检索结果-内蒙古大学图书馆

arXiv 2025年

作者： Ivanovska, Marija Todorov, Leon Damer, Naser Jain, Deepak Kumar Peer, Peter Štruc, Vitomir Faculty of Electrical Engineering University in Ljubljana Slovenia Faculty of Computer and Information Science University in Ljubljana Slovenia Dalian University of Technology China Fraunhofer Institute for Computer Graphics Research Germany

With the continuous advancement of generative models, face morphing attacks have become a significant challenge for existing face verification systems due to their potential use in identity fraud and other malicious activities. Contemporary Morphing Attack Detection (MAD) approaches frequently rely on supervised, discriminative models trained on examples of bona fide and morphed images. These models typically perform well with morphs generated with techniques seen during training, but often lead to sub-optimal performance when subjected to novel unseen morphing techniques. While unsupervised models have been shown to perform better in terms of generalizability, they typically result in higher error rates, as they struggle to effectively capture features of subtle artifacts. To address these shortcomings, we present SelfMAD, a novel self-supervised approach that simulates general morphing attack artifacts, allowing classifiers to learn generic and robust decision boundaries without overfitting to the specific artifacts induced by particular face morphing methods. Through extensive experiments on widely used datasets, we demonstrate that SelfMAD significantly outperforms current state-of-the-art MADs, reducing the detection error by more than 64% in terms of EER when compared to the strongest unsupervised competitor, and by more than 66%, when compared to the best performing discriminative MAD model, tested in cross-morph settings. The source code for SelfMAD is available at https://***/LeonTodorov/SelfMAD. © 2025, CC BY-NC-ND.

关键词： Self-supervised learning

来源：评论

学校读者我要写书评

暂无评论

PFMRC: A Unified MRC Framework for Chinese Named Entity Recognition via Semantic Feature Fusion 4

PFMRC: A Unified MRC Framework for Chinese Named Entity Reco...

引用

4th International Conference on Artificial Intelligence, Robotics, and Communication, ICAIRC 2024

作者： Deng, Zhenrong Zhang, Jinglin Xiao, Yannan Wei, Shiwei Guilin University of Electronic Technology Guangxi Key Laboratory of Images and Graphics Intelligent Processing Guilin China Nanning Research Institute Guilin University of Electronic Technology Guilin China Guangxi Key Laboratory of Images and Graphics Intelligent Processing Guilin University of Electronic Technology Guilin China School of Computer Science and Engineering Guilin University of Aerospace Technology Guilin China

ISBN: (纸本)9798331531225

The landscape of natural language processing (NLP) has been revolutionized by advancements that enable the upstream training of knowledge-rich models for downstream tasks, particularly named entity recognition (NER). Traditional NER approaches, treating it as a sequence labeling problem, often fail to deeply understand the whole text and to capture syntactic nuances of text. To address these issues, we introduce PFMRC, a novel machine reading comprehension (MRC) framework that leverages the strengths of both contextual semantics and syntactic information for enhanced NER performance. PFMRC employs a dual-pronged feature extraction strategy, utilizing RoBERTa and BiGRU to encode text features for contextual semantic information and representing them as node features of the graph structure, and a weighted embedding representation to translate syntactic dependencies into graph-structured edge features. Our model further incorporates Graph Attention Networks (GAT) to harmonize node and edge features, facilitating a nuanced understanding of text. The integration of prior knowledge and the modeling of intricate syntactic relationships through Graph Attention Networks (GAT) not only improves entity recognition accuracy but also enriches the feature representation, leading to more robust NER outcomes. Extensive experiments on three Chinese datasets demonstrate PFMRC's superior performance over state-of-the-art models. © 2024 IEEE.

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

Altered Cloud Service Composition Techniques for Enhanced Integration

Altered Cloud Service Composition Techniques for Enhanced In...

引用

2024 OPJU International Technology Conference on Smart Computing for Innovation and Advancement in Industry 4.0, OTCON 2024

作者： Arya, Nancy Gupta, Priyanka Rajalakshmi, B. Nijhawan, Ginni Praveen Alrikabi, Hareth A. Shree Guru Gobind Singh Tricentenary University Department of Computer Science and Engineering Gurugram India Institute of Aeronautical Engineering Hyderabad Dundigal India New Horizon College of Engineering Department of Computer Science Bangalore India Lovely Professional University Phagwara India Lloyd Institute of Engineering & Technology Knowledge Park II Uttar Pradesh Greater Noida201306 India National University of Science and Technology Collage of Dentist Dhi Qar64001 Iraq

ISBN: (纸本)9798350373783

Create dynamic, dependable, and cost-effective cloud service combinations using the Dynamic Cloud Service Composition (DCSC) approach. Service Ranking (SR), Adaptive Composition (AC), and Cost Optimization algorithm are used in this strategy. Their combined efforts classify services by QoS, generate flexible compositions, and minimize prices. The most important factors for ranking service quality can be found using weighted numbers. It is possible to achieve dynamic flexibility by keeping an eye on service traits and using Adaptive Composition to start reconfigurations. Cutting costs without lowering the standard of service is what cost optimization is all about. Economically beneficial compositions result. Performance Score (PS), Adaptation Rate (AR), Cost Efficiency (CE), Resilience Index (RI), Resource Utilization (RU), and (ACost) are evaluated. © 2024 IEEE.

关键词： Adaptability Cloud Service Composition Cost Optimization Dynamic Composition QoS Parameters Quality of Service Resilience Resource Utilization Service Ranking

来源：评论

学校读者我要写书评

暂无评论

Runtime Verification of JavaScript Implementations Using Aspect Oriented Programming and Regular Expressions

Runtime Verification of JavaScript Implementations Using Asp...

引用

Conferencia Latinoamericana En Informatica (CLEI)

作者： Luciano Pacione Dana K. Urribarri Martín L. Larrea Luciano H. Tamargo Dept. of Computer Science and Engineering Universidad Nacional del Sur Bahia Blanca Argentina Dept. of Computer Science and Engineering Computer Graphics and Visualization R&D Laboratory (CIC) Institute for Computer Science and Engineering (CONICET) Universidad Nacional del Sur Bahia Blanca Argentina Dept. of Computer Science and Engineering Institute for Computer Science and Engineering (CONICET) Universidad Nacional del Sur Bahia Blanca Argentina

ISBN: (数字)9798331540975

ISBN: (纸本)9798331540982

Runtime Verification is a software testing technique based on extracting and analyzing information from a system while it is running. The objective is to use this information to find faults or problems in the system under test. To achieve this, it is necessary that the insertion of testing logic does not modify the code being tested and that it does not affect the performance of the system. In this article, we present a runtime testing framework for JavaScript, which utilizes Aspect-Oriented Programming and regular expressions. This framework encapsulates the idea of Message Sequence Specification applied to Runtime Verification. Our work is freely available and open source.

关键词： Software testing Runtime Codes Programming Logic Data mining

来源：评论

学校读者我要写书评

暂无评论

HCAI4U 2023 - Preface to the First Workshop on User Perspectives in Human-Centred Artificial Intelligence 1

HCAI4U 2023 - Preface to the First Workshop on User Perspect...

引用

1st Workshop on User Perspectives in Human-Centred Artificial Intelligence, HCAI4U 2023

作者： De Luca, Ernesto W. Purificato, Erasmo Boratto, Ludovico Marrone, Stefano Sansone, Carlo Otto von Guericke University Magdeburg Faculty of Computer Science Magdeburg39106 Germany Leibniz Institute for Educational Media Georg Eckert Institute Brunswick38118 Germany University of Cagliari Department of Mathematics and Computer Science Cagliari09124 Italy University of Naples Federico II Department of Electrical Engineering and Information Technology Naples80125 Italy

The emerging concept of Human-Centred Artificial Intelligence (HCAI) involves the amplification, augmentation, empowerment, and enhancement of individuals. The goal of HCAI is to ensure that AI meets our needs while also operating transparently, delivering fair and equitable outcomes, and respecting privacy, all while preserving human control. This approach involves multiple stakeholders, such as researchers, developers, business leaders, policymakers, and users, who are affected in various ways by the implementation and evaluation of AI systems. The primary focus of the First Workshop on User Perspectives in Human-Centred Artificial Intelligence (HCAI4U) is to examine the potential positive and negative impacts of automated decision-making systems on end-users, as well as how their interaction with AI is influenced by human-centred aspects of reliability, safety, and fairness. The workshop aims to facilitate discussion and exchange of ideas among the community on advances in developing trustworthy, fair, and privacy-preserving systems, as well as user interfaces that are explainable, with a specific focus on the users’ perception in real-world scenarios rather than solely on the algorithmic and model performance. Additionally, HCAI4U aims to foster cross-disciplinary and interdisciplinary discussions between experts from various research fields, such as computer science, psychology, sociology, law, medicine, business, etc., to discuss problems and synergies in this exciting research topic. © 2023 CEUR-WS. All rights reserved.

关键词： Human computer interaction

来源：评论

学校读者我要写书评

暂无评论

Robustness and Exploration of Variational and Machine Learning Approaches to Inverse Problems: An Overview

arXiv

引用

arXiv 2024年

作者： Auras, Alexander Gandikota, Kanchana Vaishnavi Droege, Hannah Moeller, Michael Institute for Vision and Graphics University of Siegen NRW Germany Institute of Computer Science Rheinische Friedrich-Wilhelms-Universität Bonn NRW Germany

This paper provides an overview of current approaches for solving inverse problems in imaging using variational methods and machine learning. A special focus lies on point estimators and their robustness against adversarial perturbations. In this context results of numerical experiments for a one-dimensional toy problem are provided, showing the robustness of different approaches and empirically verifying theoretical guarantees. Another focus of this review is the exploration of the subspace of data-consistent solutions through explicit guidance to satisfy specific semantic or textural properties. Copyright © 2024, The Authors. All rights reserved.

关键词： Adversarial machine learning

来源：评论

学校读者我要写书评

暂无评论

Deontic Reasoning Based On Inconsistency Measures 21

Deontic Reasoning Based On Inconsistency Measures

引用

21st International Conference on Principles of Knowledge Representation and Reasoning, KR 2024

作者： Arieli, Ofer van Berkel, Kees Raddaoui, Badran Straßer, Christian School of Computer Science Tel-Aviv Academic College Israel Institute for Logic and Computation TU Wien Austria SAMOVAR Télécom SudParis Institut Polytechnique de Paris France Institute for Philosophy II Ruhr Universität Bochum Germany

ISBN: (纸本)9781956792058

Conflicts are inherent to normative systems. In this paper, we explore a novel approach to normative reasoning by quantifying the amount of conflicts within normative systems. We refine the idea from classical logic, according to which a formula is a consequence of a knowledge base in case its negation renders the knowledge base inconsistent. In our approach, whether a formula is a logical consequence depends, for instance, on its negation’s marginal contribution to the inconsistency of the given knowledge base. Accordingly, various inconsistency measures and corresponding (nonmonotonic and paraconsistent) normative entailment relations are analyzed relative to a number of logical properties. To illustrate our approach, we adopt Input/Output logic, a renowned formalism in deontic logic, specifically designed for defeasible normative reasoning. As an application, the resulting entailment relations provide recommendations to agents for minimizing norm conflicts, and may be incorporated in a number of implementations (like the Tweety libraries and the LogiKey framework) by involving inconsistency measurements in normative reasoning. © 2024 Proceedings of the International Conference on Knowledge Representation and Reasoning. All rights reserved.

关键词： computer circuits

来源：评论

学校读者我要写书评

暂无评论

Perceptual navigation in absorption-scattering space 29

Perceptual navigation in absorption-scattering space

引用

29th Color and Imaging Conference - Color science and Engineering Systems, Technologies, and Applications, CIC 2021

作者： Gigilashvili, Davit Urban, Philipp Thomas, Jean-Baptiste Pedersen, Marius Hardeberg, Jon Yngve Norwegian University of Science and Technology Department of Computer Science Gjøvik Norway Fraunhofer Institute for Computer Graphics Research IGD Darmstadt Germany

ISBN: (纸本)9780892083572

Translucency optically results from subsurface light transport and plays a considerable role in how objects and materials appear. Absorption and scattering coefficients parametrize the distance a photon travels inside the medium before it gets absorbed or scattered, respectively. Stimuli produced by a material for a distinct viewing condition are perceptually non-uniform w.r.t. these coefficients. In this work, we use multi-grid optimization to embed a non-perceptual absorption-scattering space into a perceptually more uniform space for translucency and lightness. In this process, we rely on A (alpha) as a perceptual translucency metric. Small Euclidean distances in the new space are roughly proportional to lightness and apparent translucency differences measured with A. This makes picking A more practical and predictable, and is a first step toward a perceptual translucency space. © 2021 Society for Imaging science and Technology. All rights reserved.

关键词： Color

来源：评论

学校读者我要写书评

暂无评论

A New Approach Towards Identification of Individuals Belonging to Different Subpopulations Using Machine Learning Models and CLC Data 24

A New Approach Towards Identification of Individuals Belongi...

引用

24th IEEE International Conference on Data Mining Workshops, ICDMW 2024

作者： Charytanowicz, Malgorzata Perzanowski, Kajetan Januszczak, Maciej Woloszyn-Galeza, Aleksandra Sobczuk, Maria Kulczycki, Piotr Lublin University of Technology Department of Computer Science Lublin Poland Systems Research Institute Polish Academy of Sciences Warsaw Poland John Paul II Catholic University of Lublin Institute of Biological Sciences Lublin Poland Polish Academy of Sciences Museum and Institute of Zoology Ustrzyki Dolne Poland Warsaw University of Life Sciences Chair of Animal Genetics and Conservation Warsaw Poland AGH University of Krakow Faculty of Physics and Applied Computer Science Krakow Poland

ISBN: (纸本)9798331530631

Spatial distributions of wisents (European bison) Bison bonasus (Linnaeus 1758), were studied in the Bieszczady Mountains (south-eastern Poland) on the basis of telemetric data obtained from two subpopulations: the western - inhabiting the forest districts of Baligród, Komańcza, Cisna and Lesko, and the eastern - dwelling within the districts of Lutowiska, Stuposiany, and in Bieszczadzki National park. Data was collected between 2002-2021. In our study, we propose a novel approach for classifying wisent subpopulations that utilizes machine learning methods and CLC data. For this purpose, the performances of eight algorithms: Naive Bayes, Logistic Regression, Support Vector Machine, Multilayer Perceptron, Random Forest, Extreme Gradient Boosting, k-Nearest Neighbors and Decision Tree were investigated. The algorithms were compared according to the following indicators: accuracy, Cohen's-Kappa, precision, recall and F1 score. Their assessment was enhanced through the application of statistical inference (the Friedman test with post-hoc analysis) and SHAP values. The lowest results were achieved by Naive Bayes and Logistic Regression methods (accuracy of 73.69% and 74.43%, respectively), whilst significantly higher results were achieved by eXtreme Gradient Boosting, k-Nearest Neighbors and Decision Tree classifiers, with the classification accuracy exceeding 90% (91.81%, 92.8%, 93.47%, respectively). Based on the results, we conclude that CLC data represents a valuable source of information regarding the affinity of wisents towards different habitat conditions. © 2024 IEEE.

关键词： Adversarial machine learning

来源：评论

学校读者我要写书评

暂无评论

FX-MAD: Frequency-Domain Explainability and Explainability-Driven Unsupervised Detection of Face Morphing Attacks

FX-MAD: Frequency-Domain Explainability and Explainability-D...

引用

IEEE Winter Applications and computer Vision Workshops (WACVW)

作者： Marco Huber Pedro C. Neto Ana F. Sequeira Naser Damer Fraunhofer Institute for Computer Graphics Research IGD Darmstadt Germany Department of Computer Science Technische Universität Darmstadt Germany INESC TEC Porto Portugal Faculry of Engineering University of Porto Portugal

ISBN: (数字)9798331536626

ISBN: (纸本)9798331536633

Face recognition (FR) systems are vulnerable to morphing attacks, which refer to face images created by morphing the facial features of two different identities into one face image to create an image that can match both identities, allowing serious security breaches. In this work, we apply a frequency-based explanation method from the area of explainable face recognition to shine a light on how FR models behave when processing a bona fide or attack pair from a frequency perspective. In extensive experiments, we used two different state-of-the-art FR models and six different morphing attacks to investigate possible differences in behavior. Our results show that FR models rely differently on different frequency bands when making decisions for bona fide pairs and morphing attacks. In the following step, we show that this behavioral difference can be used to detect morphing attacks in an unsupervised setup solely based on the observed frequency-importance differences in a generalizable manner.

关键词： computer vision Correlation Face recognition Soft sensors Frequency-domain analysis Conferences Benchmark testing Security Facial features

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

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

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：