Multi-level feature fusion capsule network with self-attention for facial expression recognition

人工智能 计算机科学 面部表情 模式识别(心理学) 特征提取 特征(语言学) 计算机视觉 面子(社会学概念) 面部识别系统 表达式(计算机科学) 哲学 语言学 社会科学 社会学 程序设计语言
作者
Zhiji Huang,Songsen Yu,Jun Liang
出处
期刊:Journal of Electronic Imaging [SPIE]
卷期号:32 (02) 被引量:1
标识
DOI:10.1117/1.jei.32.2.023038
摘要

Different from generic image classification, fine-grained classification, such as facial expression classification, in which multiple expressions share inherently similar underlying facial appearances, may show a small difference between facial expression classes. Unlike lab-controlled data, facial expressions from natural scenes have rich forms of the same expression due to the diversity of subjects and the complexity of real-world conditions, and as a result, facial expressions may have large differences among samples within the same class. Moreover, there is little difference between facial expressions, and facial expressions are displayed simultaneously through various facial regions, which require us to encode the feature of multiple key regions, forming high-order interactive information. To address the aforementioned problems, we design an enhanced capsule network based on multi-level feature fusion attention mechanism, which is comprised of four critical components: multi-level feature extraction module (MFEM), multi-level attention module (MAM), multi-level capsule attention fusion module (MCAFM), and reconstruction module (RM). The MFEM collects the low-level, middle-level, and high-level features from the input image, therefore lowering the high-level convolution layer’s susceptibility to blurred image and the problem of pose variation. The MAM directs the network’s attention to the most significant features in different levels of image features and can assist the network in ignoring blurred, occluded, and irrelevant features and incorporating them into our self-attention center loss function to compress the element distribution in the same class. The MCAFM preserves the attributes of each face region (such as location, size, and direction) by transferring the features into capsules in preparation for the eventual creation of the dynamic routing mechanism, which can resolve the problem of image rotation on FER in the wild. Simultaneously, the capsule features of distinct areas are combined to provide higher-order overall feature information, enhancing the model’s capacity to discriminate between different kinds of expressions. The RM reconstructs the image and calculates the difference between the reconstructed image and the original input image. Our model outperforms a large number of current methods on two public datasets, RAF-DB and SFEW.
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
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
SONG发布了新的文献求助10
刚刚
小栾完成签到,获得积分10
刚刚
1秒前
1秒前
嘎嘎嘎完成签到,获得积分10
1秒前
勤奋梨愁发布了新的文献求助10
2秒前
殷勤的晓夏完成签到,获得积分10
3秒前
cyc完成签到,获得积分10
3秒前
4秒前
why发布了新的文献求助10
4秒前
limengkai发布了新的文献求助10
5秒前
cjh完成签到,获得积分10
5秒前
6秒前
xixi完成签到,获得积分20
6秒前
领导范儿的应助被勤奋梨愁采纳,获得10
8秒前
sls完成签到,获得积分10
8秒前
yh完成签到,获得积分10
10秒前
万能图书馆的应助被Jason采纳,获得30
11秒前
陆豪杰完成签到,获得积分10
12秒前
充电宝的应助被星辰采纳,获得20
12秒前
13秒前
14秒前
14秒前
勤奋梨愁完成签到,获得积分10
14秒前
xixi关注了科研通微信公众号
15秒前
无花果的应助被guoguozhijia158采纳,获得10
15秒前
16秒前
863发布了新的文献求助10
16秒前
slsdianzi完成签到,获得积分10
17秒前
脱羰甲酸发布了新的文献求助10
18秒前
18秒前
18秒前
852的应助被小冰块采纳,获得10
18秒前
zhaoliancheng完成签到,获得积分20
21秒前
大模型的应助被执着的钢笔采纳,获得10
21秒前
Z_xy完成签到,获得积分10
21秒前
22秒前
细心鲂发布了新的文献求助10
23秒前
zhaoliancheng发布了新的文献求助10
23秒前
霞霞子完成签到 ,获得积分10
24秒前
高分求助中
(应助此贴封号)【重要!!请各用户(尤其是新用户)详细阅读】【科研通的精品贴汇总】 10000
拉伸高分子熔体中缠结行为的模拟和小角中子散射研究 1700
The World Atlas of Wine 9th edition 1000
Sex, Aging, and Death in a Medieval Medical Compendium: Trinity College Cambridge MS R.14.52, Its Texts, Language, and Scribe 500
高分子基功能界面水蒸发材料与应用研究 500
外场增强的水汽发电研究 500
基于结构调控的功能化水诱导发电材料与器件研究 500
热门求助领域 (近24小时)
化学 材料科学 医学 生物 纳米技术 计算机科学 工程类 有机化学 化学工程 生物化学 物理 复合材料 内科学 催化作用 光电子学 人工智能 细胞生物学 无机化学 物理化学 数学
热门帖子
关注 科研通微信公众号,转发送积分 8188353
求助须知:如何正确求助?哪些是违规求助? 9576169
关于积分的说明 21845860
捐赠科研通 7786410
什么是DOI,文献DOI怎么找? 3435292
关于科研通互助平台的介绍 2559588
邀请新用户注册赠送积分活动 2482235