Affective Video Content Analysis: Decade Review and New Perspectives

Video content is rich in semantics and has the ability to evoke various emotions in viewers. In recent years, with the rapid development of affective computing and the explosive growth of visual data, Affective Video Content Analysis (AVCA) as an essential branch of affective computing has become a...

Full description

Saved in:
Bibliographic Details
Main Authors: Junxiao Xue, Jie Wang, Xiaozhen Liu, Qian Zhang, Xuecheng Wu
Format: Article
Language:English
Published: Tsinghua University Press 2025-02-01
Series:Big Data Mining and Analytics
Subjects:
Online Access:https://www.sciopen.com/article/10.26599/BDMA.2024.9020048
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850169533056155648
author Junxiao Xue
Jie Wang
Xiaozhen Liu
Qian Zhang
Xuecheng Wu
author_facet Junxiao Xue
Jie Wang
Xiaozhen Liu
Qian Zhang
Xuecheng Wu
author_sort Junxiao Xue
collection DOAJ
description Video content is rich in semantics and has the ability to evoke various emotions in viewers. In recent years, with the rapid development of affective computing and the explosive growth of visual data, Affective Video Content Analysis (AVCA) as an essential branch of affective computing has become a widely researched topic. In this study, we comprehensively review the development of AVCA over the past decade, particularly focusing on the most advanced methods adopted to address the three major challenges of video feature extraction, expression subjectivity, and multimodal feature fusion. We first introduce the widely used emotion representation models in AVCA and describe commonly used datasets. We summarize and compare representative methods in the following aspects: (1) unimodal AVCA models, including facial expression recognition and posture emotion recognition; (2) multimodal AVCA models, including feature fusion, decision fusion, and attention-based multimodal models; and (3) model performance evaluation standards. Finally, we discuss future challenges and promising research directions, such as emotion recognition and public opinion analysis, human-computer interaction, and emotional intelligence.
format Article
id doaj-art-a1a9b09492c848d3b62df98f70e0b667
institution OA Journals
issn 2096-0654
language English
publishDate 2025-02-01
publisher Tsinghua University Press
record_format Article
series Big Data Mining and Analytics
spelling doaj-art-a1a9b09492c848d3b62df98f70e0b6672025-08-20T02:20:42ZengTsinghua University PressBig Data Mining and Analytics2096-06542025-02-018111814410.26599/BDMA.2024.9020048Affective Video Content Analysis: Decade Review and New PerspectivesJunxiao Xue0Jie Wang1Xiaozhen Liu2Qian Zhang3Xuecheng Wu4Research Center for Space Computing System, Zhejiang Lab, Hangzhou 311500, ChinaChina Mobile (Hangzhou) Information Technology Co. Ltd., Hangzhou 311100, ChinaSchool of Cyber Science and Engineering, Zhengzhou University, Zhengzhou 450002, ChinaSchool of Computer Science, National University of Defense Technology, Changsha 410073, ChinaSchool of Computer Science and Technology, Xi’an Jiaotong University, Xi’an 710049, ChinaVideo content is rich in semantics and has the ability to evoke various emotions in viewers. In recent years, with the rapid development of affective computing and the explosive growth of visual data, Affective Video Content Analysis (AVCA) as an essential branch of affective computing has become a widely researched topic. In this study, we comprehensively review the development of AVCA over the past decade, particularly focusing on the most advanced methods adopted to address the three major challenges of video feature extraction, expression subjectivity, and multimodal feature fusion. We first introduce the widely used emotion representation models in AVCA and describe commonly used datasets. We summarize and compare representative methods in the following aspects: (1) unimodal AVCA models, including facial expression recognition and posture emotion recognition; (2) multimodal AVCA models, including feature fusion, decision fusion, and attention-based multimodal models; and (3) model performance evaluation standards. Finally, we discuss future challenges and promising research directions, such as emotion recognition and public opinion analysis, human-computer interaction, and emotional intelligence.https://www.sciopen.com/article/10.26599/BDMA.2024.9020048affective computingvideo emotionvideo feature extractionmachine learningemotional intelligence
spellingShingle Junxiao Xue
Jie Wang
Xiaozhen Liu
Qian Zhang
Xuecheng Wu
Affective Video Content Analysis: Decade Review and New Perspectives
Big Data Mining and Analytics
affective computing
video emotion
video feature extraction
machine learning
emotional intelligence
title Affective Video Content Analysis: Decade Review and New Perspectives
title_full Affective Video Content Analysis: Decade Review and New Perspectives
title_fullStr Affective Video Content Analysis: Decade Review and New Perspectives
title_full_unstemmed Affective Video Content Analysis: Decade Review and New Perspectives
title_short Affective Video Content Analysis: Decade Review and New Perspectives
title_sort affective video content analysis decade review and new perspectives
topic affective computing
video emotion
video feature extraction
machine learning
emotional intelligence
url https://www.sciopen.com/article/10.26599/BDMA.2024.9020048
work_keys_str_mv AT junxiaoxue affectivevideocontentanalysisdecadereviewandnewperspectives
AT jiewang affectivevideocontentanalysisdecadereviewandnewperspectives
AT xiaozhenliu affectivevideocontentanalysisdecadereviewandnewperspectives
AT qianzhang affectivevideocontentanalysisdecadereviewandnewperspectives
AT xuechengwu affectivevideocontentanalysisdecadereviewandnewperspectives