典型文献
Learn Robust Pedestrian Representation Within Minimal Modality Discrepancy for Visible-Infrared Person Re-Identification
文献摘要：
Visible-infrared person re-identification has attracted extensive attention from the community due to its po-tential great application prospects in video surveillance.There are huge modality discrepancies between visible and infrared images caused by different imaging mechanisms.Existing studies alleviate modality discrepancies by aligning modality dis-tribution or extracting modality-shared features on the original image.However,they ignore a key solution,i.e.,converting visible images to gray images directly,which is efficient and effective to reduce modality discrepancies.In this paper,we transform the cross-modality person re-identification task from visible-infrared images to gray-infrared images,which is named as the minimal modality discrepancy.In addition,we propose a pyramid feature integration network(PFINet)which mines the discriminative refined features of pedestrian images and fuses high-level and semantically strong features to build a robust pedestrian representation.Specifically,PFINet first performs the feature extraction from concrete to abstract and the top-down semantic transfer to obtain multi-scale feature maps.Second,the multi-scale feature maps are inputted to the discriminative-region response module to emphasize the identity-discriminative regions by the spatial attention mechanism.Finally,the pedestrian representation is obtained by the feature integration.Extensive experiments demonstrate the effec-tiveness of PFINet which achieves the rank-1 accuracy of 81.95％and mAP of 74.49％on the multi-all evaluation mode of the SYSU-MM01 dataset.
文献关键词：
中图分类号：
作者姓名：
Yu-Jie Liu;Wen-Bin Shao;Xiao-Rui Sun
作者机构：
College of Computer Science and Technology,China University of Petroleum(East China),Qingdao 266580,China
文献出处：
引用格式：
[1]Yu-Jie Liu;Wen-Bin Shao;Xiao-Rui Sun-.Learn Robust Pedestrian Representation Within Minimal Modality Discrepancy for Visible-Infrared Person Re-Identification)[J].计算机科学技术学报（英文版）,2022(03):641-651
A类：
PFINet
B类：
Learn,Robust,Pedestrian,Representation,Within,Minimal,Modality,Discrepancy,Visible,Infrared,Person,Identification,infrared,person,identification,attracted,extensive,attention,from,community,due,its,tential,great,application,prospects,video,surveillance,There,huge,modality,discrepancies,between,visible,images,caused,by,different,imaging,mechanisms,Existing,studies,alleviate,aligning,tribution,extracting,shared,features,original,However,they,ignore,key,solution,converting,gray,directly,which,efficient,effective,reduce,this,paper,transform,cross,task,named,minimal,discrepancy,addition,propose,pyramid,integration,network,mines,discriminative,refined,pedestrian,fuses,high,level,semantically,strong,build,robust,representation,Specifically,first,performs,extraction,concrete,abstract,top,down,transfer,multi,scale,maps,Second,inputted,response,module,emphasize,identity,regions,spatial,Finally,obtained,Extensive,experiments,demonstrate,tiveness,achieves,rank,accuracy,mAP,evaluation,mode,SYSU,MM01,dataset
AB值：
0.577325
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。
