检索结果-内蒙古大学图书馆

OPO-FCM: A computational affection Based OCC-PAD-OCEAN Federation Cognitive Modeling Approach

IEEE TRANSACTIONS ON computational SOCIAL SYSTEMS 2023年第4期10卷 1813-1825页

作者： Liu, Feng Wang, Han-Yang Shen, Si-Yuan Jia, Xun Hu, Jing-Yi Zhang, Jia-Hao Wang, Xi-Yi Lei, Ying Zhou, Ai-Min Qi, Jia-Yin Li, Zhi-Bin East China Normal Univ Inst AI Educ Shanghai 200062 Peoples R China East China Normal Univ Sch Comp Sci & Technol Shanghai 200062 Peoples R China East China Normal Univ Shanghai Key Lab Mental Hlth & Psychol Crisis Int Shanghai 200062 Peoples R China East China Normal Univ Sch Psychol & Cognit Sci Shanghai 200062 Peoples R China East China Normal Univ Sch Business Adm Shanghai 200062 Peoples R China Shanghai Univ Int Business & Econ Inst Artificial Intelligence & Change Management Shanghai 200336 Peoples R China

In recent years, it is a difficult issue to integrate the deep cross-fertilization and interpretable cognitive modeling methods from the basic theory of emotional psychology with deep learning and other algorithms. To address this problem, a cognitive model that integrates the VGG-facial action coding system (FACS)-OCC model based on fer2013 expression features and the OCC-pleasure-arousal-dominance (PAD)-openness, conscientiousness, extraversion, agreeableness, and neuroticism (OCEAN) fusion of the basic theory of emotional psychology, namely, a computational affection-based OCC-PAD-OCEAN federation cognitive modeling (OPO-FCM), is constructed. By constructing this model and performing formal proof algorithms, it is shown that the OPO-FCM can acquire expression features in video streams, complete the acquisition of expression features in videos by training a deep neural network, map expressions to the PAD emotion space through the established expression-basic emotions-emotion space mapping relationship, and finally complete the mapping of the average emotion over a period time. The information of personality space is obtained through it. Finally, the experimental simulation of the model is conducted, and the results show that the average accuracy of the valid tested personalities is 79.56%. This article takes the knowledge-driven approach of emotional psychology as a starting point and combines deep learning techniques to construct interpretable cognitive models, thus providing new ideas for future cross-innovation between computer technology and psychology theory.

关键词： Psychology computational modeling Emotion recognition Brain modeling Deep learning Feature extraction Face recognition Cognitive modeling computational affection emotional psychology five-factor model (FFM) OCC-pleasure-arousal-dominance (PAD)-openness conscientiousness extraversion agreeableness and neuroticism (OCEAN) VGG-facial action coding system (FACS)-OCC

来源：评论

学校读者我要写书评

暂无评论

LMR-CBT: learning modality-fused representations with CB-Transformer for multimodal emotion recognition from unaligned multimodal sequences

引用

Frontiers of Computer Science 2024年第4期18卷 39-47页

作者： Ziwang FU Feng LIU Qing XU Xiangling FU Jiayin QI School of Computer Science(National Pilot Software Engineering School) Beijing University of Posts and TelecommunicationsBeijing 100876China Key Laboratory of Trustworthy Distributed Computing and Service(BUPT) Beijing 100876China Shanghai International School of Chief Technology Officer East China Normal UniversityShanghai 200062China School of Computer Science and Technology East China Normal UniversityShanghai 200062China School of Cyberspace Security Guangzhou UniversityGuangdong 510006China

Learning modality-fused representations and processing unaligned multimodal sequences are meaningful and challenging in multimodal emotion *** approaches use directional pairwise attention or a message hub to fuse language,visual,and audio ***,these fusion methods are often quadratic in complexity with respect to the modal sequence length,bring redundant information and are not *** this paper,we propose an efficient neural network to learn modality-fused representations with CB-Transformer(LMR-CBT)for multimodal emotion recognition from unaligned multi-modal ***,we first perform feature extraction for the three modalities respectively to obtain the local structure of the ***,we design an innovative asymmetric transformer with cross-modal blocks(CB-Transformer)that enables complementary learning of different modalities,mainly divided into local temporal learning,cross-modal feature fusion and global self-attention *** addition,we splice the fused features with the original features to classify the emotions of the ***,we conduct word-aligned and unaligned experiments on three challenging datasets,IEMOCAP,CMU-MOSI,and *** experimental results show the superiority and efficiency of our proposed method in both *** with the mainstream methods,our approach reaches the state-of-the-art with a minimum number of parameters.

关键词： modality-fused representations cross-model blocks multimodal emotion recognition unaligned multimodal sequences computational affection

来源：评论

学校读者我要写书评

暂无评论

Artificial intelligence empowering research on loneliness, depression and anxiety-Using Covid-19 as an opportunity

引用

Journal of Safety Science and Resilience 2023年第4期4卷 396-409页

作者： Qijian Zheng Feng Liu Shuya Xu Jingyi Hu Haixing Lu Tingting Liu School of Computer Science and Technology East China Normal University3663 Zhongshan North RoadShanghai200062China New York University Shanghai No.567Yangsi West RoadPudong DistrictShanghai200126China School of Psychology and Cognitive Science East China Normal University3663 Zhongshan North RoadShanghai200062China Shanghai Key Laboratory of Mental Health and Psychological Crisis Intervention School of Psychology and Cognitive ScienceEast China Normal University3663 Zhongshan North RoadShanghai200062China Faculty of Economics and Management East China Normal University3663 Zhongshan North RoadShanghai200062China

The COVID-19 pandemic has had a profound impact on public mental health,leading to a surge in loneliness,depression,and *** these public psychological issues increasingly become a factor affecting social *** researchers explore ways to address these issues,artificial intelligence(AI)has emerged as a powerful tool for understanding and supporting mental *** this paper,we provide a thorough literature review on the emotions(EMO)of loneliness,depression,and anxiety(EMO-LDA)before and during the COVID-19 ***,we evaluate the application of AI in EMO-LDA research from 2018 to 2023(AI-LDA)using Latent Dirichlet Allocation(LDA)topic *** analysis reveals a significant increase in the proportion of literature on EMO-LDA and AI-LDA before and during the COVID-19 *** also observe changes in research hotspots and trends in both ***,our results suggest that the collaborative research of EMO-LDA and AI-LDA is a promising direction for future *** conclusion,our review highlights the urgent need for effective interventions to address the mental health challenges posed by the COVID-19 *** findings suggest that the integration of AI in EMO-LDA research has the potential to provide new insights and solutions to support individuals facing loneliness,depression,and *** we hope that our study will inspire further research in this vital and revelant domin.

关键词： COVID-19 Loneliness Depression Anxiety EMO-LDA AI-LDA computational affection

来源：评论

学校读者我要写书评

暂无评论

EvoGAN: An evolutionary computation assisted GAN

引用

NEUROCOMPUTING 2022年 469卷 81-90页

作者： Liu, Feng Wang, Hanyang Zhang, Jiahao Fu, Ziwang Zhou, Aimin Qi, Jiayin Li, Zhibin East China Normal Univ Sch Comp Sci & Technol Shanghai Peoples R China Univ Int Business & Econ Inst Artificial Intelligence & Change Management Shanghai Peoples R China Beijing Univ Posts & Telecommun Sch Comp Sci Beijing Peoples R China East China Normal Univ Inst AI Educ Shanghai Peoples R China East China Normal Univ Sch Psychol & Cognit Sci Shanghai Key Lab Mental Hlth & Psychol Crisis Int Shanghai Peoples R China

The image synthesis technique is relatively well established which can generate facial images that are indistinguishable even by human beings. However, all of these approaches uses gradients to condition the output, resulting in the outputting the same image with the same input. Also, they can only generate images with basic expression or mimic an expression instead of generating compound expression. In real life, however, human expressions are of great diversity and complexity. In this paper, we propose an evo-lutionary algorithm (EA) assisted GAN, named EvoGAN, to generate various compound expressions with any accurate target compound expression. EvoGAN uses an EA to search target results in the data distri-bution learned by GAN. Specifically, we use the Facial Action Coding System (FACS) as the encoding of an EA and use a pre-trained GAN to generate human facial images, and then use a pre-trained classifier to recognize the expression composition of the synthesized images as the fitness function to guide the search of the EA. Combined random searching algorithm, various images with the target expression can be easily sythesized. Quantitative and Qualitative results are presented on several compound expres-sions, and the experimental results demonstrate the feasibility and the potential of EvoGAN. The source code is available at https://***/ECNU-Cross-Innovation-Lab/EvoGAN. (c) 2021 Elsevier B.V. All rights reserved.

关键词： Evolutionary algorithms GAN Facial expression synthesis computational affection

来源：评论

学校读者我要写书评

暂无评论

International public opinion analysis of four olympic games:From 2008 to 2022

引用

Journal of Safety Science and Resilience 2022年第3期3卷 252-262页

作者： Kun Jia Yizhen Zhu Yuxin Zhang Feng Liu Jiayin Qi Institute of Artificial Intelligence and Change Management Shanghai University of International Business and EconomicsShanghai 201620China School of Statistics and Information Shanghai University of International Business and EconomicsShanghai 201620China School of Computer Science and Technology East China Normal UniversityShanghai 200062China Shanghai Key Laboratory of Mental Health and Psychological Crisis Intervention other institutesSchool of Psychology and Cognitive ScienceEast China Normal UniversityShanghai 200062China

Since the rapid spread of the COVID-19 worldwide,the pandemic has led to a huge impact on global sporting *** a major international event,the 2022 Beijing Winter Olympics has commonalities with the 2008 Beijing Olympics,the 2014 Sochi Winter Olympics,and the 2020 Tokyo Olympics in terms of international public opinion context and epidemiological *** this study,over 1 million pieces of UGC(User Generated Contents)in Chinese and English languages were obtained from social media platforms such as Twitter,YouTube,as well as traditional mass media in various countries to compare the differences between the two languages in international public *** sentiment analysis,this study explores the evolution of international public opinion topics and sentiment differences among the above four Olympic *** analysis results show that:1)regardless of traditional mass media or online social media,there is a more obvious tendency of general politicization in the topics of the 2008 Beijing Olympics and 2022 Beijing Winter Olympics,and extreme emotional remarks of the 2022 Beijing Winter Olympics are more frequent;2)in the topic of political opinion involving China,international Chinese public opinion presents more negative sentiment than those in English;3)Among the topics involving COVID-19,the negative level of public opinion in Chinese and English is opposite for the 2020 Tokyo Olympics and the 2022 Beijing Winter Olympics;4)International public opinion on the topic of sports events is significantly more positive in Chinese than in English;5)YouTube’s Chinese opinion environment is better than English.

关键词： Public opinion Sentiment analysis Olympic games COVID-19 pandemic computational affection

来源：评论

学校读者我要写书评

暂无评论

AeS-GCN: Attention-enhanced semantic-guided graph convolutional networks for skeleton-based action recognition

引用

COMPUTER ANIMATION AND VIRTUAL WORLDS 2022年第3-4期33卷 e2070-e2070页

作者： Xu, Qing LiU, Feng Fu, Ziwang Zhou, Aimin Qi, Jiayin Beijing Univ Posts & Telecommun Natl Pilot Software Engn Sch Sch Comp Sci Beijing Peoples R China East China Normal Univ Inst AI Educ 3663 North Zhongshan Rd Shanghai Peoples R China East China Normal Univ Sch Comp Sci & Technol Shanghai Peoples R China East China Normal Univ Sch Psychol & Cognit Sci Shanghai Key Lab Mental Hlth & Psychol Crisis Int Shanghai Peoples R China Shanghai Univ Int Business & Econ Inst Artificial Intelligence & Change Management Shanghai Peoples R China

Skeleton-based action recognition has been extensively studied in recent years and applied in virtual reality, detection systems and other cases with strong requirements for low cost as well as high accuracy, but most of the existing methods mainly focus on complex architecture of deep neural networks without considering computation efficiency. To balance accuracy and computation cost well, this paper proposes a simple and efficient attention-enhanced semantic-guided graph convolutional network (AeS-GCN) for skeleton-based action recognition. Firstly, we fuse semantics of joint type and frame index and dynamics together as representation of skeleton. Then, we use spatial attention block (SAB) to explore important features in spatial structure, in which adaptive GCN layer is adopted to adaptively model skeleton topology structure. Next, we use temporal attention block (TAB) to extract latent temporal information. The model proposed is a lightweight network and achieves the state-of-the-art performance on mainstream datasets with less parameters and less computational complexity.

关键词： adaptive graph attention-enhanced computation efficiency computational affection semantics skeleton-based action recognition

来源：评论

学校读者我要写书评

暂无评论

Artificial Intelligence in Emotion Quantification:A Prospective Overview

引用

CAAI Artificial Intelligence Research 2024年第1期3卷 94-104页

作者： Feng Liu School of Computer Science and Technology East China Normal UniversityShanghai 200062China

The field of Artificial Intelligence(AI)is witnessing a rapid evolution in the field of emotion *** possibilities for understanding and parsing human emotions are emerging from advances in this ***-modal data sources,including facial expressions,speech,text,gestures,and physiological signals,are combined with machine learning and deep learning methods in modern emotion recognition *** systems achieve accurate recognition of emotional states in a wide range of complex *** paper provides a comprehensive overview of research advances in multi-modal emotion recognition *** serves as a foundation for an in-depth discussion combining the field of AI with the quantification of emotion,a focus of attention in the field of *** also explores the privacy and ethical issues faced during the processing and analysis of emotion data,and the implications of these challenges for future research *** conclusion,the objective of this paper is to adopt a forward-looking perspective on the development trajectory of AI in the field of emotion quantification,and also point out the potential value of emotion quantification research in a number of areas,including emotion quantification platforms and tools,computational psychology,and computational psychiatry.

关键词： affect quantification multi-modal emotion recognition computational affection computational psychiatry

来源：评论

学校读者我要写书评

暂无评论

An attention-based approach for assessing the effectiveness of emotion-evoking in immersive environment

引用

HELIYON 2024年第3期10卷 e25017页

作者： Liu, Feng Zhou, Yihao Hu, Jingyi East China Normal Univ Sch Comp Sci & Technol 3663 Zhongshan North Rd Shanghai 200062 Peoples R China New York Univ Shanghai 567 Yangsi West Rd Shanghai 200122 Peoples R China East China Normal Univ Fac Econ & Management 3663 Zhongshan North Rd Shanghai 200062 Peoples R China

Visual stimuli within an immersive virtual environment impact human perception and behavior in notably different ways compared to the real world. Previous studies have presented evidence indicating that individuals in various emotional states exhibit an unconscious attentional bias toward either positive or negative stimuli. However, whether these findings can be replicated within an immersive virtual environment remains uncertain. In this study, we devised an attention-based experiment to explore whether the correlation between participants ' emotional states and the valence of visual stimuli influences their attentional bias. Participants (n=28) viewed 360-degree videos with varying valence levels (positive and negative) to evoke emotions. Subsequently, we utilized standard emotional human faces as stimuli to assess how the consistency in video valence and emotional faces affects reaction time (RT) in Go tasks and error rates in No-go tasks. We employed the Ex-Gaussian approach to analyze the RT data. The parameters-mu (mu), sigma (sigma), and tau (tau)-were computed to denote response speed and attentional lapses, respectively. Our findings revealed a significant increase in tau (tau) when the valence of the video and emotional faces aligned. This suggests that the Go/No-go paradigm is effective in evaluating the impact of emotion-evoking stimuli within an immersive environment.

关键词： Go/No-go tasks Emotion-evoking Attentional bias Ex-Gaussian Response time 360-degree videos computational affection

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：