is defined for the concurrent optimization of multiple fitness functions belonging to related tasks. To enhance solution quality and convergence speed, the proposed bi-channel knowledge sharing mechanism plays its role. The intra-task knowledge sharing introduces aiding tasks that are much simpler to solve, and useful information is shared across aiding tasks and the original tasks, accelerating the search process. The inter-task knowledge sharing explores commonalities buried among the original tasks, aiming to prevent tasks from getting stuck to local optima. Comprehensive experiments conducted on model object as well as scene point clouds show the efficacy of the proposed method. Copyright © 2022, The Authors. All rights reserved.

关键词： Multitasking

来源：评论

学校读者我要写书评

暂无评论

Predicting at-risk students in the early stage of a blended learning course via machine learning using limited data

引用

computers and Education: artificial intelligence 2024年 7卷

作者： Azizah, Zahra Ohyama, Tomoya Zhao, Xiumin Ohkawa, Yuichi Mitsuishi, Takashi Graduate School of Information Science Tohoku University 6-3-09 Aoba Aramaki-aza Aoba-ku Miyagi Sendai980-8579 Japan Department of Computer and Informatics Engineering Politeknik Negeri Jakarta Jl. Prof. DR. G.A. Siwabessy Kampus Universitas Indonesia Jawa Barat Depok16425 Indonesia Center for Data-driven Science and Artificial Intelligence Tohoku University 41 Kawauchi Aoba-ku Miyagi Sendai980-8576 Japan Institute for Excellence in Higher Education Tohoku University 41 Kawauchi Aoba-ku Miyagi Sendai980-8576 Japan Graduate School of Education Tohoku University 27-1 Kawauchi Aoba-ku Miyagi Sendai980-8576 Japan

Academic failure is a persistent challenge in education. Despite the limited available data, in this study, we focus on identifying at-risk students in a blended learning (BL) course. Several motivational variables are analyzed to determine their effect on student performance. We use a machine-learning classifier to compare two approaches: 1) The benchmark study, which uses data from the same academic year for both training and testing;and 2) a prospective study, which focuses on extrapolating a model trained on the previous fall semester to predict outcomes for the upcoming fall semester. We categorize the motivational variables, including time management and event-occurrence frequency. The window-expansion strategy is adopted to enhance performance through periodic evaluation to facilitate timely intervention. Consequently, the prospective approach is consistent with the benchmark results, thus demonstrating its generalizability across academic years and student populations. This approach is promising for identifying at-risk students in the BL course early. The Shapley additive explanations (SHAP) method emphasizes the importance of time-management variables, particularly study in time, for identifying at-risk students. This study enhances our understanding of early detection methods for at-risk students. By analyzing time-related behaviors, we establish a robust foundation for data-driven decisions to improve future BL implementations as well as support motivation and self-regulated learning practices. © 2024 The Author(s)

关键词： Students

来源：评论

学校读者我要写书评

暂无评论

Correction to: Dynamic clustering of spatial–temporal rainfall and temperature data over multi‑sites in Yemen using multivariate functional approach

引用

Stochastic Environmental Research and Risk Assessment 2024年第7期38卷 2611-2611页

作者： Hael, Mohanned Abduljabbar Ma, Haiqiang Al‑Sakkaf, Ali Salem Al-kuhali, Hamas A. Thobhani, Alaa Al‑selwi, Fahmi School of Statistics and Data Science Jiangxi University of Finance and Economics Nanchang China Department of Data Science and Information Technology Taiz University Taiz Yemen College of Earth and Planetary Sciences University of Chinese Academy of Sciences (UCAS) Beijing China School of Computer & Artificial Intelligence Wuhan University of Technology Wuhan China School of Computer Science and Engineering Central South University Changsha China

来源：评论

学校读者我要写书评

暂无评论

Leveraging Pre-Trained Visual Transformers for Multi-Band Photometric Light Curve Classification

arXiv

引用

arXiv 2025年

作者： Moreno-Cartagena, Daniel Protopapas, Pavlos Cabrera-Vives, Guillermo Cádiz-Leyton, Martina Becker, Ignacio Donoso-Oliva, Cristóbal Department of Computer Science Universidad de Concepción Edmundo Larenas 219 Concepción Chile Center for Data and Artificial Intelligence Universidad de Concepción Edmundo Larenas 310 Concepción Chile John A. Paulson School of Engineering and Applied Science Harvard University CambridgeMA02138 United States Heidelberg Institute for Theoretical Studies Baden-Württemberg Heidelberg Germany Nuncio Monseñor Sotero Sanz 100 Of. 104 Providencia Santiago Chile Chile Edinburgh Futures Institute University of Edinburgh 1 Lauriston Pl EdinburghEH3 9EF United Kingdom

Context. The advent of large-scale sky surveys, such as the Vera C. Rubin Observatory Legacy Survey of Space and Time (LSST), will generate vast volumes of photometric data, necessitating automatic classification of light curves to identify variable stars and transient events. However, challenges such as irregular sampling, multi-band observations, and diverse flux distributions across bands demand advanced models for accurate classification. Aims. This study investigates the potential of a pre-trained visual transformer (VT) model, specifically the Swin Transformer V2 (SwinV2), to classify photometric light curves without the need for feature extraction or multi-band preprocessing. The goal is to assess whether this image-based approach can accurately differentiate astronomical phenomena and if it can serve as a viable option for working with multi-band photometric light curves. Methods. We transformed each multi-band light curve into an image. These images serve as input to the SwinV2 model, which is pre-trained on ImageNet-21K. The datasets employed include the public Catalog of Variable Stars from the Massive Compact Halo Object (MACHO) survey, using both one and two bands, and the first round of the recent Extended LSST Astronomical Time-Series Classification Challenge (ELAsTiCC), which includes six bands. The model’s performance was evaluated on 6 classes for the MACHO dataset and 20 distinct classes of variable stars and transient events for the ELAsTiCC dataset. Results. The fine-tuned SwinV2 achieved better performance than models specifically designed for light curves, such as Astromer and the Astronomical Transformer for time series And Tabular data (ATAT). When trained on the Full MACHO dataset, it attained a macro F1-score of 80.2% and outperformed Astromer in single-band experiments. Incorporating a second band further improved performance, increasing the F1-score to 84.1%. In the ELAsTiCC dataset, SwinV2 achieved a macro F1-score of 65.5%, slightly su

关键词： Time series

来源：评论

学校读者我要写书评

暂无评论

Comparative analysis of FSO, OFC and diffused channel links in photonics using artificial intelligence based S-band, C-band and L-band of the attenuation metrics

引用

Optical and Quantum Electronics 2022年第7期54卷 420-420页

作者： Karpagarajesh, G. Santhana Krishnan, R. Harold Robinson, Y. Vimal, S. Thamizharasan, S. Subbulakshmi, P. Kaliappan, M. Department of Electronics and Communication Engineering Government College of Engineering Tirunelveli India Department of Electronics and Communication Engineering SCAD College of Engineering and Technology Tirunelveli India School of Information Technology and Engineering Vellore Institute of Technology Vellore India Department of Artificial Intelligence and Data Science Ramco Institute of Technology Rajapalayam India Department of ECE Sri Manakula Vinayagar Engineering College Puducherry Madagadipet 605107 India School of computer science and Engineering VIT Chennai India

Optical communication system is preferred over microwave and radio frequency communication system because of license free operation. Simulative analysis of 10gbps Optical Communication using different optical bands of L-Band S-Band, E-Band and C-Band under different attenuation condition has been performed in this paper. The Free Space Optics system has been analyzed with transmission distance of 1 km using Optical Wireless Communication channel and the effect of variation in attenuation value in the scenario of different weather conditions (clear, haze, rain and fog) were also examined. The Optical Fiber Communication is also examined under conditions of attenuations due to physical imperfections. The cross-layer artificial intelligence Framework is implemented to perform the prediction of different optical communication. The diffused channel is studied by varying the parameters of transmitter half angle and the distance of separation between the transmitter and the receiver. The attenuation effects of the links are also taken into consideration. Bit Error Rate and Quality factor performance of the different optical links are carried over at different wavelengths;thus the best link for the particular wavelength and the distance is identified. © 2022, The Author(s), under exclusive licence to Springer science+Business Media, LLC, part of Springer Nature.

关键词： Attenuation C-band FSO L-band Mach–Zehnder modulator OFC Quality factor S-band

来源：评论

学校读者我要写书评

暂无评论

Harmonizing Pathological and Normal Pixels for Pseudo-healthy Synthesis

arXiv

引用

arXiv 2022年

作者： Zhang, Yunlong Lin, Xin Zhuang, Yihong Sun, Liyan Huang, Yue Ding, Xinghao Wang, Guisheng Yang, Lin Yu, Yizhou The School of Informatics Xiamen University Xiamen361005 China The Institute of Artificial Intelligence Xiamen University Xiamen361005 China The School of Electronic Science and Engineering Xiamen University Xiamen361005 China The Department of Radiology The Third Medical Centre Chinese PLA General Hospital Beijing China The Deepwise AI Laboratory Beijing100125 China The Department of Computer Science The University of Hong Kong Hong Kong The School of Engineering Westlake University Hangzhou310012 China

Synthesizing a subject-specific pathology-free image from a pathological image is valuable for algorithm development and clinical practice. In recent years, several approaches based on the Generative Adversarial Network (GAN) have achieved promising results in pseudo-healthy synthesis. However, the discriminator (i.e., a classifier) in the GAN cannot accurately identify lesions and further hampers from generating admirable pseudo-healthy images. To address this problem, we present a new type of discriminator, the segmentor, to accurately locate the lesions and improve the visual quality of pseudo-healthy images. Then, we apply the generated images into medical image enhancement and utilize the enhanced results to cope with the low contrast problem existing in medical image segmentation. Furthermore, a reliable metric is proposed by utilizing two attributes of label noise to measure the health of synthetic images. Comprehensive experiments on the T2 modality of BraTS demonstrate that the proposed method substantially outperforms the state-of-the-art methods. The method achieves better performance than the existing methods with only 30% of the training data. The effectiveness of the proposed method is also demonstrated on the LiTS and the T1 modality of BraTS. The code and the pre-trained model of this study are publicly available at https://***/Au3C2/Generator-Versus-Segmentor. © 2022, CC BY.

关键词： Image enhancement

来源：评论

学校读者我要写书评

暂无评论

Double relaxed broad learning system for image classification

引用

Knowledge-Based Systems 2025年 324卷

作者： Zhenhao Qin Dengxiu Yu Junwei Jin C.L. Philip Chen Unmanned System Research Institute Northwestern Polytechnical University Xi’an 710072 China School of Artificial Intelligence OPtics and ElectroNics Northwestern Polytechnical University Xi’an 710072 China School of Artificial Intelligence and Big Data Henan University of Technology Zhengzhou 450001 China School of Computer Science and Engineering South China University of Technology Guangzhou 510641 China

The Broad Learning System (BLS), as a prominent network paradigm, has garnered significant attention across various domains in machine learning due to its remarkable efficiency and impressive performance. Nevertheless, two deficiencies exist when its variants are applied to supervised image classification tasks. First, they generally rely on rigid binary labels, which restricts the approximation procedure and fails to find the best classification margins. Second, using a single transformation matrix in graph-regularized BLS struggles to mitigate the overfitting problem. In this article, we focus on offering more freedom to the graph regularized BLS to explore appropriate margins between samples. Specifically, we learn the adaptive labels from data, and a marginalized constraint is implemented to enhance the distinguishability of the learned labels simultaneously. Subsequently, two distinct transformation matrices are employed for the graph embedding process, with the addition of a novel matrix designed to capture the similar structure between the transformations. The intra-class compactness of samples can be assured through experimental verification. Hence, a novel method named double relaxed BLS (DRBLS) is proposed. Further, with the help of the alternating direction method of multipliers, an efficient iterative approach is developed to find the closed-form solution. Experiments on diverse image classification tasks are conducted to certify the effectiveness of our method compared to state-of-the-art algorithms.

关键词： Broad learning system Double relaxed Optimization Similar structure Soft labels

来源：评论

学校读者我要写书评

暂无评论

Entropy-Based Characterization of Influence Pathways in Traditional and Social Media

Entropy-Based Characterization of Influence Pathways in Trad...

引用

International Conference on Collaborative Computing: Networking, Applications and Worksharing (CollaborateCom)

作者： Ozlem Ozmen Garibay Niloofar Yousefi Kevin Aslett Jacopo Baggio Erik Hemberg Chathura Jayalath Alexander Mantzaris Bruce Miller Una-May O’Reilly William Rand Chathurani Senevirathna Ivan Garibay Industrial Engineering & Management Systems University of Central Florida Orlando FL USA School of Politics Security and International Affairs University of Central Florida Orlando FL USA Computer Science & Artificial Intelligence Lab Massachusetts Institute of Technology Cambridge MA USA Statistics & Data Science Department University of Central Florida Orlando FL USA Poole School of Management North Carolina State University Raleigh NC USA

Despite much work on social media, analysis of individual influence campaigns, messages, and platforms, we lack the tools and techniques and fundamental research to effectively understand the information flows and their effects on the dynamics of the entire information ecosystem. For example, how information is amplified or dampened as it moves from one online community to another, how information is spinned or framed into narratives that favor or malign viewpoints organically or by foreign actors, how disinformation flows from fringe to mainstream communities, etc. We postulate that the information ecosystem is an attention economy, and that influence-the ability to gather attention towards a particular message or messages- is its currency. As a result, we model the information ecosystem as a complex network of influences flowing between actors, communities and platforms. This paper advocate for the use of information-theoretic entropic methods to model and characterize this complex network of influences over time: Influence Cascades Ecosystem (ICE). We envision leveraging the concept of influence cascades in conjunction with a novel geopolitical news-centric model of the information ecosystem in order to better understand the influence pathways by which various types of information (new articles from trusted, untrusted, fringe or mainstream sources) propagate across the social and traditional hybrid media environment.

关键词： Social networking (online) Ecosystems Collaboration Complex networks Media Internet Currencies

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：