检索结果-内蒙古大学图书馆

arXiv 2023年

作者： Ahmad, Wasim Peng, Yan-Tsung Chang, Yuan-Hao Ganfure, Gaddisa Olani Khan, Sarwar Shahzad, Sahibzada Adil Institute of Information Science Academia Sinica Taipei11529 Taiwan Department of Computer Science National Chengchi University Taipei116 Taiwan Social Networks Human-Centered Computing Taiwan International Graduate Program Academia Sinica Taipei11529 Taiwan Dire Dawa University Ethiopia Research Center for Information Technology Innovation Academia Sinica Taipei11529 Taiwan

The proliferation of deepfake videos, synthetic media produced through advanced Artificial Intelligence techniques, has raised significant concerns across various sectors, encompassing realms such as politics, entertainment, and security. In response, this research introduces an innovative and streamlined model designed to classify deepfake videos generated by five distinct encoders adeptly. Our approach not only achieves state-of-the-art performance but also optimizes computational resources. At its core, our solution employs part of a VGG19_bn as a backbone to efficiently extract features, a strategy proven effective in image-related tasks. We integrate a Capsule Network coupled with a Spatial-Temporal attention mechanism to bolster the model’s classification capabilities while conserving resources. This combination captures intricate hierarchies among features, facilitating robust identification of deepfake attributes. Delving into the intricacies of our innovation, we introduce an existing video-level fusion technique that artfully capitalizes on temporal attention mechanisms. This mechanism serves to handle concatenated feature vectors, capitalizing on the intrinsic temporal dependencies embedded within deepfake videos. By aggregating insights across frames, our model gains a holistic comprehension of video content, resulting in more precise predictions. Experimental results on an extensive benchmark dataset of deepfake videos (DFDM) showcase the efficacy of our proposed method. Notably, our approach achieves up to a 4% improvement in accurately categorizing deepfake videos compared to baseline models, all while demanding fewer computational resources. Copyright © 2023, The Authors. All rights reserved.

关键词： Routing algorithms

来源：评论

学校读者我要写书评

暂无评论

R2 Indicator and Deep Reinforcement Learning Enhanced Adaptive Multi-Objective Evolutionary Algorithm

arXiv

引用

arXiv 2024年

作者： Tahernezhad-Javazm, Farajollah Rankin, Debbie Bois, Naomi Du Smith, Alice E. Coyle, Damien Intelligent Systems Research Center School of Computing Engineering and Intelligent Systems Ulster University LondonderryBT48 7JL United Kingdom The Bath Institute for Augmented Human University of Bath BathBA2 7AY United Kingdom The Department of Industrial and Systems Engineering Department of Computer Science and Software Engineering Auburn University AuburnAL36849 United States

Choosing an appropriate optimization algorithm is essential to achieving success in optimization challenges. Here we present a new evolutionary algorithm structure that utilizes a reinforcement learning-based agent aimed at addressing these issues. The agent employs a double deep q-network to choose a specific evolutionary operator based on feedback it receives from the environment during optimization. The algorithm’s structure contains five single-objective evolutionary algorithm operators. This single-objective structure is transformed into a multi-objective one using the R2 indicator. This indicator serves two purposes within our structure: first, it renders the algorithm multi-objective, and second, provides a means to evaluate each algorithm’s performance in each generation to facilitate constructing the reinforcement learning-based reward function. The proposed R2-reinforcement learning multi-objective evolutionary algorithm (R2-RLMOEA) is compared with six other multiobjective algorithms that are based on R2 indicators. These six algorithms include the operators used in R2-RLMOEA as well as an R2 indicator-based algorithm that randomly selects operators during optimization. We benchmark performance using the CEC09 functions, with performance measured by inverted generational distance and spacing. The R2-RLMOEA algorithm outperforms all other algorithms with strong statistical significance (p © 2024, CC BY.

关键词： Reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

Unlocking the Emotional World of Visual Media: An Overview of the science, Research, and Impact of Understanding Emotion

arXiv

引用

arXiv 2023年

作者： Wang, James Z. Zhao, Sicheng Wu, Chenyan Adams, Reginald B. Newman, Michelle G. Shafir, Tal Tsachor, Rachelle The Data Science and Artificial Intelligence Area the Human-Computer Interaction Area the College of Information Sciences and Technology The Pennsylvania State University University ParkPA16802 United States The Department of Psychology The Pennsylvania State University University ParkPA16802 United States BNRist Tsinghua University Beijing100084 China The Emily Sagol Creative Arts Therapies Research Center University of Haifa 3498838 Israel The School of Theatre and Music University of Illinois ChicagoIL60607 United States

The emergence of artificial emotional intelligence technology is revolutionizing the fields of computers and robotics, allowing for a new level of communication and understanding of human behavior that was once thought impossible. Whereas recent advancements in deep learning have transformed the field of computer vision, automated understanding of evoked or expressed emotions in visual media remains in its infancy. This foundering stems from the absence of a universally accepted definition of "emotion," coupled with the inherently subjective nature of emotions and their intricate nuances. In this paper, we provide a comprehensive, multidisciplinary overview of the field of emotion analysis in visual media, drawing on insights from psychology, engineering, and the arts. We begin by exploring the psychological foundations of emotion and the computational principles that underpin the understanding of emotions from images and videos. We then review the latest research and systems within the field, accentuating the most promising approaches. We also discuss the current technological challenges and limitations of emotion analysis, underscoring the necessity for continued investigation and innovation. We contend that this represents a "Holy Grail" research problem in computing and delineate pivotal directions for future inquiry. Finally, we examine the ethical ramifications of emotion-understanding technologies and contemplate their potential societal impacts. Overall, this article endeavors to equip readers with a deeper understanding of the domain of emotion analysis in visual media and to inspire further research and development in this captivating and rapidly evolving field. Copyright © 2023, The Authors. All rights reserved.

关键词： Intelligent robots

来源：评论

学校读者我要写书评

暂无评论

Explaining GPT-4's Schema of Depression Using Machine Behavior Analysis

arXiv

引用

arXiv 2024年

作者： Ganesan, Adithya V. Varadarajan, Vasudha Lal, Yash Kumar Eijsbroek, Veerle C. Kjell, Katarina Kjell, Oscar N.E. Dhanasekaran, Tanuja Stade, Elizabeth C. Eichstaedt, Johannes C. Boyd, Ryan L. Schwartz, H. Andrew Flek, Lucie Department of Computer Science Stony Brook University United States Department of Psychology Lund University Sweden United States Department of Psychology Stanford University United States Institute for Human-Centered AI Stanford University United States Department of Psychology School of Behavioral and Brain Sciences The University of Texas Dallas United States Bonn-Aachen International Center for Information Technology University of Bonn Germany The Lamarr Institute for Machine Learning and Artificial Intelligence Germany

Use of large language models such as ChatGPT (GPT-4) for mental health support has grown rapidly, emerging as a promising route to assess and help people with mood disorders, like depression. However, we have a limited understanding of GPT-4's schema of mental disorders, that is, how it internally associates and interprets symptoms. In this work, we leveraged contemporary measurement theory to decode how GPT-4 interrelates depressive symptoms to inform both clinical utility and theoretical understanding. We found GPT-4's assessment of depression: (a) had high overall convergent validity (r = 0.71 with self-report on 955 samples, and r = 0.81 with experts judgments on 209 samples);(b) had moderately high internal consistency (symptom inter-correlates r = .23 to .78) that largely aligned with literature and self-report except that GPT-4;(c) underemphasized suicidality's - and overemphasized psychomotor's - relationship with other symptoms, and (d) had symptom inference patterns that suggest nuanced hypotheses (e.g. sleep and fatigue are influenced by most other symptoms while feelings of worthlessness/guilt is mostly influenced by depressed mood). © 2024, CC BY-SA.

关键词： Measurement theory

来源：评论

学校读者我要写书评

暂无评论

GroundTruth: Augmenting expert image geolocation with crowdsourcing and shared representations

引用

Proceedings of the ACM on human-computer interaction 2019年第CSCW期3卷 1-30页

作者： Venkatagiri, Sukrit Thebault-Spieker, Jacob Kohler, Rachel Purviance, John Mansur, Rifat Sabbir Luther, Kurt Department of Computer Science and Center for Human-Computer Interaction Virginia Tech ArlingtonVA United States BNSF Railway Company Fort WorthTX United States Bloomberg L.P New YorkNY United States

Expert investigators bring advanced skills and deep experience to analyze visual evidence, but they face limits on their time and attention. In contrast, crowds of novices can be highly scalable and parallelizable, but lack expertise. In this paper, we introduce the concept of shared representations for crowd–augmented expert work, focusing on the complex sensemaking task of image geolocation performed by professional journalists and human rights investigators. We built GroundTruth, an online system that uses three shared representations—a diagram, grid, and heatmap—to allow experts to work with crowds in real time to geolocate images. Our mixed-methods evaluation with 11 experts and 567 crowd workers found that GroundTruth helped experts geolocate images, and revealed challenges and success strategies for expert–crowd interaction. We also discuss designing shared representations for visual search, sensemaking, and beyond. © 2019 Copyright held by the owner/author(s). Publication rights licensed to ACM.

关键词： crowd crowd-augmented expert work crowdsourcing expert geolocation investigation journalism misinformation real-time crowdsourcing sensemaking shared representations verification visual search

来源：评论

学校读者我要写书评

暂无评论

Harnessing the power of AI in qualitative research: Exploring, using and redesigning ChatGPT

Computers in Human Behavior: Artificial Humans

引用

computers in human Behavior: Artificial humans 2025年 4卷

作者： He Zhang Chuhao Wu Jingyi Xie Yao Lyu Jie Cai John M. Carroll College of Information Sciences and Technology The Pennsylvania State University Westgate Building University Park PA 16803 USA The School of Information University of Michigan MI 48109 USA The Pervasive Human Computer Interaction Laboratory Department of Computer Science and Technology Tsinghua University Future Internet Technology Research Center (FIT) Haidian District Beijing 100084 China

AI tools, particularly large-scale language model (LLM) based applications such as ChatGPT, have the potential to mitigate qualitative research workload. In this study, we conducted semi-structured interviews with 17 participants and held a co-design session with 13 qualitative researchers to develop a framework for designing prompts specifically crafted to support junior researchers and stakeholders interested in leveraging AI for qualitative research. Our findings indicate that improving transparency, providing guidance on prompts, and strengthening users' understanding of LLMs' capabilities significantly enhance their ability to interact with ChatGPT. By comparing researchers' attitudes toward LLM-supported qualitative analysis before and after the co-design process, we reveal that the shift from an initially negative to a positive perception is driven by increased familiarity with the LLM's capabilities and the implementation of prompt engineering techniques that enhance response transparency and, in turn, foster greater trust. This research not only highlights the importance of well-designed prompts in LLM applications but also offers reflections for qualitative researchers on the perception of AI's role. Finally, we emphasize the potential ethical risks and the impact of constructing AI ethical expectations by researchers, particularly those who are novices, on future research and AI development.

关键词： ChatGPT Qualitative analysis Prompt design Large language models AI-Assisted research Ethical considerations

来源：评论

学校读者我要写书评

暂无评论

Supporting child–group interactions with hands-off museum exhibit

引用

International Journal of Child-computer interaction 2021年 27卷

作者： Kotut, Lindah Hoang, Ann Panda, Havisha Shenk, Jennifer Newbill, Phyllis Kellogg, Derek Scott McCrickard, D. Department of Computer Science Virginia Tech Blacksburg VA United States Center for Human Computer Interaction Virginia Tech Blacksburg VA United States Institute of Creativity Arts and Technology (ICAT) Virginia Tech Blacksburg VA United States Science Museum of Western Virginia Roanoke VA United States

Technology can be used to augment visitors’ experience with a museum exhibit and provide museum visitors with means of interacting with otherwise hands-off exhibits. However, introducing technology to support interactivity has the likelihood of usurping users’ attention from the exhibit or diminishing interactions with other visitors. Our approach to this problem involves supporting hands-on interactions for groups visiting a pollinator garden—a science museum exhibit containing fragile species where touching is discouraged. Through interviews with museum experts and docents, we elicited design goals that we then enfolded into an Android application that leverages visual recognition to support interactions with the exhibit. We tested our application in-situ with 65 children in three groups and subsequently propose and describe design approaches that uses the ethos of scaling to support different number of users and leveling to varied cognitive levels. We conclude by recommending reusable designs guidelines to support interactions within other evolving and hands-off contexts. © 2020 Elsevier B.V.

关键词： Child–group interaction Child–mobile interactions Hands-off exhibits Museum

来源：评论

学校读者我要写书评

暂无评论

The Golden Age of Silver Workers?: The Role of Age in the Perception of Increasing Digital Work Environments 5th

The Golden Age of Silver Workers?: The Role of Age in the Pe...

引用

5th International Conference on human Aspects of IT for the Aged Population, ITAP 2019, held as part of the 21st International Conference on human-computer interaction, HCI International 2019

作者： Kluge, Johanna Hildebrandt, Julian Ziefle, Martina Chair of Communication Science Human Computer Interaction Center RWTH Aachen Campus-Boulevard 57 Aachen52074 Germany

ISBN: (纸本)9783030220143

Digitization is progressing intensively, in particular in the world of work. Thereby, intelligent systems, mobile devices, cloud computing, and social media change the development of work and employment by (in parts) replacing employees or changing ways of production. In line with demographic change and in order to face economic, societal, and demographic challenges of a future labor market, it is necessary to consider the integration of aging employees. Therefore, this paper investigates the perception of motivational factors and stress factors triggered by technology in the working context. In addition, factors influencing the individual perception of strains are analyzed. For this purpose, an online survey was conducted (N = 507) asking for agreement to motivational and stressing factors in the context of increasing digital working environments. The results show that the overall motivational factors received a similar evaluation pattern for younger and older participants. However, the younger employees showed stronger agreements to all motivational aspects. Additionally, the results show that the perception of techno-stress factors was significant lower in the older aged group compared to the younger aged group. The study’s findings highlight the importance of user diversity for a successful and healthy transformation to a digital work environment putting employees needs and requirements into the center. © 2019, Springer Nature Switzerland AG.

关键词： Personnel

来源：评论

学校读者我要写书评

暂无评论

Development,validation,and transportability of several machine-learned,non-exercise-based VO_(2max)prediction models for older adults

引用

Journal of Sport and Health science 2024年第5期13卷 611-620页

作者： Benjamin T.Schumacher Michael J.LaMonte Andrea Z.LaCroix Eleanor M.Simonsick Steven P.Hooker Humberto Parada Jr. John Bellettiere Arun Kumar Herbert Wertheim School of Public Health and Human Longevity Science University of California San DiegoLa JollaCA 92093USA Department of Epidemiology and Environmental Health School of Public Health and Health ProfessionsUniversity at BuffaloState University of New YorkBuffaloNY 14214USA Translational Gerontology Branch Intramural Research ProgramNational Institute on AgingNational Institutes of HealthBaltimoreMD 21225USA College of Health and Human Services San Diego State UniversitySan DiegoCA 92182USA Division of Epidemiology and Biostatistics School of Public HealthSan Diego State UniversitySan DiegoCA 92182USA University of California San Diego Moores Cancer Center La JollaCA 92093USA Computer Science and Engineering and Halicioglu Data Science Institute University of California San DiegoLa JollaCA 92093USA

Background:There exist few maximal oxygen uptake(VO_(2max))non-exercise-based prediction equations,fewer using machine learning(ML),and none specifically for older *** direct measurement of VO_(2max)is infeasible in large epidemiologic cohort studies,we sought to develop,validate,compare,and assess the transportability of several ML VO_(2max)prediction ***:The Baltimore Longitudinal Study of Aging(BLSA)participants with valid VO2_(max)tests were included(n=1080).Least absolute shrinkage and selection operator,linear-and tree-boosted extreme gradient boosting,random forest,and support vector machine(SVM)algorithms were trained to predict VO_(2max)*** developed these algorithms for:(a)the overall BLSA,(b)by sex,(c)using all BLSA variables,and(d)variables common in aging ***,we quantified the associations between measured and predicted VO_(2max)and ***:The age was 69.0±10.4 years(mean±SD)and the measured VO_(2max)was 21.6±5.9 mL/kg/*** absolute shrinkage and selection operator,linear-and tree-boosted extreme gradient boosting,random forest,and support vector machine yielded root mean squared errors of 3.4 mL/kg/min,3.6 mL/kg/min,3.4 mL/kg/min,3.6 mL/kg/min,and 3.5 mL/kg/min,*** quartiles of measured VO_(2max)showed an inverse gradient in mortality *** VO_(2max)variables yielded similar effect estimates but were not robust to ***:Measured VO_(2max)is a strong predictor of *** ML can improve the accuracy of prediction as compared to simpler approaches but estimates of association with mortality remain sensitive to *** studies should seek to reproduce these results so that VO_(2max),an important vital sign,can be more broadly studied as a modifiable target for promoting functional resiliency and healthy aging.

关键词： Cardiorespiratory fitness Prediction algorithms Epidemiology Mortality

来源：评论

学校读者我要写书评

暂无评论

Skeleton-Based Intake Gesture Detection With Spatial-Temporal Graph Convolutional Networks

arXiv

引用

arXiv 2025年

作者： Wang, Chunzhuo Xue, Zhewen Kumar, T. Sunil Camps, Guido Hallez, Hans Vanrumste, Bart e-Media Research Lab the ESAT-STADIUS Division KU Leuven Leuven3000 Belgium University of Gävle Gävle801 76 Sweden Division of Human Nutrition and Health Department of Agrotechnology and Food Sciences Wageningen University and Research OnePlanet Research Center 6700EA Wageningen Wageningen6708WE Netherlands M-Group DistriNet Department of Computer Science KU Leuven Sint-Michiels8200 Belgium

Overweight and obesity have emerged as widespread societal challenges, frequently linked to unhealthy eating patterns. A promising approach to enhance dietary monitoring in everyday life involves automated detection of food intake gestures. This study introduces a skeleton based approach using a model that combines a dilated spatial-temporal graph convolutional network (ST-GCN) with a bidirectional long-short-term memory (BiLSTM) framework, as called ST-GCN-BiLSTM, to detect intake gestures. The skeleton-based method provides key benefits, including environmental robustness, reduced data dependency, and enhanced privacy preservation. Two datasets were employed for model validation. The OREBA dataset, which consists of laboratory-recorded videos, achieved segmental F1-scores of 86.18% and 74.84% for identifying eating and drinking gestures. Additionally, a self-collected dataset using smartphone recordings in more adaptable experimental conditions was evaluated with the model trained on OREBA, yielding F1-scores of 85.40% and 67.80% for detecting eating and drinking gestures. The results not only confirm the feasibility of utilizing skeleton data for intake gesture detection but also highlight the robustness of the proposed approach in cross-dataset validation. Copyright © 2025, The Authors. All rights reserved.

关键词： Musculoskeletal system

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：