Pose-invariant facial expression recognition(FER)is an active but challenging research topic in computer vision.Especially with the involvement of diverse observation angles,FER makes the training parameter models inc...Pose-invariant facial expression recognition(FER)is an active but challenging research topic in computer vision.Especially with the involvement of diverse observation angles,FER makes the training parameter models inconsistent from one view to another.This study develops a deep global multiple-scale and local patches attention(GMS-LPA)dual-branch network for pose-invariant FER to weaken the influence of pose variation and selfocclusion on recognition accuracy.In this research,the designed GMS-LPA network contains four main parts,i.e.,the feature extraction module,the global multiple-scale(GMS)module,the local patches attention(LPA)module,and the model-level fusion model.The feature extraction module is designed to extract and normalize texture information to the same size.The GMS model can extract deep global features with different receptive fields,releasing the sensitivity of deeper convolution layers to pose-variant and self-occlusion.The LPA module is built to force the network to focus on local salient features,which can lower the effect of pose variation and self-occlusion on recognition results.Subsequently,the extracted features are fused with a model-level strategy to improve recognition accuracy.Extensive experimentswere conducted on four public databases,and the recognition results demonstrated the feasibility and validity of the proposed methods.展开更多
A circular thin plate is proposed for vibration attenuation,which is attached alternately by annular piezoelectric unimorphs with resonant shunt circuits.Two kinds of equal frequency resonant shunt circuits are design...A circular thin plate is proposed for vibration attenuation,which is attached alternately by annular piezoelectric unimorphs with resonant shunt circuits.Two kinds of equal frequency resonant shunt circuits are designed to achieve an integrated locally resonant（LR）band gap（BG） with a much smaller transmission factor：（1） the structure is arrayed periodically while the resonant shunt circuits are aperiodic;（2） the resonant shunt circuits are periodic while the structure is aperiodic.The transmission factor curve is calculated,which is validated by the finite element method.Dependences of the LR BG performance upon the geometric and electric parameters are also analyzed.展开更多
现有的注意力机制仅增强特征图的通道或空间维度,未能充分捕捉细微视觉元素和多尺度特征变化。为解决此问题,提出一种基于局部分块与全局多尺度特征融合的注意力机制(patch and global multiscale attention,PGMA)。将特征图分割成多个...现有的注意力机制仅增强特征图的通道或空间维度,未能充分捕捉细微视觉元素和多尺度特征变化。为解决此问题,提出一种基于局部分块与全局多尺度特征融合的注意力机制(patch and global multiscale attention,PGMA)。将特征图分割成多个小块,分别计算这些小块的注意力得分,增强对局部信息的感知能力。使用一组空洞卷积计算整个特征图的得分,获得全局多尺度信息的权衡。实验中,将PGMA集成到U-Net、DeepLab、SegNet等语义分割网络中,有效提升了它们的分割性能。这表明PGMA在增强CNN性能方面优于当前主流方法。展开更多
基金supported by the National Natural Science Foundation of China (No.31872399)Advantage Discipline Construction Project (PAPD,No.6-2018)of Jiangsu University。
文摘Pose-invariant facial expression recognition(FER)is an active but challenging research topic in computer vision.Especially with the involvement of diverse observation angles,FER makes the training parameter models inconsistent from one view to another.This study develops a deep global multiple-scale and local patches attention(GMS-LPA)dual-branch network for pose-invariant FER to weaken the influence of pose variation and selfocclusion on recognition accuracy.In this research,the designed GMS-LPA network contains four main parts,i.e.,the feature extraction module,the global multiple-scale(GMS)module,the local patches attention(LPA)module,and the model-level fusion model.The feature extraction module is designed to extract and normalize texture information to the same size.The GMS model can extract deep global features with different receptive fields,releasing the sensitivity of deeper convolution layers to pose-variant and self-occlusion.The LPA module is built to force the network to focus on local salient features,which can lower the effect of pose variation and self-occlusion on recognition results.Subsequently,the extracted features are fused with a model-level strategy to improve recognition accuracy.Extensive experimentswere conducted on four public databases,and the recognition results demonstrated the feasibility and validity of the proposed methods.
基金Project supported by the National Natural Science Foundation of China(Nos.11272126,51435006,and 51421062)the Fundamental Research Funds for the Central Universities,HUST:2016JCTD114 and 2015TS121the Research Fund for the Doctoral Program of Higher Education of China(No.20110142120050)
文摘A circular thin plate is proposed for vibration attenuation,which is attached alternately by annular piezoelectric unimorphs with resonant shunt circuits.Two kinds of equal frequency resonant shunt circuits are designed to achieve an integrated locally resonant（LR）band gap（BG） with a much smaller transmission factor：（1） the structure is arrayed periodically while the resonant shunt circuits are aperiodic;（2） the resonant shunt circuits are periodic while the structure is aperiodic.The transmission factor curve is calculated,which is validated by the finite element method.Dependences of the LR BG performance upon the geometric and electric parameters are also analyzed.
文摘现有的注意力机制仅增强特征图的通道或空间维度,未能充分捕捉细微视觉元素和多尺度特征变化。为解决此问题,提出一种基于局部分块与全局多尺度特征融合的注意力机制(patch and global multiscale attention,PGMA)。将特征图分割成多个小块,分别计算这些小块的注意力得分,增强对局部信息的感知能力。使用一组空洞卷积计算整个特征图的得分,获得全局多尺度信息的权衡。实验中,将PGMA集成到U-Net、DeepLab、SegNet等语义分割网络中,有效提升了它们的分割性能。这表明PGMA在增强CNN性能方面优于当前主流方法。
