PrGCN: Probability prediction with graph convolutional network for person re-identification

doi:10.1016/j.neucom.2020.10.019

	PrGCN: Probability prediction with graph convolutional network for person re-identification
	Liu, Hongmin 1,2; Xiao, Zhenzhen 2; Fan, Bin1 ; Zeng, Hui 1; Zhang, Yifan3 ; Jiang, Guoquan 2
发表期刊	NEUROCOMPUTING
ISSN	0925-2312
	2021-01-29
卷号	423 页码:57-70
通讯作者	Fan, Bin(bin.fan@ieee.org)
摘要	Robust similarity measurement is an important issue for person re-identification (ReID). Most existing ReID models estimate the similarity between query and gallery images by computing their Euclidean distances while ignoring the rich context information contained in the image space. In this paper, we pro pose a graph convolutional network (GCN) based method to improve the similarity measurement in ReID, which regards the ReID task as a prediction problem of the link probability between node pairs. Our method is named as PrGCN (Probability GCN), in which each person is regarded as an instance node. Firstly, an Instance Centered Sub-graphs (ICS) is constructed for each instance node to depict its rich local context information. Secondly, the constructed ICS is input to a GCN to infer and predict the link probability of node pairs, followed by a similarity ranking between the query and gallery images according to the predicted probabilities. Extensive experiments show that the proposed method improves the mAP and Top-1 accuracy of ReID significantly, yielding better or comparable results to the state-of-the-art methods on various benchmarks (Market1501, DukeMTMC-ReID and CUHK03). In addition, we validate that the proposed PrGCN can be easily embedded into other deep learning architectures to replace Euclidean distance metric and achieve significant performance improvements. (c) 2020 Elsevier B.V. All rights reserved.
关键词	Person re-identification Graph convolutional network Link probability prediction Similarity measurement
DOI	10.1016/j.neucom.2020.10.019
关键词[WOS]	OBJECT DETECTION ; MULTISCALE
收录类别	SCI
语种	英语
资助项目	Scientific and Technological Innovation Team Support Program[19IRTSTHN012] ; National Natural Science Foundation of China[61973029] ; National Natural Science Foundation of China[61876180] ; Beijing Natural Science Foundation[4202073] ; Young Elite Scientists Sponsorship Program by CAST[2018QNRC001]
项目资助者	Scientific and Technological Innovation Team Support Program ; National Natural Science Foundation of China ; Beijing Natural Science Foundation ; Young Elite Scientists Sponsorship Program by CAST
WOS研究方向	Computer Science
WOS类目	Computer Science, Artificial Intelligence
WOS记录号	WOS:000599837600006
出版者	ELSEVIER
引用统计	被引频次：35[WOS] [WOS记录] [WOS相关记录]
文献类型	期刊论文
条目标识符	http://ir.ia.ac.cn/handle/173211/42762
专题	复杂系统认知与决策实验室_高效智能计算与学习
通讯作者	Fan, Bin
作者单位	1.Univ Sci & Technol Beijing, Sch Automat & Elect Engn, Beijing, Peoples R China 2.Henan Polytech Univ, Sch Comp Sci & Technol, Jiaozuo, Henan, Peoples R China 3.Chinese Acad Sci, Inst Automat, Natl Lab Pattern Recognit, Beijing, Peoples R China
推荐引用方式 GB/T 7714	Liu, Hongmin,Xiao, Zhenzhen,Fan, Bin,et al. PrGCN: Probability prediction with graph convolutional network for person re-identification[J]. NEUROCOMPUTING,2021,423:57-70.
APA	Liu, Hongmin,Xiao, Zhenzhen,Fan, Bin,Zeng, Hui,Zhang, Yifan,&Jiang, Guoquan.(2021).PrGCN: Probability prediction with graph convolutional network for person re-identification.NEUROCOMPUTING,423,57-70.
MLA	Liu, Hongmin,et al."PrGCN: Probability prediction with graph convolutional network for person re-identification".NEUROCOMPUTING 423(2021):57-70.