典型文献
Residual Network with Enhanced Positional Attention and Global Prior for Clothing Parsing
文献摘要：
Clothing parsing, also known as clothing image segmentation, is the problem of assigning a clothing category label to each pixel in clothing images. To address the lack of positional and global prior in existing clothing parsing algorithms, this paper proposes an enhanced positional attention module (EPAM) to collect positional information in the vertical direction of each pixel, and an efficient global prior module ( GPM ) to aggregate contextual information from different sub-regions. The EPAM and GPM based residual network (EG-ResNet) could effectively exploit the intrinsic features of clothing images while capturing information between different scales and sub-regions. Experimental results show that the proposed EG-ResNet achieves promising performance in clothing parsing of the colorful fashion parsing dataset (CFPD) (51.12％ of mean Intersection over Union(mIoU) and 92.79％ of pixel-wise accuracy(PA)) compared with other state-of-the-art methods.
文献关键词：
中图分类号：
作者姓名：
WANG Shaoyu;HU Yun;ZHU Yian;YE Shaoping;QIN Yanxia;SHI Xiujin
作者机构：
School of Computer Science and Technology,Donghua University,Shanghai 201620,China
文献出处：
引用格式：
[1]WANG Shaoyu;HU Yun;ZHU Yian;YE Shaoping;QIN Yanxia;SHI Xiujin-.Residual Network with Enhanced Positional Attention and Global Prior for Clothing Parsing)[J].东华大学学报（英文版）,2022(05):505-510
A类：
EPAM,CFPD
B类：
Residual,Network,Enhanced,Positional,Attention,Global,Prior,Clothing,Parsing,parsing,also,known,clothing,segmentation,problem,assigning,category,label,each,pixel,images,To,address,lack,positional,global,prior,existing,algorithms,this,paper,proposes,enhanced,attention,module,collect,information,vertical,direction,efficient,GPM,aggregate,contextual,from,different,sub,regions,residual,network,EG,ResNet,could,effectively,exploit,intrinsic,features,while,capturing,between,scales,Experimental,results,show,that,proposed,achieves,promising,performance,colorful,fashion,dataset,mean,Intersection,over,Union,mIoU,wise,accuracy,compared,other,state,art,methods
AB值：
0.601392
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。
