典型文献
Saliency guided self-attention network for pedestrian attribute recognition in surveillance scenarios
文献摘要：
Pedestrian attribute recognition is often considered as a multi-label image classification task.In order to make full use of attribute-related location information,a saliency guided self-attention network(SGSA-Net)was proposed to weakly supervise attribute localization,without annotations of attribute-related regions.Saliency priors were integrated into the spatial attention module(SAM).Meanwhile,channel-wise attention and spatial attention were introduced into the network.Moreover,a weighted binary cross-entropy loss(WCEL)function was employed to handle the imbalance of training data.Extensive experiments on richly annotated pedestrian(RAP)and pedestrian attribute(PETA)datasets demonstrated that SGSA-Net outperformed other state-of-the-art methods.
文献关键词：
中图分类号：
作者姓名：
Li Na;Wu Yangyang;Liu Ying;Li Daxiang;Gao Jiale
作者机构：
School of Communication and Information Engineering,Xi'an University of Posts and Telecommunications,Xi'an 710121,China;Key Laboratory of Electronic Information Application Technology for Scene Investigation,Xi'an University of Posts and Telecommunications,Xi'an 710121,China
文献出处：
引用格式：
[1]Li Na;Wu Yangyang;Liu Ying;Li Daxiang;Gao Jiale-.Saliency guided self-attention network for pedestrian attribute recognition in surveillance scenarios)[J].中国邮电高校学报（英文版）,2022(05):21-29
A类：
SGSA,WCEL,richly
B类：
Saliency,guided,self,attention,network,pedestrian,attribute,recognition,surveillance,scenarios,Pedestrian,often,considered,multi,label,image,classification,task,In,order,make,full,use,related,location,information,saliency,Net,was,proposed,weakly,supervise,localization,without,annotations,regions,priors,were,integrated,into,spatial,module,SAM,Meanwhile,channel,wise,introduced,Moreover,weighted,binary,cross,entropy,loss,function,employed,handle,imbalance,training,Extensive,experiments,annotated,RAP,PETA,datasets,demonstrated,that,outperformed,other,state,art,methods
AB值：
0.6423
相似文献
机标中图分类号，由域田数据科技根据网络公开资料自动分析生成，仅供学习研究参考。
