Pose matters:Pose guided graph attention network for person re-identification

作     者：Zhijun HE Hongbo ZHAO Jianrong WANG Wenquan FENG Zhijun HE;Hongbo ZHAO;Jianrong WANG;Wenquan FENG

作者机构：School of Electronics and Information EngineeringBeihang UniversityBeijing 100191China Hefei Innovation Research Institute of Beihang UniversityHefei 230012China 

出 版 物：《Chinese Journal of Aeronautics》 (中国航空学报（英文版）)

年 卷 期：2023年第36卷第5期

页      面：447-464页

核心收录：

学科分类：08[工学] 080203[工学-机械设计及理论] 0802[工学-机械工程] 0825[工学-航空宇航科学与技术] 0801[工学-力学（可授工学、理学学位）] 

基　　金：supported by the National Natural Science Foundation of China(No.61901015) 

主　　题：Convolutional neural networks Deep learning Graph neural networks Identification Image retrieval Image processing 

摘      要：Person re-Identification(reID),aiming at retrieving a person across different cameras,has been playing a more and more important role in the construction of smart city and social *** deep-learning-based reID methods,it has been proved that using local feature together with global feature could help to give robust representation for person *** pose information can provide the locations of human skeleton to effectively guide the network to pay more attention to these key areas,and can also help to reduce the noise distractions from background or *** on human pose,a Pose Guided Graph Attention(PGGA)network is proposed in this paper,which is a multi-branch architecture consisting of one branch for global feature and two branches for local key-point features.A graph attention convolution layer is carefully designed to re-assign the contribution weight of each extracted local feature by modeling the similarity *** experimental results demonstrate the effectiveness of our approach on discriminative feature *** model achieves the state-of-the-art performance on several mainstream evaluation datasets.A plenty of ablation studies and different kinds of comparison experiments are conducted to prove the effectiveness of this work,including the tests on occluded datasets and cross-domain ***,we further design supplementary tests in practical scenario to indicate the advantage of our work in real-word applications.