SOLVER: Scene-Object Interrelated Visual Emotion Reasoning Network

计算机科学 人工智能 可解释性 对象(语法) 图形 可视化 利用 稳健性(进化) 卷积神经网络 计算机视觉 理论计算机科学 计算机安全 生物化学 基因 化学
作者
Jingyuan Yang,Xinbo Gao,Leida Li,Xiumei Wang,Jinshan Ding
出处
期刊:IEEE transactions on image processing [Institute of Electrical and Electronics Engineers]
卷期号:30: 8686-8701 被引量:2
标识
DOI:10.1109/tip.2021.3118983
摘要

Visual Emotion Analysis (VEA) aims at finding out how people feel emotionally towards different visual stimuli, which has attracted great attention recently with the prevalence of sharing images on social networks. Since human emotion involves a highly complex and abstract cognitive process, it is difficult to infer visual emotions directly from holistic or regional features in affective images. It has been demonstrated in psychology that visual emotions are evoked by the interactions between objects as well as the interactions between objects and scenes within an image. Inspired by this, we propose a novel Scene-Object interreLated Visual Emotion Reasoning network (SOLVER) to predict emotions from images. To mine the emotional relationships between distinct objects, we first build up an Emotion Graph based on semantic concepts and visual features. Then, we conduct reasoning on the Emotion Graph using Graph Convolutional Network (GCN), yielding emotion-enhanced object features. We also design a Scene-Object Fusion Module to integrate scenes and objects, which exploits scene features to guide the fusion process of object features with the proposed scene-based attention mechanism. Extensive experiments and comparisons are conducted on eight public visual emotion datasets, and the results demonstrate that the proposed SOLVER consistently outperforms the state-of-the-art methods by a large margin. Ablation studies verify the effectiveness of our method and visualizations prove its interpretability, which also bring new insight to explore the mysteries in VEA. Notably, we further discuss SOLVER on three other potential datasets with extended experiments, where we validate the robustness of our method and notice some limitations of it.
最长约 10秒,即可获得该文献文件

科研通智能强力驱动
Strongly Powered by AbleSci AI
更新
PDF的下载单位、IP信息已删除 (2025-6-4)

科研通是完全免费的文献互助平台,具备全网最快的应助速度,最高的求助完成率。 对每一个文献求助,科研通都将尽心尽力,给求助人一个满意的交代。
实时播报
缓慢怜翠发布了新的文献求助10
1秒前
1秒前
任性映秋发布了新的文献求助10
1秒前
1秒前
科研通AI5应助爱听歌起眸采纳,获得10
1秒前
2秒前
2秒前
athenalin1988完成签到,获得积分10
2秒前
核桃发布了新的文献求助10
3秒前
3秒前
3秒前
4秒前
上官若男应助周五采纳,获得30
5秒前
科研通AI5应助鲜艳的帅哥采纳,获得10
5秒前
HJJHJH发布了新的文献求助10
6秒前
S-Lab Sonic完成签到,获得积分10
6秒前
7秒前
沙亮完成签到 ,获得积分10
7秒前
妮子完成签到,获得积分10
7秒前
TK发布了新的文献求助10
8秒前
8秒前
hyg发布了新的文献求助10
8秒前
10秒前
英俊的铭应助xiu采纳,获得10
10秒前
烟花应助HJJHJH采纳,获得10
11秒前
耍酷弱发布了新的文献求助10
11秒前
李健的小迷弟应助孙1采纳,获得10
16秒前
16秒前
17秒前
why发布了新的文献求助10
17秒前
20秒前
22秒前
汉堡包应助11tty采纳,获得10
23秒前
23秒前
圣尊鳕幽发布了新的文献求助10
23秒前
Firmian完成签到,获得积分10
24秒前
24秒前
花生糕发布了新的文献求助10
24秒前
25秒前
morena发布了新的文献求助30
26秒前
高分求助中
Pipeline and riser loss of containment 2001 - 2020 (PARLOC 2020) 1000
哈工大泛函分析教案课件、“72小时速成泛函分析:从入门到入土.PDF”等 660
Comparing natural with chemical additive production 500
The Leucovorin Guide for Parents: Understanding Autism’s Folate 500
Phylogenetic study of the order Polydesmida (Myriapoda: Diplopoda) 500
A Manual for the Identification of Plant Seeds and Fruits : Second revised edition 500
The Social Work Ethics Casebook: Cases and Commentary (revised 2nd ed.) 400
热门求助领域 (近24小时)
化学 医学 生物 材料科学 工程类 有机化学 内科学 生物化学 物理 计算机科学 纳米技术 遗传学 基因 复合材料 化学工程 物理化学 病理 催化作用 免疫学 量子力学
热门帖子
关注 科研通微信公众号,转发送积分 5208817
求助须知:如何正确求助?哪些是违规求助? 4386099
关于积分的说明 13660012
捐赠科研通 4245182
什么是DOI,文献DOI怎么找? 2329154
邀请新用户注册赠送积分活动 1326960
关于科研通互助平台的介绍 1279228