清晨好,您是今天最早来到科研通的研友!由于当前在线用户较少,发布求助请尽量完整地填写文献信息,科研通机器人24小时在线,伴您科研之路漫漫前行!

Face2Nodes: Learning facial expression representations with relation-aware dynamic graph convolution networks

计算机科学 模式识别(心理学) 嵌入 人工智能 图形 卷积神经网络 判别式 图嵌入 特征学习 深度学习 面部表情 卷积(计算机科学) 理论计算机科学 人工神经网络
作者
Fan Jiang,Qionghao Huang,Xiaoyong Mei,Quanlong Guan,Yaxin Tu,Weiqi Luo,Changqin Huang
出处
期刊:Information Sciences [Elsevier BV]
卷期号:649: 119640-119640 被引量:5
标识
DOI:10.1016/j.ins.2023.119640
摘要

Deep convolutional neural networks (CNNs) have become the standard model architecture for facial expression recognition (FER). However, CNN-based models struggle to capture the structural correlations between different local regions in a face image. Recent methods based on Vision Transformer (ViT) have been introduced to capture long-range dependencies among local regions. Nonetheless, ViT-based approaches are vulnerable to facial regions unrelated to expressions and may learn redundant correlation representations due to their self-attention mechanism. To address these issues, we propose a novel graph-based model called Face2Nodes, which can flexibly learn the graph representations of facial expressions without requiring additional auxiliary facial information such as landmarks. Our Face2Nodes consists of two key components: a multi-scale feature fusion-based patch embedding and a relation-aware dynamic graph convolution network. The patch embedding method uses a multi-scale feature fusion mechanism to obtain more discriminative graph node features for further graph representation learning. A dynamic graph is constructed using the dilated k-nearest neighbors algorithm, and a relation-aware graph convolution operator is designed to learn the latent informative correlations among different nodes in the graph. Extensive experiment results show that Face2Nodes achieves state-of-the-art performance on several popular in-the-wild FER datasets, with overall accuracies of 91.41%, 91.02%, and 66.69% on the FERPlus, RAF-DB, and AffectNet databases, respectively. Furthermore, we found that CNN-based FER approaches have a more significant performance gap between pre-training and training from scratch than Face2Nodes, demonstrating that our model is more data-efficient than CNN-based approaches.

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
科研通AI6.4的应助被纯情的阁采纳,获得10
2秒前
2秒前
故意的冷安完成签到,获得积分10
4秒前
9秒前
坚定的咖啡完成签到,获得积分10
9秒前
冷艳千柳完成签到,获得积分10
9秒前
12秒前
28秒前
28秒前
科研通AI6.4的应助被纯情的阁采纳,获得10
29秒前
科研通AI6.4的应助被纯情的阁采纳,获得30
29秒前
科研通AI6.2的应助被纯情的阁采纳,获得10
29秒前
池雨完成签到 ,获得积分10
44秒前
苗条的香萱完成签到,获得积分10
52秒前
年轻狗完成签到,获得积分10
57秒前
59秒前
1分钟前
研友_nqrKQZ发布了新的文献求助10
1分钟前
隐形曼青的应助被研友_nqrKQZ采纳,获得10
1分钟前
1分钟前
爱听歌的语堂完成签到,获得积分10
1分钟前
1分钟前
1分钟前
1分钟前
1分钟前
纯情的阁发布了新的文献求助10
1分钟前
搞怪山河完成签到,获得积分10
1分钟前
1分钟前
纯情的阁发布了新的文献求助10
1分钟前
星辰大海的应助被天熙采纳,获得10
1分钟前
纯情的阁发布了新的文献求助30
1分钟前
1分钟前
纯情的阁发布了新的文献求助10
1分钟前
科研通AI6.2的应助被纯情的阁采纳,获得30
1分钟前
1分钟前
1分钟前
xun发布了新的文献求助10
1分钟前
1分钟前
天熙发布了新的文献求助10
1分钟前
1分钟前
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 1500
The World Atlas of Wine 9th edition 1000
奈特基础组织学:配套组织病理学(第4版)(Netter's Essential Histology With Correlated Histopathology) 800
John McDowells Bildungstheorie 800
八旗制度の研究 600
Analyses de reconnaissances de dettes passées devant les échevins d'Ypres (1249-1291) 600
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 8158905
求助须知:如何正确求助?哪些是违规求助? 9554522
关于积分的说明 21719373
捐赠科研通 7748459
什么是DOI,文献DOI怎么找? 3427107
关于科研通互助平台的介绍 2552006
邀请新用户注册赠送积分活动 2471370