典型文献
Self-supervised human semantic parsing for video-based person re-identification
文献摘要：
Video-based person re-identification is an important research topic in computer vision that entails associating a pedestrian' s identity with non-overlapping cameras. It suffers from severe temporal appearance misalignment and visual ambiguity problems. We propose a novel self-supervised human semantic parsing approach (SS-HSP) for video-based per-son re-identification in this work. It employs self-supervised learning to adaptively segment the human body at pixel-level by estimating motion information of each body part between consecutive frames and explores complementary temporal re-lations for pursuing reinforced appearance and motion representations. Specifically, a semantic segmentation network within SS-HSP is designed, which exploits self-supervised learning by constructing a pretext task of predicting future frames. The network learns precise human semantic parsing together with the motion field of each body part between con-secutive frames, which permits the reconstruction of future frames with the aid of several customized loss functions. Local aligned features of body parts are obtained according to the estimated human parsing. Moreover, an aggregation network is proposed to explore the correlation information across video frames for refining the appearance and motion representa-tions. Extensive experiments on two video datasets have demonstrated the effectiveness of the proposed approach.
文献关键词：
中图分类号：
作者姓名：
Wei Wu;Jiawei Liu
作者机构：
School of Information Science and Technology,University of Science and Technology of China,Hefei 230027,China
文献出处：
引用格式：
[1]Wei Wu;Jiawei Liu-.Self-supervised human semantic parsing for video-based person re-identification)[J].中国科学技术大学学报,2022(09):47-58
A类：
pretext
B类：
Self,supervised,human,semantic,parsing,video,person,identification,Video,important,research,topic,computer,vision,that,entails,associating,pedestrian,identity,overlapping,cameras,It,suffers,from,severe,temporal,appearance,misalignment,visual,ambiguity,problems,We,novel,self,approach,SS,HSP,this,employs,learning,adaptively,body,pixel,level,by,estimating,motion,information,each,between,consecutive,frames,explores,complementary,lations,pursuing,reinforced,representations,Specifically,segmentation,network,within,designed,which,exploits,constructing,task,predicting,future,learns,precise,together,field,permits,reconstruction,aid,several,customized,loss,functions,Local,aligned,features,parts,are,obtained,according,estimated,Moreover,aggregation,proposed,correlation,across,refining,Extensive,experiments,datasets,have,demonstrated,effectiveness
AB值：
0.540434
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。
