检索结果-内蒙古大学图书馆

29th International Computing and Combinatorics Conference, COCOON 2023

作者： Hellmuth, Marc Scholz, Guillaume E. Department of Mathematics Faculty of Science Stockholm University Stockholm10691 Sweden Bioinformatics Group Department of Computer Science and Interdisciplinary Center for Bioinformatics Universität Leipzig Leipzig04107 Germany

ISBN: (纸本)9783031491894

The class of Galled-Tree Explainable (GaTEx) graphs has just recently been discovered as a natural generalization of cographs. Cographs are precisely those graphs that can be uniquely represented by a rooted tree where the leaves of the tree correspond to the vertices of the graph. As a generalization, GaTEx graphs are precisely those graphs that can be uniquely represented by a particular rooted directed acyclic graph (called galled-tree). We consider here four prominent problems that are, in general, NP-hard: computing the size ω(G) of a maximum clique, the size χ(G) of an optimal vertex-coloring and the size α(G) of a maximum independent set of a given graph G as well as determining whether a graph is perfectly orderable. We show here that ω(G), χ(G), α(G) can be computed in linear-time for GaTEx graphs G. The crucial idea for the linear-time algorithms is to avoid working on the GaTEx graphs G directly, but to use the galled-trees that explain G as a guide for the algorithms to compute these invariants. In particular, we show first how to employ the galled-tree structure to compute a perfect ordering of GaTEx graphs in linear-time which is then used to determine ω(G), χ(G), α(G). © The Author(s), under exclusive license to Springer Nature Switzerland AG 2024.

关键词： Clustering algorithms

来源：评论

学校读者我要写书评

暂无评论

BeLLE: Detecting National Differences in Computational Thinking and computer science Through an International Challenge 7th

BeLLE: Detecting National Differences in Computational Thin...

引用

7th International Conference on Creative Mathematical sciences Communication, CMSC 2024

作者： Kaarto, Heidi Bilbao, Javier Pears, Arnold Dagienė, Valentina Kilpi, Janica Parviainen, Marika Pluhár, Zsuzsa Gülbahar, Yasemin Laakso, Mikko-Jussi Turku Research Institute for Learning Analytics University of Turku Turku Finland Bilbao Spain KTH Royal Institute of Technology Stockholm Sweden Vilnius University Institute of Educational Sciences Vilnius Lithuania Eötvös Loránd University Budapest Hungary Teachers College Columbia University New York United States

ISBN: (纸本)9783031732560

The Bebras challenge is an international initiative to engage school pupils with computer science and computational thinking via an annual challenge designed by computer science experts and educators. BeLLE is an international consortium focusing on international comparisons of standard challenge task banks. The consortium uses the ViLLE platform to manage the challenge as it offers a digital exercise-based learning environment with comprehensive learning analytics. The goal is to learn more about students’ knowledge in computer science and computational thinking in order to provide information for curriculum development and other educational planning and research. BeLLE started in 2021 with a pilots in Hungary and India. After the successful pilot, the consortium expanded substantially in the following year, many multiple choice questions were transformed into interactive tasks, and the process of organizing the challenge in ViLLE was refined. In this paper, we present some results of the challenge conducted within the BeLLE consortium in 2022. Over 90,000 students (47 % girls, 53 % boys) participated in the challenge in total through BeLLE. The results show that most students across countries and age groups get less than half of the maximum scores. The difference between girls and boys become apparent in Hungary and Lithuania: in the two oldest age groups (14–16 and 16–19 years old) boys score higher than girls. The time spent on the challenge is often 30 to 40 min with a difference between girls and boys in Hungary and Lithuania: boys use either less or more time than girls. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2025.

关键词： Contrastive Learning

来源：评论

学校读者我要写书评

暂无评论

Progressive Multiscale Attention Network for Diabetic Retinopathy 24th

Progressive Multiscale Attention Network for Diabetic Retin...

引用

24th International Conference on Algorithms and Architectures for Parallel Processing, ICA3PP 2024

作者： Zhou, Qiuji Guo, Yongde Liu, Yifeng Lin, YanZhen Faculty of Data Science City university of Macau China Faculty of Innovation Engineering Macau University of Science and Technology China

ISBN: (纸本)9789819615476

Given the time-intensive nature of manual fundus examination and its significant dependence on expert knowledge, the task of computer-aided multi-classification of diabetic retinopathy (DR) severity is of crucial importance. However, the application of multi-classification for DR severity remains limited by a scarcity of high-quality training data, despite its potential. Moreover, challenges such as suboptimal data quality, ambiguous pathological characteristics, and minimal dissimilarity among categories are prevalent. Further research on image preprocessing methods is necessary. This study proposes a new framework for diabetic retinopathy classification, PMADR-Net (Progressive Multiscale Attention Network for Diabetic Retinopathy). By applying progressive multiscale training and attention mechanisms, this framework is suitable for few-shot medical image classification. It could automatically shift its focus towards learning samples of pathological features that are more challenging to discriminate. Moreover, in order to mitigate the class imbalance in the dataset, this research employs a balanced sampling approach and a patch reconstruction technique to produce multiscale features, thereby facilitating the model’s accurate differentiation of each category. Our proposed model achieved a classification accuracy of 93.97% and an AUC evaluation metric of 0.9850, demonstrating its superior effectiveness over state-of-the-art techniques and showing potential for widespread application in similar medical classification tasks involving small datasets. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

关键词： Contrastive Learning

来源：评论

学校读者我要写书评

暂无评论

AffViT: Fast Affine Medical Image Registration with Convolutional Vision Transformer 21st

AffViT: Fast Affine Medical Image Registration with Convolu...

引用

21st Pacific Rim International Conference on Artificial Intelligence, PRICAI 2024

作者： Shen, Chaomin Huang, Hao Zhou, Zhongyi School of Computer Science and Technology East China Normal University Shanghai China

ISBN: (纸本)9789819601219

Affine registration is a key component in a wide range of medical image processing frameworks and is extensively applied in clinical settings. Nevertheless, recent works often emphasize the integration of affine and deformable registration, resulting in the standalone performance of affine registration being underexplored. Despite its clinical significance, affine registration faces two major challenges: it involves larger transformations compared to deformable registration, and it requires fast runtime for high-resolution 3D medical images to meet real-time clinical demands. To address these challenges, we introduce a Transformer block into the CNN-based affine registration network to effectively model the long-range dependencies in high-level features. This integration also preserves the CNN’s ability to capture local features while avoiding the high computational cost of a full Transformer architecture. Moreover, for the CNN stage, we use a Siamese network to extract low-level features for fixed and moving images. We also add parallel convolution branches to enhance the receptive field of convolution operations. Experiments on common and practical affine registration tasks, i.e., template-matching normalization and atlas-based registration, demonstrate that our method achieves higher registration accuracy than the state-of-the-art methods while being 10 times faster and having only half of the model parameters. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

关键词： Template matching

来源：评论

学校读者我要写书评

暂无评论

GWUNet: A UNet with Gated Attention and Improved Wavelet Transform for Thyroid Nodules Segmentation 31st

GWUNet: A UNet with Gated Attention and Improved Wavelet Tra...

引用

31st International Conference on Multimedia Modeling, MMM 2025

作者： Zheng, Shuijing Yu, Suxi Wang, Yi Wen, Jing College of Computer Science Chongqing University Chongqing401331 China

ISBN: (纸本)9789819620609

Thyroid nodules are a common high-incidence disease of the thyroid. Therefore, the precise segmentation of thyroid nodules in ultrasound images is crucial for the clinical auxiliary diagnosis of thyroid diseases. However, the boundary between thyroid nodules and surrounding tissue is indistinct and exhibits high variability, which lead to unsatisfactory segmentation performance. To tackle this issue, we propose the U-shaped segmentation network (GWUNet) combining gated attention and improved wavelet transform. In this network, we introduce a gated attention mechanism module based on Swin-Transformer, which enables the network to fully learn the location information. Furthermore, we design a wavelet transform module based on a frequency domain selection mechanism. This module is capable of simultaneously learning features from both the frequency domain and the spatial domain, thereby enhancing the ability to extract texture features of thyroid nodules. The proposed network (GWUNet) is evaluated on two thyroid nodules datasets, including the hospital-collected dataset and the open dataset DDTI, and it is shown that it achieves better segmentation performance compared to other state-of-the-art networks. The code is available at https://***/Shuijing2018/GWUNet. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

关键词： Frequency domain analysis

来源：评论

学校读者我要写书评

暂无评论

Highway Gates Dynamic Adaptation Network For Knowledge Graph Entity Alignment 21st

Highway Gates Dynamic Adaptation Network For Knowledge Graph...

引用

21st Pacific Rim International Conference on Artificial Intelligence, PRICAI 2024

作者： Yusuf, Nursharbat Yilahun, Hankiz Imam, Seyyare Hamdulla, Askar School of Computer Science and Technology Xinjiang University Urumqi830017 China Xinjiang Key Laboratory of Multilingual Information Technology Urumqi830017 China School of National Security Studies Xinjiang University Urumqi830017 China

ISBN: (纸本)9789819601240

The Entity alignment aims to align entities across different Knowledge Graphs and plays an important role in knowledge fusion tasks. In recent years, existing methods have typically used multiple aspects of information to enhance the accuracy of matching, which makes the matching process more comprehensive. However, existing methods that integrate multiple features have relied on fixed weighting strategies, making it challenging to adjust the relative importance of each feature. Therefore, this paper proposes an entity alignment framework(HGEA) based on highway gates dynamic adaptive network. Firstly, HGEA aggregates the structure, name, and node importance of entities. Among them, to fully utilize of the structural information of the Knowledge Graphs, we propose an entity and relation representation strategy based on a graph attention network. Then, we have a highway gates dynamic adaptation network, which combines the gating mechanism and multi-level self-attention to dynamically adjust the weight of each feature to adapt to the information flow of different entity features and optimize the entity alignment. Experiments on three real-world cross-lingual datasets demonstrate that our framework surpasses the current state-of-the-art methods. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

关键词： Knowledge graph

来源：评论

学校读者我要写书评

暂无评论

A Robust Preprocessing Method for Measuring Image Visual Quality Using Log-Polar FFT Features 8th

A Robust Preprocessing Method for Measuring Image Visual Qua...

引用

8th International Congress on Artificial Intelligence and Pattern Recognition, IWAIPR 2023

作者： Chen, Guang Yi Krzyzak, Adam Valev, Ventzeslav Department of Computer Science and Software Engineering Concordia University MontrealQCH3G 1M8 Canada Institute of Mathematics and Informatics Bulgarian Academy of Sciences Sofia1113 Bulgaria

ISBN: (纸本)9783031495519

To register two images, existing methods normally estimate the parameters of an affine transform, and then perform an inverse affine transform to the test image by using the estimated parameters. Any metric can then be applied to the reference image and the normalized image. In this paper we propose a new method for measuring visual image quality which circumvents the need to estimate the parameters of the affine transform. Instead, we use the log-polar transform and the fast Fourier transform (FFT) to extract features that are invariant to translation, rotation, and scaling. We apply the existing structural similarity index measure (SSIM) to the two invariant feature images, where no inverse transform is needed. Experimental results show that our proposed method outperforms the standard metric, the mean SSIM (MSSIM), significantly in terms of visual quality scores. © 2024, The Author(s), under exclusive license to Springer Nature Switzerland AG.

关键词： image visual quality quality metrics rotation invariance scale invariance translation invariance

来源：评论

学校读者我要写书评

暂无评论

A Hybrid Centralized-Peer Authentication System Inspired by Block-Chain

Lecture Notes on Data Engineering and Communications Technol...

引用

lecture notes on Data Engineering and Communications Technologies 2023年 180卷 271-287页

作者： Anabtawi, Wasim Maqboul, Ahmad Othman Othman, M.M. Computer Science Department An-Najah National University Nablus Palestine

The process of identifying and authenticating people is considered to be a crucial task nowadays. However, this ease of use comes with its own problems;like identity theft and identity fraud. Which, might be exploited by means like;the collusion of a corrupt authenticating organization, or internal fraud within the authenticating organization, or by a manipulative majority in case of multipleauthenticators. The proposed system will be an attempt to deflect such cases by establishing an unbiased organizational authentication system. This work illustrates a design of a hybrid authenticating system that does not have a single actor that carries out the whole authentication process. Instead, it will borrow the concept of authenticating peers from the block-chain technology and utilize it with the architecture of centralized authenticating system. Security analysis of the proposed system shows its effectiveness against various types of attacks and scenarios. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2023.

关键词： Authentication

来源：评论

学校读者我要写书评

暂无评论

On Identifiability of BN2A Networks 17th

On Identifiability of BN2A Networks

引用

17th European Conference on Symbolic and Quantitative Approaches to Reasoning with Uncertainty, ECSQARU 2023

作者： Pérez, Iván Vomlel, Jiří Institute of Information Theory and Automation Czech Academy of Sciences Prague Czech Republic Institute of Computer Science Czech Academy of Sciences Prague Czech Republic

ISBN: (纸本)9783031456077

In this paper, we consider two-layer Bayesian networks. The first layer consists of hidden (unobservable) variables and the second layer consists of observed variables. All variables are assumed to be binary. The variables in the second layer depend on the variables in the first layer. The dependence is characterised by conditional probability tables representing Noisy-AND or simple Noisy-AND. We will refer to this class of models as BN2A models. We found that the models known in the Bayesian network community as Noisy-AND and simple Noisy-AND are also used in the cognitive diagnostic modelling known in the psychometric community under the names of RRUM and DINA, respectively. In this domain, the hidden variables of BN2A models correspond to skills and the observed variables to students’ responses to test questions. In this paper we analyse the identifiability of these models. Identifiability is an important concept because without it we cannot hope to learn correct models. We present necessary conditions for the identifiability of BN2As with Noisy-AND models. We also propose and test a numerical approach for testing identifiability. © 2024, The Author(s), under exclusive license to Springer Nature Switzerland AG.

关键词： Bayesian networks

来源：评论

学校读者我要写书评

暂无评论

Contour-Guided Context Learning for Scene Text Recognition 27th

Contour-Guided Context Learning for Scene Text Recognition

引用

27th International Conference on Pattern Recognition, ICPR 2024

作者： Hsieh, Wei-Chun Hsu, Gee-Sern Chen, Jun-Yi Yap, Moi Hoon Chao, Zi-Chun National Taiwan University of Science and Technology Taipei City Taiwan Manchester Metropolitan University Manchester United Kingdom

ISBN: (纸本)9783031784972

We propose contour-guided context learning (CCL) for bilingual scene text recognition (STR). The CCL framework consists of three parts: Contour Guided Transformer (CGT), Contextual Learning Transformer (CLT) and Multimodal Transformer (MMT) for fusion. CGT embeds a CLIP image encoder and utilizes CLIP’s pre-training capabilities to capture contour features from input images, and CLT embeds a CLIP text encoder to correct contextual errors. The fusion network incorporates attention features extracted by Transformer to enhance text recognition performance. Unlike most STR methods that only target English, the proposed CCL is designed to handle both English and Chinese and can handle irregularly shaped scene text. We conduct a comprehensive evaluation on Chinese and English benchmark datasets to validate the performance of our approach against state-of-the-art methods. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2025.

关键词： Contourlet transform

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：