检索结果-内蒙古大学图书馆

7th IEEE International Conference on Artificial Intelligence and eXtended and Virtual Reality, AIxVR 2025

作者： Qiu, Shi Xie, Binzhu Liu, Qixuan Heng, Pheng-Ann Department of Computer Science and Engineering The Chinese University of Hong Kong HKSAR China Institute of Medical Intelligence and XR The Chinese University of Hong Kong HKSAR China

ISBN: (纸本)9798331521578

3D Gaussian Splatting (3DGS) has attracted significant attention for its potential to revolutionize 3D representation, rendering, and interaction. Despite the rapid growth of 3DGS research, its direct application to Extended Reality (XR) remains underexplored. Although many studies recognize the potential of 3DGS for XR, few have explicitly focused on or demonstrated its effectiveness within XR environments. In this paper, we aim to synthesize innovations in 3DGS that show specific potential for advancing XR research and development. We conduct a comprehensive review of publicly available 3DGS papers, with a focus on those referencing XR-related concepts. Additionally, we perform an indepth analysis of innovations explicitly relevant to XR and propose a taxonomy to highlight their significance. Building on these insights, we propose several prospective XR research areas where 3DGS can make promising contributions, yet remain rarely touched. By investigating the intersection of 3DGS and XR, this paper provides a roadmap to push the boundaries of XR using cutting-edge 3DGS techniques. © 2025 IEEE.

关键词： 3D modeling

来源：评论

学校读者我要写书评

暂无评论

FreqSense: Universal and Low-Latency Adversarial Example Detection for Speaker Recognition with Interpretability in Frequency Domain

FreqSense: Universal and Low-Latency Adversarial Example Det...

引用

2025 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2025

作者： Huang, Yihuan Li, Yuanzhe Ren, Yanzhen Tu, Weiping Yang, Yuhong Key Laboratory of Aerospace Information Security and Trusted Computing Ministry of Education China School of Cyber Science and Engineering Wuhan University China National Engineering Research Center for Multimedia Software School of Computer Science Wuhan University China

ISBN: (纸本)9798350368741

Speaker recognition (SR) systems are particularly vulnerable to adversarial example (AE) attacks. To mitigate these attacks, AE detection systems are typically integrated into SR systems. To overcome the limitations of low detection accuracy, poor generalization, and high latency in existing schemes, this paper proposes FreqSense, an AE detection scheme based on frequency distribution features. FreqSense detects a variety of unknown AE attacks with low latency, and provides interpretability in its detection process. The basic idea of FreqSense is that AE typically introduce carefully designed noise in specific frequency bands that are associated with highly distinctive speaker identities. Therefore, leveraging the distributional variations in these frequency bands can effectively distinguish between AE and benign audio. FreqSense models frequency distribution features by integrating time-frequency transformation technology with a self-attention mechanism and employs a neural network-based classifier to distinguish between AE and benign audio. Experimental results show that FreqSense achieves an overall detection accuracy of 99.2%, surpassing state-of-the-art (SOTA) schemes by 27.2%. When confronting unknown AE attacks, FreqSense achieves a detection accuracy of 98.3% with a latency of just 0.0014 seconds. © 2025 IEEE.

关键词： Adversarial Attack Adversarial Example Detection Speaker Recognition

来源：评论

学校读者我要写书评

暂无评论

DocTTT: Test-Time Training for Handwritten Document Recognition Using Meta-Auxiliary Learning

DocTTT: Test-Time Training for Handwritten Document Recognit...

引用

IEEE Workshop on Applications of computer Vision (WACV)

作者： Wenhao Gu Li Gu Ziqiang Wang Ching Yee Suen Yang Wang Department of Computer Science and Software Engineering Concordia University

ISBN: (数字)9798331510831

ISBN: (纸本)9798331510848

Despite recent significant advancements in Handwritten Document Recognition (HDR), the efficient and accurate recognition of text against complex backgrounds, diverse handwriting styles, and varying document layouts remains a practical challenge. Moreover, this issue is seldom addressed in academic research, particularly in scenarios with minimal annotated data available. In this paper, we introduce the DocTTT framework to address these challenges. The key innovation of our approach is that it uses test-time training to adapt the model to each specific input during testing. We propose a novel Meta-Auxiliary learning approach that combines Meta-learning and self-supervised Masked Autoencoder (MAE). During testing, we adapt the visual representation parameters using a self-supervised MAE loss. During training, we learn the model parameters using a meta-learning framework, so that the model parameters are learned to adapt to a new input effectively. Experimental results show that our proposed method significantly outperforms existing state-of-the-art approaches on benchmark datasets.

关键词： Training Metalearning Adaptation models Handwriting recognition Visualization Technological innovation computer vision Text recognition Computational modeling Layout

来源：评论

学校读者我要写书评

暂无评论

Generating Avatar Using HamNoSys and SiGML for British Sign Language

Generating Avatar Using HamNoSys and SiGML for British Sign ...

引用

International Conference on Signal Processing and Communication (ICSC)

作者： Harshit Singh Ashish Mishra Rahul Dubey Vipin Tiwari Computer Science and Engineering Jaypee Institute of Information Technology Noida India Computer Science and Engineering Madhav Institute of Technology and Science Gwalior India Computer Science and Engineering Symbiosis Institute of Technology Pune Campus Symbiosis International (Deemed University) Pune India

ISBN: (数字)9798331511890

ISBN: (纸本)9798331511906

In today's digital world online video lectures have become a crucial tool for learning. Yet, these resources aren't available to a big part of the world's population those who are deaf or hard of hearing. This study presents a new system that aims to make these resources available to everyone by turning spoken words from video lectures into sign language gestures. The system uses advanced video processing to change spoken words into text. It then turns this text into British Sign Language (BSL) glosses, which are then written in the Hamburg Notation System (HamNoSys). Using the Signing Gesture Markup Language (SiGML), the system creates a virtual avatar that can show complex sign language gestures. The heart of this research is in combining cutting-edge technologies to offer a deep learning experience that goes beyond hearing limits and tries to make online education for everyone. Early tests of the system show it has the power to close the current gap in education highlighting how important it is to include everyone in the digital age.

关键词： Heart Sign language Translation Avatars Markup languages Education Auditory system Signal processing Turning Information age

来源：评论

学校读者我要写书评

暂无评论

TSR: a Location Privacy Preservation Mechanism in Public Transportation Route Planning Service 25th

TSR: a Location Privacy Preservation Mechanism in Public T...

引用

25th International Conference on Parallel and Distributed Computing, Applications and Technologies, PDCAT 2024

作者： Wu, Wei Sang, Yingpeng Zhang, Haibo Hong, Shen School of Computer Science and Engineering Sun Yet-sen University Guangzhou China School of Computing University of Otago Dunedin New Zealand School of Engineering and Technology Central Queensland University Brisbane Australia

ISBN: (纸本)9789819642069

Location-based service (LBS) applications are increasingly popular for travelling. The public transit scenario is very common in urban areas, yet there is a lack of effective privacy protection mechanisms to safeguard users’ location privacy when using services from untrusted third-party LBS providers. This paper introduces Transportation Shift-based Routing (TSR), a privacy protection mechanism for public transportation travel scenarios. It allows users to query public transit routes through applications that comply with this mechanism without disclosing any significant details about the location, and fills the gap in privacy protection mechanisms in public transportation scenarios. The fundamental concept is to shift the query’s starting and ending points to nearby stations and repeatedly perform perturbations that satisfy geo-indistinguishability, submitting a collection of perturbed station pairs to the LBS. TSR computes the set of obtained routes to derive an optimal route plan. The best route calculated can maintain service availability and protect user location privacy, with only a minimal difference from the best route obtained by direct query. TSR also allows users to freely choose privacy parameters for different scenarios and strives to ensure service quality, offering high flexibility. We implement the TSR application and conduct experiments with real-world map services. The experimental outcomes indicate that TSR successfully strikes a balance between preserving location privacy and maintaining service usability. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

关键词： Differential privacy

来源：评论

学校读者我要写书评

暂无评论

3DGCformer: 3-Dimensional Graph Convolutional transformer for multi-step origin–destination matrix forecasting

引用

Applied Intelligence 2025年第6期55卷 1-18页

作者： Huang, Yiou Deng, Hao Zhao, Shengjie School of Computer Science and Technology Tongji University Shanghai China Key Laboratory of Embedded System and Service Computing Shanghai China Engineering Research Center of Key Software Technologies for Smart City Perception and Planning Ministry of Education Shanghai China

Forecasting Human mobility is of great significance in the simulation and control of infectious diseases like COVID-19. To get a clear picture of potential future outbreaks, it is necessary to forecast multi-step Origin–Destination (OD) matrices for a relatively long period in the future. However, multi-step Origin–Destination Matrix Forecasting (ODMF) is a non-trivial problem. First, previous ODMF models only forecast the OD matrix for the next time-step, and they cannot perform well on long-term multi-step forecasts due to error accumulation. Second, many ODMF methods capture spatial and temporal dependencies with separate modules, which is insufficient to model spatio-temporal correlations in the time-varying OD matrix sequence. To address the challenges in multi-step ODMF, we propose 3-Dimensional Graph Convolutional Transformer (3DGCformer). As an enhancement of the original 3DGCN, we propose a novel Origin–Destination Feature Propagation (ODFP) rule between 3DGCN layers and integrate 2 3DGCNs with different spatio-temporal graphs and corresponding feature propagation rules to model the formation of OD flows in a more comprehensive way. For multi-step forecasts, 3DGCformer uses Transformer to capture long-term global temporal dependency, and adapt its decoder using labeled tokens to avoid error accumulation and improve time efficiency. To avoid information loss as the number of regions increases, we propose a patch embedding approach to convert data from 3DGCNs to the Transformer module. We perform extensive experiments on 4 real-world human mobility datasets, and the results show that our proposed model outperforms the state-of-the-art methods. © The Author(s), under exclusive licence to Springer science+Business Media, LLC, part of Springer Nature 2025.

关键词： Convolution

来源：评论

学校读者我要写书评

暂无评论

A Web-Based Interface that Leverages Machine Learning to Assess an Individual’s Vulnerability to Brain Stroke

引用

IEEE Access 2025年 13卷 87950-87964页

作者： Bhandari, Divyansh Agarwal, Arnav Reena Roy, R. Priyatharshini, Rajaram Cristian, Rodriguez Rivero Vellore Institute of Technology School of Electronics Engineering Tamil Nadu Chennai India Vellore Institute of Technology School of Computer Science and Engineering Tamil Nadu Chennai India Cardiff Metropolitan University Cardiff School of Technologies Centre for Engineering Research in Intelligent Sensors and SystemsComputer Science Wales United Kingdom Cardiff Metropolitan University Academic Associate Cardiff School of Technologies Cardiff United Kingdom Universitat Politècnica de Catalunya Industrial and ICT Systems Engineering Dept. of Mining Spain

Cerebral stroke is a major global health issue, contributing to high mortality and long-term disability. Early identification of individuals at high risk of stroke can significantly improve preventive care outcomes. We present a web-based stroke risk assessment tool that uniquely combines an accessible user interface with robust machine learning modeling. The proposed platform leverages a novel combination of SMOTE oversampling and logistic regression to address class imbalance in patient health records, improving the detection of stroke risk factors over existing methods. We compare a range of algorithms – including traditional classifiers and deep learning models – and report comprehensive performance metrics (accuracy, precision, recall, F1-score, and AUC-ROC) for each. Our best model (logistic regression with SMOTE and standard scaling) achieves 93.2% accuracy with a substantially higher F1-score for the stroke-positive class than other models, indicating improved sensitivity to stroke cases. To bridge the gap between complex predictive models and end-users, we deploy this model in an intuitive web interface (built with Streamlit) that non-technical individuals and healthcare providers can easily use. This interface requires no specialized knowledge, preserves user privacy by avoiding any data storage, and provides clear explanations of results. By offering a practical and transparent tool for stroke risk screening, our work advances health informatics with an emphasis on accessibility, interpretability, and early intervention. Potential applications range from personal health self-assessment to integration in clinical workflows for preventive care, ultimately aiming to improve public health outcomes through early detection and intervention in stroke. © 2013 IEEE.

关键词： Health insurance

来源：评论

学校读者我要写书评

暂无评论

From Superficial to Deep: Integrating External Knowledge for Follow-up Question Generation Using Knowledge Graph and LLM 31

From Superficial to Deep: Integrating External Knowledge for...

引用

31st International Conference on Computational Linguistics, COLING 2025

作者： Liu, Jianyu Huang, Yi Bi, Sheng Feng, Junlan Qi, Guilin School of Computer Science and Engineering Southeast University China Law and Innovation Lab Law School Southeast University China China Mobile Research Institute China

ISBN: (纸本)9798891761964

In a conversational system, dynamically generating follow-up questions based on context can help users explore information and provide a better user experience. Humans are usually able to ask questions that involve some general life knowledge and demonstrate higher order cognitive skills. However, the questions generated by existing methods are often limited to shallow contextual questions that are uninspiring and have a large gap to the human level. In this paper, we propose a three-stage external knowledge-enhanced follow-up question generation method, which generates questions by identifying contextual topics, constructing a knowledge graph (KG) online, and finally combining these with a large language model to generate the final question. The model generates information-rich and exploratory followup questions by introducing external common sense knowledge and performing a knowledge fusion operation. Experiments show that compared to baseline models, our method generates questions that are more informative and closer to human questioning levels while maintaining contextual relevance. © 2025 Association for Computational Linguistics.

关键词： Knowledge graph

来源：评论

学校读者我要写书评

暂无评论

Classification of Bengali News Articles Using Voting Classification Approach

Classification of Bengali News Articles Using Voting Classif...

引用

Interdisciplinary Approaches in Technology and Management for Social Innovation (IATMSI), IEEE Conference on

作者： Piyal Roy Shivnath Ghosh Sohini Ghosh Amitava Podder Somsindhu Das Computer Science & Engineering Brainware University Barasat India

ISBN: (数字)9798331521691

ISBN: (纸本)9798331521707

Text classification is a crucial technology that helps in extracting and organizing textual data by automatically identifying its type based on the content. It can be applied to categorize Bengali news content into various categories. In this re-search paper, we employed the voting classification technique, which includes multiple classifiers such as Logistic Regression, Support Vector Classification (SVC), Multinomial Naive Bayes (NB), Bernoulli NB, Stochastic Gradient De-scent (SGD) Classifier, AdaBoost Classifier, Decision Tree Classifier, Logistic RegressionCV, Calibrated ClassifierCV, and Random Forest Classifier. The model was trained and tested on a gold standard dataset consisting of Bengali news content, and categorized the data into eight distinct categories, including Economy, Education, Entertainment, International, National, science and Tech-nology, Sports, and Politics. Our results indicate that the hard voting approach achieved an accuracy rate of 89%, while the soft voting approach achieved an accuracy rate of 93%. This paper demonstrates the effectiveness of employing text classification techniques for categorizing Bengali news content and highlights the potential for its application in other languages and domains.

关键词： Technological innovation Accuracy Text categorization Stochastic processes Static VAr compensators Vectors Regression tree analysis Random forests Sports Logistics

来源：评论

学校读者我要写书评

暂无评论

An Online Integrated Development Environment for Automated Programming Assessment Systems 17

An Online Integrated Development Environment for Automated P...

引用

17th International Conference on computer Supported Education, CSEDU 2025

作者： Frankford, Eduard Crazzolara, Daniel Vierhauser, Michael Meißner, Niklas Krusche, Stephan Breu, Ruth University of Innsbruck Department of Computer Science Austria University of Stuttgart Institute of Software Engineering Germany Technical University of Munich School of Computation Information and Technology Germany

ISBN: (纸本)9789897587467

The increasing demand for programmers has led to a surge in participants in programming courses, making it increasingly challenging for instructors to assess student code manually. As a result, automated programming assessment systems (APASs) have been developed to streamline this process. These APASs support lecturers by managing and evaluating student programming exercises at scale. However, these tools often do not provide feature-rich online editors compared to their traditional integrated development environments (IDEs) counterparts. This absence of key features, such as syntax highlighting and autocompletion, can negatively impact the learning experience, as these tools are crucial for effective coding practice. To address this gap, this research contributes to the field of programming education by extracting and defining requirements for an online IDE in an educational context and presenting a prototypical implementation of an open-source solution for a scalable and secure online IDE. The usability of the new online IDE was assessed using the Technology Acceptance Model (TAM), gathering feedback from 27 first-year students through a structured survey. In addition to these qualitative insights, quantitative measures such as memory (RAM) usage were evaluated to determine the efficiency and scalability of the tool under varying usage conditions. Copyright © 2025 by SCITEPRESS - science and Technology Publications, Lda.

关键词： Teaching

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：