检索结果-内蒙古大学图书馆

arXiv 2023年

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

Multimodal manipulations (also known as audiovisual deepfakes) make it difficult for unimodal deepfake detectors to detect forgeries in multimedia content. To avoid the spread of false propaganda and fake news, timely detection is crucial. The damage to either modality (i.e., visual or audio) can only be discovered through multi-modal models that can exploit both pieces of information simultaneously. Previous methods mainly adopt uni-modal video forensics and use supervised pre-training for forgery detection. This study proposes a new method based on a multi-modal self-supervised-learning (SSL) feature extractor to exploit inconsistency between audio and visual modalities for multi-modal video forgery detection. We use the transformer-based SSL pre-trained Audio-Visual HuBERT (AV-HuBERT) model as a visual and acoustic feature extractor and a multi-scale temporal convolutional neural network to capture the temporal correlation between the audio and visual modalities. Since AV-HuBERT only extracts visual features from the lip region, we also adopt another transformer-based video model to exploit facial features and capture spatial and temporal artifacts caused during the deepfake generation process. Experimental results show that our model outperforms all existing models and achieves new state-of-the-art performance on the FakeAVCeleb and DeepfakeTIMIT datasets. © 2023, CC BY.

关键词： Audio acoustics

来源：评论

学校读者我要写书评

暂无评论

HAEE: Question Classification Using Hierarchical Intra-Attention Enhancement Encoder

HAEE: Question Classification Using Hierarchical Intra-Atten...

引用

International Conference on Technologies and Applications of Artificial Intelligence (TAAI)

作者： Jen-Wei Wang Kai-Hsiang Chen Jen-Wei Huang National Cheng Kung University Tainan Taiwan Graduate Program for Multimedia Systems and Intelligent Computing National Cheng Kung University and Academia Sinica Taiwan

ISBN: (纸本)9781665408264

With the development of E-commerce, an Automated Question-Answering system takes a crucial part in customer service. Question classification, which assigns labels to questions according to the answer types, is one of the tasks in question answering. Previous methods usually used handcraft features like named entity recognition, but it needs the predefined dictionary or tools. The machine learning approaches are recently applied to this task and achieve high accuracy. In this paper, we proposed HAEE, a Hierarchical intra-Attention Enhancement Encoder which composed of bidirectional GRUs and intra-attentions. In addition, we adopt the character input to address the issue of the OOV (Out-Of-Vocabulary) problem and create multiple intra-attentions to simulate the certain relationships between characters (Chinese) or words (English) to enhance the influence of tokens on the sentence. We evaluate the HAEE model in an actual corporate setting and several datasets. As shown in the experimental results, our HAEE model outperforms the existing state-of-the-art models on question classification tasks, especially for the Chinese corpus.

关键词： Dictionaries Customer services Machine learning Predictive models Electronic commerce Task analysis

来源：评论

学校读者我要写书评

暂无评论

Bias Evaluation and Mitigation in Retrieval-Augmented Medical Question-Answering systems

arXiv

引用

arXiv 2025年

作者： Ji, Yuelyu Zhang, Hang Wang, Yanshan Dept. of Information Science University of Pittsburgh PittsburghPA United States Intelligent Systems Program School of Computing and Information University of Pittsburgh PittsburghPA United States Dept. of Health Information Management University of Pittsburgh PA United States Clinical and Translational Science Institute University of Pittsburgh PittsburghPA United States University of Pittsburgh Medical Center PittsburghPA United States

Medical Question-Answering (QA) systems based on Retrieval-Augmented Generation (RAG) are promising for clinical decision support due to their capability to integrate external knowledge, thus reducing inaccuracies inherent in standalone large language models (LLMs). However, these systems may unintentionally propagate biases associated with sensitive demographic attributes like race, gender, and socioeconomic factors. This study systematically evaluates demographic biases within medical RAG pipelines across multiple QA benchmarks, including MedQA, MedMCQA, MMLU, and EquityMedQA. We quantify disparities in retrieval consistency and answer correctness by generating and analyzing queries sensitive to demographic variations. We further implement and compare several bias mitigation strategies—including Chain-of-Thought reasoning, Counterfactual filtering, Adversarial prompt refinement, and Majority Vote aggregation—to address identified biases. Experimental results reveal significant demographic disparities, highlighting that Majority Vote aggregation improves accuracy and fairness metrics. Our findings underscore the critical need for explicitly fairness-aware retrieval methods and prompt engineering strategies to develop truly equitable medical QA systems. © 2025, CC BY.

关键词： Decision support systems

来源：评论

学校读者我要写书评

暂无评论

Learning Pairwise Preferences from Movie Ratings 7

Learning Pairwise Preferences from Movie Ratings

引用

7th International Conference on ICT for Smart Society, ICISS 2020

作者： Qomariyah, Nunung Nurul Fajar, Ahmad Nurul Bina Nusantara University Faculty of Computing and Media Computer Science Department Jakarta11480 Indonesia Bina Nusantara University BINUS Graduate Program-Master of Information Systems Management Information Systems Management Department Jakarta11480 Indonesia

ISBN: (纸本)9781665404228

Preference Elicitation is now considered a crucial stage in recommender system. That is the stage where we collect and query preferences of the users as part of interactive decision support system. Preference elicitation can be performed using many ways, such as asking the user explicitly to give ratings or feedbacks for some products, or implicitly observing their behaviour. Once this preference has been collected by the system, it can then be used to generate item recommendation. Using explicit feedback itself, such as rating only, has several drawbacks. Using ratings is very subjective. Two users with similar taste might give different rating to the same item. A user also may not be consistent in giving number to express their liking. In other case, a user may like an item more than the other items, but feels difficult to give lower rating on the other item, because it means that the particular item is just as bad as the one he/she does not like. By showing two different items as a pair, it will be easier for the users to pick which one is the best. In this paper, we show the result of our experiment in predicting user pairwise preferences by using their movie ratings data. We evaluated five different machine learning algorithms to predict the data in pairwise preference format. The result shows that K-Nearest Neighbour and Random Forest outperformed the other algorithms. © 2020 IEEE.

关键词： Recommender systems

来源：评论

学校读者我要写书评

暂无评论

An Analysis Method for Metric-Level Switching in Beat Tracking

arXiv

引用

arXiv 2022年

作者： Chiu, Ching-Yu Müller, Meinard Davies, Matthew E.P. Su, Alvin Wen-Yu Yang, Yi-Hsuan Graduate Program of Multimedia Systems and Intelligent Computing National Cheng Kung University Academia Sinica Taiwan International Audio Laboratories Erlangen Germany Department of Informatics Engineering Centre for Informatics and Systems The University of Coimbra University of Coimbra Portugal Department of CSIE National Cheng Kung University Taiwan Taiwan AI Labs Taiwan

For expressive music, the tempo may change over time, posing challenges to tracking the beats by an automatic model. The model may first tap to the correct tempo, but then may fail to adapt to a tempo change, or switch between several incorrect but perceptually plausible ones (e.g., half- or double-tempo). Existing evaluation metrics for beat tracking do not reflect such behaviors, as they typically assume a fixed relationship between the reference beats and estimated beats. In this paper, we propose a new performance analysis method, called annotation coverage ratio (ACR), that accounts for a variety of possible metric-level switching behaviors of beat trackers. The idea is to derive sequences of modified reference beats of all metrical levels for every two consecutive reference beats, and compare every sequence of modified reference beats to the subsequences of estimated beats. We show via experiments on three datasets of different genres the usefulness of ACR when being utilized alongside existing metrics, and discuss the new insights that can be gained. © 2022, CC BY.

关键词： Taps

来源：评论

学校读者我要写书评

暂无评论

Anterior Cruciate Ligament Classification in Knee MRI using Automated Pseudo-Masking

Anterior Cruciate Ligament Classification in Knee MRI using ...

引用

Medical Imaging 2023: Computer-Aided Diagnosis

作者： Dadsetan, Saba Albers, Marcio Weinstock, Allison Musahl, Volker Kitamura, Gene Arefan, Dooman Wu, Shandong Intelligent Systems Program School of Computing and Information University of Pittsburgh PittsburghPA15213 United States Department of Radiology School of Medicine University of Pittsburgh PittsburghPA15213 United States Department of Biomedical Informatics School of Medicine University of Pittsburgh PittsburghPA15213 United States Department of Bioengineering School of Engineering University of Pittsburgh PittsburghPA15213 United States Department of Orthopedic Surgery School of Medicine University of Pittsburgh PittsburghPA15213 United States Department of Radiology Loma Linda University Medical Center Loma LindaCA92354 United States

ISBN: (纸本)9781510660359

Anterior cruciate ligament (ACL) is one of the most common injuries associated with sports. Knee osseous morphology can play a role in increased knee instability. Our hypothesis is that the morphological features of the knee, as seen in knee osseous morphology, can contribute to increased knee instability and, thus, increase the likelihood of ACL tear. To test this relationship, it is necessary to segment the femur and tibia bones and extract relevant imaging features. However, manual annotation of 3D medical images, such as on magnetic resonance imaging (MRI) scans, can be a time-consuming and challenging task. In this work, we propose an automated pipeline for creating pseudo-masks of the femur and tibia bones in knee MRI. Our approach involves unsupervised segmentation and deep learning models to classify ACL integrity (intact or torn). Our results demonstrate a high agreement between the automated pseudo-masks and a radiologist's manual segmentation, which also leads to comparable AUC values for the ACL integrity classification. © 2023 SPIE.

关键词： Magnetic resonance imaging

来源：评论

学校读者我要写书评

暂无评论

CIS controls the functional polarization of GM-CSF-derived macrophages

引用

Cellular & Molecular Immunology 2023年第1期20卷 65-79页

作者： Shengbo Zhang Jai Rautela Naiara G.Bediaga Tatiana B.Kolesnik Yue You Junli Nie Laura F.Dagley Justin Bedo Hanqing Wang Li Sun Robyn Sutherland Elliot Surgenor Nadia Iannarella Rhys Allan Fernando Souza-Fonseca-Guimaraes Yi Xie Qike Wang Yuxia Zhang Yuekang Xu Stephen L.Nutt Andrew M.Lew Nicholas D.Huntington Sandra E.Nicholson Michaël Chopin Yifan Zhan Walter and Eliza Hall Institute of Medical Research ParkvilleVICAustralia Department of Medical Biology University of MelbourneParkvilleVICAustralia Department of Biochemistry and Molecular Biology Biomedicine Discovery InstituteMonash UniversityClaytonVICAustralia oNKo-Innate Pty Ltd Moonee PondsVICAustralia Department of Computing and Information Systems University of MelbourneParkvilleVICAustralia Department of Respiratory Medicine Guangzhou Institute of PediatricsGuangzhou Women and Children’s Medical CentreState Key Laboratory of Respiratory DiseasesGuangzhou Medical UniversityGuangzhouGuangdongChina College of Biological Science Anhui Normal UniversityHefeiChina University of Queensland Diamantina Institute University of QueenslandTranslational Research InstituteBrisbaneQLDAustralia Program in Cardiovascular and Metabolic Disorders Duke-NUS Medical SchoolDukeSingapore Drug Discovery Shanghai Huaota BiopharmShanghaiChina

The cytokine granulocyte-macrophage-colony stimulating factor (GM-CSF) possesses the capacity to differentiate monocytes into macrophages (MØs) with opposing functions, namely, proinflammatory M1-like MØs and immunosuppressive M2-like MØs. Despite the importance of these opposing biological outcomes, the intrinsic mechanism that regulates the functional polarization of MØs under GM-CSF signaling remains elusive. Here, we showed that GM-CSF-induced MØ polarization resulted in the expression of cytokine-inducible SH2-containing protein (CIS) and that CIS deficiency skewed the differentiation of monocytes toward immunosuppressive M2-like MØs. CIS deficiency resulted in hyperactivation of the JAK-STAT5 signaling pathway, consequently promoting downregulation of the transcription factor Interferon Regulatory Factor 8 (IRF8). Loss- and gain-of-function approaches highlighted IRF8 as a critical regulator of the M1-like polarization program. In vivo, CIS deficiency induced the differentiation of M2-like macrophages, which promoted strong Th2 immune responses characterized by the development of severe experimental asthma. Collectively, our results reveal a CIS-modulated mechanism that clarifies the opposing actions of GM-CSF in MØ differentiation and uncovers the role of GM-CSF in controlling allergic inflammation.

关键词： CIS GM-CSF Macrophage M2 M1

来源：评论

学校读者我要写书评

暂无评论

Improvement of Spatial Ambiguity in Multi-Channel Speech Separation Using Channel Attention

Improvement of Spatial Ambiguity in Multi-Channel Speech Sep...

引用

Asia-Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA)

作者： Qian-Bei Hong Chung-Hsien Wu Thanh Binh Nguyen Hsin-Min Wang Graduate Program of Multimedia Systems and Intelligent Computing National Cheng Kung University and Academia Sinica Tainan Taiwan National Cheng Kung University Tainan Taiwan

ISBN: (纸本)9781665441629

Multi-channel speech separation has been successfully applied in a complex real-world environment such as the far-field condition. The common solution to deal with the far-field condition is using a multi-channel signal captured by a structured microphone array and leveraging the inner difference between channels to enhance the speech separation performance. The spatial feature has been widely used in recent speech separation research. This feature appears to be insufficient when the location information becomes ambiguous. This is known as the spatial ambiguity problem. In order to deal with the spatial ambiguity problem, this study proposes an attention mechanism for the Temporal-Spatial Neural Filter (TSNF), in which the channel attention on merged features and the feature map of 1D convolution block in the temporal convolution network is proposed. The proposed method is evaluated on the multi-channel reverberant dataset which is built based on the WSJ0-2mix dataset. The dataset is simulated in the real-environment room by using the Room Impulse Response generator. In the experimental results, the proposed methods produced the SI -SNR improvement of about 1.2dB in close speakers' case, while a small decrease of 0.1dB in other cases.

关键词： Convolution Information processing Speech enhancement Information filters Microphone arrays Generators Reliability

来源：评论

学校读者我要写书评

暂无评论

Behavior analysis of students in video classes

Behavior analysis of students in video classes

引用

2020 IEEE Frontiers in Education Conference, FIE 2020

作者： Silva, Francisco Genivan Da Silva, Thiago Reis De Oliveira Santana, Alan Aranha, Eduardo Federal Institute of Education Science and Technology - Ifrn Currais Novos Brazil Federal University of Rio Grande Do Norte - Ufrn Postgraduate Program in Systems and Computing - PPgSC Natal Brazil

ISBN: (纸本)9781728189611

This Research-to-Practice full paper presents the result of a study whose core is characterized by the application of data analysis techniques from the use of video lessons. Distance education contributes to the generation of educational data to conduct investigations of educational processes. Methodologies for the automatic extraction of useful information from large volumes of data, especially data mining, have significantly contributed to improvements in the field of education. However, most traditional methods focus entirely on the data or how it is structured, with no significant concern with the educational process as a whole. Also, little attention has been given to information related to the students' behavior during the use of educational resources and media. Therefore, we consider that examining the students' behavior during the execution of educational videos can contribute to a more accurate analysis of the quality of the resources used, the way they learn, and what factors influence their learning. Thus, this research to practice full paper presents conducts a study to investigate how students behave during the use of video classes and seek to highlight the benefits of this type of analysis for education. Results demonstrate that evaluating the educational resource through the analysis of the actions involved can contribute substantially to the activities performed by teachers and content makers. © 2020 IEEE.

关键词： Students

来源：评论

学校读者我要写书评

暂无评论

Opportunities and Challenges from Using Animal Videos in Reinforcement Learning for Navigation

arXiv

引用

arXiv 2022年

作者： Giammarino, Vittorio Queeney, James Carstensen, Lucas C. Hasselmo, Michael E. Paschalidis, Ioannis Ch. Division of Systems Engineering Boston University BostonMA02215 United States Center for Systems Neuroscience Department of Psychological and Brain Sciences Graduate Program for Neuroscience Boston University BostonMA02215 United States College of Engineering Hariri Institute for Computing & Computational Science & Engineering Boston University BostonMA02215 United States

We investigate the use of animal videos (observations) to improve Reinforcement Learning (RL) efficiency and performance in navigation tasks with sparse rewards. Motivated by theoretical considerations, we make use of weighted policy optimization for off-policy RL and describe the main challenges when learning from animal videos. We propose solutions and test our ideas on a series of 2D navigation tasks. We show how our methods can leverage animal videos to improve performance over RL algorithms that do not leverage such observations. © 2022, CC BY.

关键词： Reinforcement learning

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：