全局卷积和双注意力机制在动态表情识别中的应用  

Application of global convolution and dual attention mechanism in dynamic expression recognition

作　　者：梁成旭 董建设[1] 李金良 LIANG Chengxu;DONG Jianshe;LI Jinliang(School of Information Technology and Engineering,Tianjin University of Technology and Education,Tianjin 300222,China)

机构地区：[1]天津职业技术师范大学信息技术工程学院,天津300222

出　　处：《天津职业技术师范大学学报》2024年第3期57-63,共7页Journal of Tianjin University of Technology and Education

基　　金：天津市自然科学基金资助项目(22JCYBJC00470).

摘　　要：静态面部表情识别无法捕捉表情的动态变化,识别过程中丢失了表情的连续性特征,同时现实情境中存在的表情强度差异给识别带来不利影响。针对以上问题,提出一种全局卷积双注意力机制的强感知学习神经网络模型,对动态表情序列进行识别。该模型通过全局卷积双注意力块重新缩放特征映射通道,引入全局卷积双注意力块(squeeze and excitation-global convolution attention,GCSA)增强残差网络的学习能力,提高表情识别的准确率。在训练的过程中,引入强感知交叉熵损失函数(cross entropy-auxiliary-intensity aware loss,CAI)来处理视频序列中存在不同感知强度帧的问题。通过在公开数据集DFEW和FERV39K上进行实验,从客观指标和主观视觉效果上与经典方法进行比较。结果表明,所提方法在多个性能指标上均优于对比方法,证明了方法的有效性。Static facial expression recognition fails to capture the dynamic changes of expressions,resulting in the loss of continuity features during the recognition process.Additionally,discrepancies in expression intensity in real-world contexts adversely affect the recognition accuracy.To address these challenges,this paper proposes a robust perceptual neural network model that leverages global convolution and a dual attention mechanism for recognizing dynamic expression sequences.This model incorporates a global convolutional dual attention block(squeeze and excitation-global convolution attention,GCSA)to rescale the channels of feature maps,thus enhancing the learning capabilities of the residual network and improving the accuracy of expression recognition.To tackle the issue of varying perceptual intensities across frames in video sequences,a strong perceptual cross-entropy loss function(cross-entropy-auxiliary-intensity aware loss,CAI)is introduced during the training process.Experiments conducted on the publicly available datasets DFEW and FERV39K demonstrate that the proposed method outperforms classical approaches in multiple performance metrics,validating the effectiveness of this approach through both objective measures and subjective visual assessments.

关 键 词：表情识别 动态表情序列 注意力机制 表情强度 

分 类 号：TP391.41[自动化与计算机技术—计算机应用技术]