检索结果-内蒙古大学图书馆

arXiv 2024年

作者： Hashmi, Ammarah Shahzad, Sahibzada Adil Lin, Chia-Wen Tsao, Yu Wang, Hsin-Min The Social Networks and Human-Centered Computing Program Taiwan International Graduate Program Institute of Information Science Academia Sinica Taipei11529 Taiwan The Institute of Information Systems and Applications National Tsing Hua University Hsinchu300044 Taiwan The Department of Computer Science National Chengchi University Taipei11529 Taiwan The Department of Electrical Engineering The Institute of Communications Engineering National Tsing Hua University Hsinchu300044 Taiwan The Research Center for Information Technology Innovation Academia Sinica Taipei11529 Taiwan The Institute of Information Science Academia Sinica Taipei11529 Taiwan

Deep Learning has been successfully applied in diverse fields, and its impact on deepfake detection is no exception. Deepfakes are fake yet realistic synthetic content that can be used deceitfully for political impersonation, phishing, slandering, or spreading misinformation. Despite extensive research on unimodal deepfake detection, identifying complex deepfakes through joint analysis of audio and visual streams remains relatively unexplored. To fill this gap, this survey first provides an overview of audiovisual deepfake generation techniques, applications, and their consequences, and then provides a comprehensive review of state-of-the-art methods that combine audio and visual modalities to enhance detection accuracy, summarizing and critically analyzing their strengths and limitations. Furthermore, we discuss existing open source datasets for a deeper understanding, which can contribute to the research community and provide necessary information to beginners who want to analyze deep learning-based audiovisual methods for video forensics. By bridging the gap between unimodal and multimodal approaches, this paper aims to improve the effectiveness of deepfake detection strategies and guide future research in cybersecurity and media integrity. © 2024, CC BY.

关键词： Audiovisual

来源：评论

学校读者我要写书评

暂无评论

AVTENet: A Human-Cognition-Inspired Audio-Visual Transformer-Based Ensemble Network for Video Deepfake Detection

引用

IEEE Transactions on Cognitive and Developmental Systems 2025年

作者： Hashmi, Ammarah Shahzad, Sahibzada Adil Lin, Chia-Wen Tsao, Yu Wang, Hsin-Min Taiwan International Graduate Program Academia Sinica Social Networks and Human-Centered Computing Program Taipei11529 Taiwan National Tsing Hua University Institute of Information Systems and Applications Hsinchu30013 Taiwan National Chengchi University Department of Computer Science Taipei11605 Taiwan National Tsing Hua University Department of Electrical Engineering Institute of Communications Engineering Hsinchu300044 Taiwan Academia Sinica Research Center for Information Technology Innovation Taipei11529 Taiwan

The recent proliferation of hyper-realistic deepfake videos has drawn attention to the threat of audio and visual forgeries. Most previous studies on detecting artificial intelligence-generated fake videos only utilize visual modality or audio modality. While some methods exploit audio and visual modalities to detect forged videos, they have not been comprehensively evaluated on multimodal datasets of deepfake videos involving acoustic and visual manipulations, and are mostly based on convolutional neural networks with low detection accuracy. Considering that human cognition instinctively integrates multisensory information including audio and visual cues to perceive and interpret content and the success of transformer in various fields, this study introduces the audio-visual transformer-based ensemble network (AVTENet). This innovative framework tackles the complexities of deepfake technology by integrating both acoustic and visual manipulations to enhance the accuracy of video forgery detection. Specifically, the proposed model integrates several purely transformer-based variants that capture video, audio, and audio-visual salient cues to reach a consensus in prediction. For evaluation, we use the recently released benchmark multimodal audio-video FakeAVCeleb dataset. For a detailed analysis, we evaluate AVTENet, its variants, and several existing methods on multiple test sets of the FakeAVCeleb dataset. Experimental results show that the proposed model outperforms all existing methods and achieves state-of-the-art performance on Testset-I and Testset-II of the FakeAVCeleb dataset. We also compare AVTENet against humans in detecting video forgery. The results show that AVTENet significantly outperforms humans. © 2016 IEEE.

关键词： audio-visual AVTENet Deepfake detection

来源：评论

学校读者我要写书评

暂无评论

Adaptive Contextual Caching for Mobile Edge Large Language Model Service

arXiv

引用

arXiv 2025年

作者： Liu, Guangyuan Liu, Yinqiu Wang, Jiacheng Du, Hongyang Niyato, Dusit Kang, Jiawen Xiong, Zehui College of Computing and Data Science The Energy Research Institute @ NTU Interdisciplinary Graduate Program Nanyang Technological University Singapore College of Computing and Data Science Nanyang Technological University Singapore Department of Electrical and Electronic Engineering University of Hong Kong Hong Kong School of Automation Guangdong University of Technology China Pillar of Information Systems Technology and Design Singapore University of Technology and Design Singapore

Mobile edge Large Language Model (LLM) deployments face inherent constraints, such as limited computational resources and network bandwidth. Although Retrieval-Augmented Generation (RAG) mitigates some challenges by integrating external knowledge bases, inefficient cache management can still result in high retrieval latency and frequent cache updates. To address these issues, we propose an Adaptive Contextual Caching (ACC) framework that anticipates user needs by proactively caching semantically relevant data for mobile-edge LLMs. ACC utilizes a deep reinforcement learning (DRL) module to refine cache replacement policies, balancing user context, document similarity, and the overhead associated with cache misses. Experimental results demonstrate that ACC increases cache hit rates to over 80% after only 11 training episodes, outperforming FIFO, LRU, and semantic-only caching while reducing retrieval latency by up to 40%. In particular, ACC also reduces local caching overhead (i.e., the cost of updating the cache when a miss occurs) by as much as 55%, enabling scalable, low-latency LLM services in resource-constrained edge environments. © 2025, CC BY.

关键词： Deep reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

Analysis of the Musculoskeletal Load Generated when a Small Dog Walks on a Slippery Floor*

Analysis of the Musculoskeletal Load Generated when a Small ...

引用

IEEE/SICE International Symposium on System Integration

作者： Shijian Li Daisuke Chugo Satoshi Muramatsu Sho Yokota Jin-Hua She Hiroshi Hashimoto Uemura Takashi Hiroaki Kamishina Yoshiharu Hata Takayuki Yamada Takahiro Uchida Graduate School of Science and Technology Kwansei Gakuin University Sanda Japan School of Information Science and Technology Tokai University Hiratsuka Japan Faculty of Science and Engineering Toyo University Kawagoe Japan School of Engineering Tokyo University of Technology Tokyo Japan Master Program of Innovation for Design and Engineering Advanced Institute of Industrial Technology Tokyo Japan KyotoAR Animal Advanced Medical Center Kyoto Japan Rinrei Co. Ltd. Tokyo Japan

ISBN: (数字)9798331531614

ISBN: (纸本)9798331531621

The objective of this paper is to identify the stresses placed on the musculoskeletal system when small dogs walk on floors with low friction coefficients. In many households, and small dogs in particular are often kept indoors. According to veterinary experience, it is known that small dogs kept indoors that walk with their lower limbs slipping cause a great deal of stress on the musculoskeletal system, and that the incidence of joint disease in the lower limbs of such small dogs is high. In this study, we measured the body movements of small dogs walking on slippery floors using a three-dimensional motion capture system and force plate system. Furthermore, by inputting these measurements into the musculoskeletal simulation model we have developed to simulate the musculoskeletal system of dogs, we derived the load on the musculoskeletal system of small dogs on slippery and non-slippery floors. As a result, it was identified that walking on a slippery floor causes a strong load on the lower limb muscles of small dogs.

关键词： Legged locomotion Limbs Friction Dogs System integration Muscles Object recognition Floors Stress Paints

来源：评论

学校读者我要写书评

暂无评论

Proposing a visualized comparative review analysis model on tourism domain using Naïve Bayes classifier

引用

Procedia Computer science 2023年 227卷 482-489页

作者： Albert Verasius Dian Sano Adriel Anderson Stefanus Evaristus Didik Madyatmadja Hendro Nindito Agung Purnomo Corinthias P.M. Sianipar Computer Science Department School of Computer Science Bina Nusantara University Jakarta 11480 Indonesia Information Systems Department School of Information Systems Bina Nusantara University Jakarta 11480 Indonesia Entrepreneurship Department BINUS Business School Undergraduate Program Bina Nusantara University Jakarta 11480 Indonesia Department of Global Ecology Graduate School of Global Environmental Studies (GSGES) Division of Environmental Science and Technology Graduate School of Agriculture (GSA) Kyoto University Kyoto 606-8502 Japan

This study, using the Naïve Bayes classifier, proposes a new descriptive model for conducting a comparative review analysis on the tourism domain. The proposed model seeks to improve the understanding of tourists' experiences by visually representing their opinions between various tourist destinations. The model predicts the sentiment of tourist reviews using the Naive Bayes classifier, which is then used to generate visualizations that facilitate comparative analysis. The comparison takes two tourism sites as experimental examples. The results, in terms of accuracy, show 80% and 64% for the first and the second site respectively. The study discusses the model's implementation, effectiveness, and potential applications in the tourism industry. The findings of the study suggest that the proposed model can provide valuable insights into tourist experiences and help tourism stakeholders, such as the managements of tourism sites, the future or soon coming tourists to make informed decisions based on comparative analysis.

关键词： Comparative review analysis Naïve Bayes classifier tourism

来源：评论

学校读者我要写书评

暂无评论

HAAQI-Net: A Non-intrusive Neural Music Audio Quality Assessment Model for Hearing Aids

arXiv

引用

arXiv 2024年

作者： Wisnu, Dyah A.M.G. Rini, Stefano Zezario, Ryandhimas E. Wang, Hsin-Min Tsao, Yu Taiwan International Graduate Program—Social Network and Human Centered Computing Institute of Information Science Academia Sinica Taipei Taiwan College of Informatics National Chengchi University Taipei Taiwan Institute of Communications Engineering National Yang Ming Chiao Tung University Hsinchu Taiwan Research Center for Information Technology Innovation Academia Sinica Taipei Taiwan Institute of Information Science Academia Sinica Taipei Taiwan

This paper introduces HAAQI-Net, a non-intrusive deep learning-based music audio quality assessment model for hearing aid users. Unlike traditional methods like the Hearing Aid Audio Quality Index (HAAQI) that require intrusive reference signal comparisons, HAAQI-Net offers a more accessible and computationally efficient alternative. By utilizing a Bidirectional Long Short-Term Memory (BLSTM) architecture with attention mechanisms and features extracted from the pre-trained BEATs model, it can predict HAAQI scores directly from music audio clips and hearing loss patterns. Experimental results demonstrate HAAQI-Net’s effectiveness, achieving a Linear Correlation Coefficient (LCC) of 0.9368, a Spearman’s Rank Correlation Coefficient (SRCC) of 0.9486, and a Mean Squared Error (MSE) of 0.0064 and inference time significantly reduces from 62.52 to 2.54 seconds. To address computational overhead, a knowledge distillation strategy was applied, reducing parameters by 75.85% and inference time by 96.46%, while maintaining strong performance (LCC: 0.9071, SRCC: 0.9307, MSE: 0.0091). To expand its capabilities, HAAQI-Net was adapted to predict subjective human scores like the Mean Opinion Score (MOS) through fine-tuning. This adaptation significantly improved prediction accuracy, validated through statistical analysis. Furthermore, the robustness of HAAQI-Net was evaluated under varying Sound Pressure Level (SPL) conditions, revealing optimal performance at a reference SPL of 65 dB, with accuracy gradually decreasing as SPL deviated from this point. The advancements in subjective score prediction, SPL robustness, and computational efficiency position HAAQI-Net as a scalable solution for music audio quality assessment in hearing aid applications, contributing to efficient and accurate models in audio signal processing and hearing aid technology. Copyright © 2024, The Authors. All rights reserved.

关键词： Mean square error

来源：评论

学校读者我要写书评

暂无评论

Foliated field theories and multipole symmetries

引用

Physical Review B 2024年第16期109卷 165112-165112页

作者： Hiromi Ebisu Masazumi Honda Taiichi Nakanishi Department of Physics and Astronomy Rutgers University Piscataway New Jersey 08854 USA Center for Gravitational Physics and Quantum Information Yukawa Institute for Theoretical Physics Kyoto University Sakyo-ku Kyoto 606-8502 Japan Interdisciplinary Theoretical and Mathematical Sciences Program (iTHEMS) RIKEN Wako 351-0198 Japan Theoretical Sciences Visiting Program Okinawa Institute of Science and Technology Graduate University (OIST) Onna 904-0495 Japan

Due to the recent studies of the fracton topological phases, the host of which deconfined quasiparticle excitations with mobility restrictions, the concept of symmetries has been updated. Focusing on one of these new symmetries, multipole symmetries, including global, dipole, and quadruple symmetries, and gauge fields associated with them, we construct new sets of ZN(2+1)-dimensional foliated background-field (BF) theories, where BF theories of conventional topological phases are stacked in layers with couplings between them. By investigating gauge-invariant nonlocal operators, we show that our foliated BF theories exhibit unusual ground-state degeneracy depending on the system size; it depends on the greatest common divisor between N and the system size. Our result provides an important connection between UV lattice models of the fracton topological phases and other unconventional ones in view of foliated field theories.

关键词： Anyons Fractons Topological field theories Topological order

来源：评论

学校读者我要写书评

暂无评论

TreeXGNN: can gradient-boosted decision trees help boost heterogeneous graph neural networks?

TreeXGNN: can gradient-boosted decision trees help boost het...

引用

International Conference on Acoustics, Speech, and Signal Processing (ICASSP)

作者： Ming-Yi Hong Shih-Yen Chang Hao-Wei Hsu Yi-Hsiang Huang Chih-Yu Wang Che Lin Graduate Program of Data Science National Taiwan University and Academia Sinica Taiwan Graduate Institute of Communication Engineering National Taiwan University Taiwan Research Center for Information Technology Innovation Academia Sinica Taiwan Department of Electrical Engineering National Taiwan University Taiwan

Graph neural networks are a promising deep learning method that can apply graph structures to various tasks. In real-world scenarios, we often have heterogeneous graphs, wherein different node and edge types capture complex interactions between nodes. High-dimensional node features provide rich information about the target nodes. Conventional heterogeneous graph neural networks (HGNN) focus more on graph structures than node features and may have difficulties extracting knowledge from complex node features. In this study, we propose a novel framework, the tree-boosted heterogeneous graph neural network abbreviated as TreeXGNN, which could efficiently and automatically extract target node features via gradient-boosted decision trees (GBDT). It integrates community structure information with proper fusion modules and a shared feature space design on HGNN. We achieved state-of-the-art performance on the three well-known heterogeneous graph benchmark datasets, IMDB, DBLP, and ACM, and significantly improved performance compared to previous studies. Our work paves the foundation for integrating tree-based models to boost HGNNs for general community analysis.

关键词： Training Knowledge engineering Deep learning Signal processing Feature extraction Graph neural networks Decision trees

来源：评论

学校读者我要写书评

暂无评论

Analysis of the Physical Capabilities of Individual Elderly People using Muscle Synergy and a Standing Assistance Robot based on this Analysis

Analysis of the Physical Capabilities of Individual Elderly ...

引用

Annual Conference of Industrial Electronics Society

作者： Haruki Asai Masataka Miyahara Daisuke Chugo Satoshi Muramatsu Sho Yokota Ken-Ichi Tabei Jin-Hua She Hiroshi Hashimoto Graduate School of Science and Technology Kwansei Gakuin University Sanda Hyogo Japan School of Engineering Kwansei Gakuin University Sanda Hyogo Japan School of Information Science and Technology Tokai University Hiratsuka Kanagawa Japan Faculty of Science and Engineering Toyo University Kawagoe Saitama Japan Master Program of Innovation for Design and Engineering Advanced Institute of Industrial Technology Shinagawa Tokyo Japan School of Engineering Tokyo University of Technology Hachioji Tokyo Japan

ISBN: (数字)9781665464543

ISBN: (纸本)9781665464550

The aim of this paper is to realize a robot that supports standing motion for elderly people with low care needs, using the person's residual physical strength to prevent further decline in their physical strength. To realize this objective, the two key ideas proposed in this paper are as follows. The first idea is to identify the multiple basic movements that make up the standing motion of the elderly through a muscle synergy analysis of the standing motion of the elderly. This makes it possible to design standing assistance procedures according to the physical condition of the elderly person, as the basic motions can be matched to the stability margin range, which varies from one elderly person to another. The second idea proposes standing assistance procedures that allow the voluntary standing motion of the elderly to demonstrate their remaining physical abilities in standing motions. Even if an elderly person performs a standing assistance procedure that differs from the designed standing assistance procedure, our standing assistance robot allows the posture of the elderly person if it is within the stability margin of the individual elderly person, and only gives force assistance to the elderly person if the posture is not within the stability margin. This leads to safety and voluntary movement during standing motion. The above proposed method was implemented in our standing assistance robot prototype, and through experiments with subjects, we confirmed that it brought out the subject's remaining physical strength in standing assistance procedures.

关键词： Industrial electronics Service robots Force Prototypes Position control Muscles Stability analysis Safety Object recognition Older adults

来源：评论

学校读者我要写书评

暂无评论

Into 3D-Reconstructed Apparel over Virtual Try-On with Virtual Reality

Into 3D-Reconstructed Apparel over Virtual Try-On with Virtu...

引用

IEEE International Conference on Consumer Electronics-Taiwan (ICCE-TW)

作者： Surasachai Doungtap Jirayu Petchhan Varinya Phanichraksaphong Jenq-Haur Wang International Graduate Program of Electrical Engineering and Computer Science Dept. of Electrical Engineering National Taiwan University of Science & Technology Taiwan R. O. C. Department of Computer Science and Information Engineering National Taipei University of Technology Taiwan R. O. C.

Virtualization technologies are still growing bigger and faster. Despite the greatness of its advancement, the costume industry is still very accessible when it comes to real trials. Off-the-shelf stuff are inadequate details for the desired individual to assess its in-depth utility for each garment trying on for a second, including custom stuff are much harder to try out right away. To this end, 2D image-based 3D reconstruction inclusive of touchable-virtualized space is accessible easier to stuff details for mans' decision making in purchasing. We establish the overall end-to-end pipeline from reconstruction until visualization for one instance to be triable on its stuff for a moment. As an expectation, our proposed approach can bring objects into the experimental area and use them immediately without any obstacle.

关键词：

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：