检索结果-内蒙古大学图书馆

arXiv 2025年

作者： Hou, Abe Bohan Du, Hongru Wang, Yichen Zhang, Jingyu Wang, Zixiao Liang, Paul Pu Khashabi, Daniel Gardner, Lauren He, Tianxing Department of Computer Science Johns Hopkins University United States Department of Civil & System Engineering Johns Hopkins University United States Department of Computer Science University of Chicago United States Department of Epidemiology Harvard University United States Media Lab and EECS Massachusetts Institute of Technology United States Institute of Interdisciplinary Information Sciences Tsinghua University China Shanghai Qi Zhi Institute China

Can we simulate a sandbox society with generative agents to model human behavior, thereby reducing the over-reliance on real human trials for assessing public policies? In this work, we investigate the feasibility of simulating health-related decision-making, using vaccine hesitancy, defined as the delay in acceptance or refusal of vaccines despite the availability of vaccination services (MacDonald, 2015), as a case study. To this end, we introduce the VACSIM1 framework with 100 generative agents powered by Large Language Models (LLMs). VACSIM simulates vaccine policy outcomes with the following steps: 1) instantiate a population of agents with demographics based on census data;2) connect the agents via a social network and model vaccine attitudes as a function of social dynamics and disease-related information;3) design and evaluate various public health interventions aimed at mitigating vaccine hesitancy. To align with real-world results, we also introduce simulation warmup and attitude modulation to adjust agents’ attitudes. We propose a series of evaluations to assess the reliability of various LLM simulations. Experiments indicate that models like Llama and Qwen can simulate aspects of human behavior but also highlight real-world alignment challenges, such as inconsistent responses with demographic profiles. This early exploration of LLM-driven simulations is not meant to serve as definitive policy guidance;instead, it serves as a call for action to examine social simulation for policy development. Copyright © 2025, The Authors. All rights reserved.

关键词： Population statistics

来源：评论

学校读者我要写书评

暂无评论

Methods for pitch analysis in contemporary popular music: highlighting pitch uncertainty in Primaal’s commercial works

arXiv

引用

arXiv 2025年

作者： Deruty, Emmanuel Leroy, Luc Macé, Yann Meredith, David Sony Computer Science Laboratories 6 rue Amyot Paris75005 France Neodrome Entertainment 5 rue Vernet Paris75008 France Department of Architecture Design and Media Technology Aalborg University Rendsburggade 14 Aalborg9000 Denmark

We identify characteristic features of how pitch is manipulated for expressive purposes by Hyper Music, a mainstream commercial music company specialising in advertisement music for global corporations. The study shows that the use and organisation of pitch in the company’s ‘Primaal’ brand differs from Western classical music. Through interviews with producers and in-depth analysis of their work, we reveal that their methods centre on a conscious aim to construct a musical discourse based on pitch uncertainty, contrasting with the clear transmission of well-defined pitches in Western classical traditions. According to the Primaal producers, who acknowledge the influence of artists such as Kanye West and Daft Punk and use widely available technology, pitch uncertainty captures the listener’s attention. We provide analyses of musical excerpts demonstrating their approach, alongside descriptions of the tools and methods employed to achieve their expressive goals. These goals and methods are placed in a broader historical context, contrasting with fundamental principles of pitch organisation in Western music. Techniques used by Hyper Music to introduce and control pitch uncertainty include boosting upper partials, expressive use of inharmonicity, continuous pitch distributions around ‘poles’ tied to specific ‘modes’, and continuously evolving pitch. We examine these techniques from a psychoacoustic perspective, and conduct listening tests corroborating some of the observations. The ultimate goal of the study is to introduce a set of methods suited to the analysis of pitch in contemporary popular *** Codes 00A65 © 2025, CC BY.

关键词： Music

来源：评论

学校读者我要写书评

暂无评论

LEARNING DISCRIMINATIVE FEATURES FROM SPECTROGRAMS USING CENTER LOSS FOR SPEECH EMOTION RECOGNITION

arXiv

引用

arXiv 2025年

作者： Dai, Dongyang Wu, Zhiyong Li, Runnan Wu, Xixin Jia, Jia Meng, Helen Tsinghua-CUHK Joint Research Center for Media Sciences Technologies and Systems Graduate School at Shenzhen Tsinghua University Shenzhen China Department of Computer Science and Technology Tsinghua University Beijing China Department of Systems Engineering and Engineering Management The Chinese University of Hong Kong Shatin Hong Kong

Identifying the emotional state from speech is essential for the natural interaction of the machine with the speaker. However, extracting effective features for emotion recognition is difficult, as emotions are ambiguous. We propose a novel approach to learn discriminative features from variable length spectrograms for emotion recognition by cooperating softmax cross-entropy loss and center loss together. The softmax cross-entropy loss enables features from different emotion categories separable, and center loss efficiently pulls the features belonging to the same emotion category to their center. By combining the two losses together, the discriminative power will be highly enhanced, which leads to network learning more effective features for emotion recognition. As demonstrated by the experimental results, after introducing center loss, both the unweighted accuracy and weighted accuracy are improved by over 3% on Mel-spectrogram input, and more than 4% on Short Time Fourier Transform spectrogram input. Copyright © 2025, The Authors. All rights reserved.

关键词： Spectrographs

来源：评论

学校读者我要写书评

暂无评论

Encoding syntactic representations with a neural network for sentiment collocation extraction

引用

science China(Information sciences) 2017年第11期60卷 7-18页

作者： Yanyan ZHAO Bing QIN Ting LIU Department of Media Technology and Art Harbin Institute of Technology Department of Computer Science and Technology Harbin Institute of Technology

Sentiment collocation refers to the collocation of a target word and a polarity word. Sentiment collocation extraction aims to extract the targets and their modifying polarity words by analyzing the relationships between them. This can be regarded as a basic sentiment analysis task and is relevant in many practical applications. Previous studies relied mainly on the syntactic path, which is used to connect the target word and the polarity word. To deeply exploit the semantic information of the syntactic path, we propose two types of syntactic representation, namely, relation embedding and subtree embedding, to capture the latent semantic features. Relation embedding is used to represent the latent semantics between targets and their corresponding polarity words, and subtree embedding is used to explore the rich syntactic information for each word on the path. To combine the two types of syntactic representations, a neural network is constructed. We use a recursive neural network(RNN) to model the subtree embeddings, and then the subtree embedding and the word embedding are combined as the enhanced word representation for each word in the syntactic path. Finally,a convolutional neural network(CNN) is adopted to integrate the two types of syntactic representations to extract the sentiment collocations from reviews. Our experiments were conducted on six types of reviews, which included product domains(such as cameras and phones) and service domains(such as hotels and restaurants).The experimental results show that our proposed method can accurately capture the latent semantic features hidden behind the syntactic paths that neither the common feature-based methods nor the syntactic-path-based method can handle, and, further, that it significantly outperforms numerous baselines and previous methods.

关键词： sentiment collocation extraction sentiment analysis syntactic representation neural network re cursive neural network(RNN) convolutional neural network(CNN)

来源：评论

学校读者我要写书评

暂无评论

Intelligent Flagged Content Detection with Transformer-Based Models for Secure Online Environments

Intelligent Flagged Content Detection with Transformer-Based...

引用

International Electrical Engineering Congress (iEECON)

作者： R. S. Lakshmi Balaji G. Abirami Sirimonpak Suwannakhun Thiruvenkataswamy C S Thaweesak Yingthawornsuk Department of Advanced Computing Sciences Academy of Maritime Education and Training University (AMET) Chennai India Department of Computer Science and Engineering Academy of Maritime Education and Training University (AMET) Chennai India Faculty of Industrial Education and Technology King Mongkut's University of Technology Thonburi Bangkok Thailand National Cadet Corps Govt of India Tamil Nadu India Department of Media Technology King Mongkut's University of Technology Thonbur Bangkok Thailand

ISBN: (数字)9798331543952

ISBN: (纸本)9798331543969

The increasing volume of user-generated content on global online platforms has made it very crucial to detect and moderate harmful content like criminal activities, illegal substances, extremist codewords, and other prohibited materials across multiple languages. In this study, we present an intelligent system for detecting flagged content using advanced transformer-based models such as BERT, RoBERTa, XLNet, and T5. These models have been further trained to very accurately and effectively detect from illegal activities to extreme language and drug related content. Our method surpasses previous methods of content moderation achieving great improvements in classification accuracy, precision, recall and F1-score. Furthermore, the implemented system enables offline or online real-time process and therefore large-scale throughput. It also gives a detailed overview of the architectural designs of the model, training processes and other problems faced during the model development stage. The results illustrate the power of transformer-based models in offering a robust strategy for automated detection of flagged content across languages to help in cultivating better online safety. This research also contributes to SDG 16 by enhancing online security and SDG 10 by promoting fairer digital spaces. The study concludes with a discussion on potential applications in social media moderation, law enforcement, and global security agencies and future research aimed at improving detection capabilities.

关键词： Training Accuracy Law enforcement Social networking (online) User-generated content Transformers Throughput Real-time systems Multilingual Security

来源：评论

学校读者我要写书评

暂无评论

A Fine-Grained Flash-Memory Fragment Recognition Approach for Low-Level Data Recovery

引用

Chinese Journal of Electronics 2022年第4期31卷 732-740页

作者： ZHANG Li HAO Shengang ZHANG Quanxin Department of Media Engineering Zhejiang University of Media and Communication School of Computer Science Beijing Institute of Technology

Data recovery from flash memory in the mobile device can effectively reduce the loss caused by data corruption. Type recognition of data fragment is an essential prerequisite to the low-level data recovery. Previous works in this field classify data fragment based on its file type. Still, the classification efficiency is low, especially when the data fragment is a part of a composite *** propose a fine-grained approach to classifying data fragment from the low-level flash memory to improve the classification accuracy and efficiency. The proposed method redefines flash-memory-page data recognition problem based on the encoding format of the data segment, and applies a hybrid machine learning algorithm to detect the data type of the flash page. The hybrid algorithm can significantly decompose the given data space and reduce the cost of training. The experimental results show that our method achieves better classification accuracy and higher time performance than the existing methods.

关键词： data handling flash memories File organisation type recognition flash page fine-grained flash-memory fragment recognition approach fine-grained approach Semiconductor storage Other topics in statistics classifying data fragment computer vision and image processing techniques low-level data recovery data corruption pattern classification given data space low-level flash memory classification accuracy learning (artificial intelligence) storage management data segment Memory circuits Codes Data handling techniques method redefines flash-memory-page data recognition problem error correction codes

来源：评论

学校读者我要写书评

暂无评论

Embodied AI-Enhanced Vehicular Networks: An Integrated Large Language Models and Reinforcement Learning Method

arXiv

引用

arXiv 2025年

作者： Zhang, Ruichen Zhao, Changyuan Du, Hongyang Niyato, Dusit Wang, Jiacheng Sawadsitang, Suttinee Shen, Xuemin Kim, Dong In The College of Computing and Data Science Nanyang Technological University Singapore The Department of Electrical and Electronic Engineering City University of Hong Kong Pok Fu Lam Hong Kong The College of Arts Media and Technology Chiang Mai University Suthep 50200 Thailand The Department of Electrical and Computer Engineering University of Waterloo Canada The Department of Electrical and Computer Engineering Sungkyunkwan University Suwon16419 Korea Republic of

This paper investigates adaptive transmission strategies in embodied AI-enhanced vehicular networks by integrating large language models (LLMs) for semantic information extraction and deep reinforcement learning (DRL) for decision-making. The proposed framework aims to optimize both data transmission efficiency and decision accuracy by formulating an optimization problem that incorporates the Weber-Fechner law, serving as a metric for balancing bandwidth utilization and quality of experience (QoE). Specifically, we employ the large language and vision assistant (LLAVA) model to extract critical semantic information from raw image data captured by embodied AI agents (i.e., vehicles), reducing transmission data size by approximately more than 90% while retaining essential content for vehicular communication and decision-making. In the dynamic vehicular environment, we employ a generalized advantage estimation-based proximal policy optimization (GAE-PPO) method to stabilize decision-making under uncertainty. Simulation results show that attention maps from LLAVA highlight the model’s focus on relevant image regions, enhancing semantic representation accuracy. Additionally, our proposed transmission strategy improves QoE by up to 36% compared to DDPG and accelerates convergence by reducing required steps by up to 47% compared to pure PPO. Further analysis indicates that adapting semantic symbol length provides an effective trade-off between transmission quality and bandwidth, achieving up to a 61.4% improvement in QoE when scaling from 4 to 8 vehicles. © 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

Human-Robot Experience (HRX) Theatre—An Interdisciplinary Methodology for Reimagining Human-Robot Relationships Through Movement 25

Human-Robot Experience (HRX) Theatre—An Interdisciplinary M...

引用

ACM/IEEE International Conference on Human-Robot Interaction (HRI)

作者： Petra Gemeinboeck Rob Saunders Audrey Rochette Steph Hutchison Kristina Mah Center for Transformative Media Technology (CTMT) Swinburne University of Technology Melbourne Australia Leiden Institute of Advanced Computer Science (LIACS) Leiden University Leiden Netherlands Dance Department Université du Québec à Montréal Montreal Canada School of Creative Arts Queensland University of Technology Brisbane Australia Design Lab The University of Sydney Sydney Australia

ISBN: (数字)9798350378931

ISBN: (纸本)9798350378948

How can we connect with robots without mimicking human traits? Can we build meaningful relationships with nonhuman-like bodies? What if sociality emerges in the encounter itself? The Human-Robot Experience (HRX) Theatre tutorial introduces a participatory methodology for reimagining our relationships with robots through movement-based, experience-centered exploration. Participants will explore how we bodily resonate and make meaning with non-anthropomorphic machines using our Relational Body Mapping (RBM) method, employing robot costumes to facilitate embodied perspective-taking. Adopting a robot's unique perspective to experience its distinct social affordances expands our understanding beyond anthropocentric views, unlocking new modes of nonverbal communication and embodied empathy. Movement and its meaning-making potential are key to HRX. We begin with gentle movement explorations. This heightened sensitivity will shape our first embodied dialogues with artifacts. A live performance with dancers, costumes, and a robot will showcase how RBM harnesses kinesthetic awareness to explore how sociality arises in the encounter. Applying their embodied insights, participants will develop and enact inclusive speculative scenarios through embodied role-play with robot costumes. This tutorial introduces an embodied prototyping approach that leverages the potential of movement dynamics for designing expressive, nonhumanlike robots. Cultivating empathy with machinelike entities could promote the design of more diverse and sustainable relationships that recognize and leverage the differences between humans and robots. No prior dance experience is required; participants will engage at their own comfort level. Join us to explore the transformative potential of movement in reimagining our robotic futures! Supported by the Australian Government through the Australian Research Council (FT190100567).

关键词： Humanities Sensitivity Shape Affordances Government Human-robot interaction Tutorials Robot sensing systems

来源：评论

学校读者我要写书评

暂无评论

Formula for computing knots with minimum stress and stretching energies

引用

science China(Information sciences) 2018年第5期61卷 171-185页

作者： Xuemei LI Fan ZHANG Guoning CHEN Caiming ZHANG School of Computer Science and Technology Shandong University School of Computer Science and Technology Shandong Technology and Business University Department of Computer Science University of Houston Shandong Provincial Key Laboratory of Digital Media Technology

Computing knots for a given set of data points in a plane is one of the key steps in the construction of fitting curves with high precision. In this study, a new method is proposed for computing a parameter value(knot) for each data point. With only three adjacent consecutive data points, one may not determine a unique interpolation quadratic polynomial curve, which has one degree of freedom(a variable). To obtain a better curve, the stress and stretching energies are used to optimize this variable so that the quadratic polynomial curve has required properties, which ensure that when the three consecutive points are co-linear, the optimal quadratic polynomial curve constructed is the best. If the position of the mid-point of the three points lies between the first point and the third point, the quadratic polynomial curve becomes a linear polynomial curve. Minimizing the stress and stretching energies is a time-consuming task. To avoid the computation of energy minimization, a new model for simplifying the stress and stretching energies is presented. The new model is an explicit function and is used to compute the knots directly, which greatly reduces the amount of computation. The knots are computed by the new method with minimum stress and stretching energies in the sense that if the knots computed by the new method are used to construct quadratic polynomial,the quadratic polynomial constructed has the minimum stress and stretching energies. Experiments show that the curves constructed using the knots generated by the proposed method result in better interpolation precision than the curves constructed using the knots by the existing methods.

关键词： parameter stress and stretching energies polynomial precision curve construction

来源：评论

学校读者我要写书评

暂无评论

Pixel Memories: Do Lifelog Summaries Fail to Enhance Memory but Offer Privacy-Aware Memory Assessments? 25

Pixel Memories: Do Lifelog Summaries Fail to Enhance Memory ...

引用

Proceedings of the 2025 CHI Conference on Human Factors in Computing Systems

作者： Passant Elagroudy Rufat Rzayev Tonja-Katrin Machulla Huy Viet Le Tilman Dingler Lars Lischke Sarah Clinch Geoffrey Ward Albrecht Schmidt German Research Centre for Artificial Intelligence (DFKI) Kaiserslautern Germany and RPTU Kaiserslautern Kaiserslautern Germany Interactive Media Lab Dresden TUD Dresden University of Technology Dresden Germany Institute for Media Research TU Chemnitz Chemnitz Germany University of Stuttgart Stuttgart Germany Industrial Design Engineering Delft University of Technology Delft Netherlands User Centric Data Science Vrije Universiteit Amsterdam Amsterdam Netherlands Department of Computer Science The University of Manchester Manchester United Kingdom Department of Psychology University of Essex Essex United Kingdom LMU Munich Munich Germany

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：