PrGCN: Probability prediction with graph convolutional network for person re-identification
文献类型：期刊论文
| 作者 | Liu, Hongmin2,3; Xiao, Zhenzhen2; Fan, Bin3 ; Zeng, Hui3; Zhang, Yifan1; Jiang, Guoquan2
|
| 刊名 | NEUROCOMPUTING
 |
| 出版日期 | 2021-01-29 |
| 卷号 | 423页码:57-70 |
| ISSN号 | 0925-2312 |
| 关键词 | Person re-identification Graph convolutional network Link probability prediction Similarity measurement |
| DOI | 10.1016/j.neucom.2020.10.019 |
| 通讯作者 | Fan, Bin(bin.fan@ieee.org) |
| 英文摘要 | 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. |
| WOS关键词 | OBJECT DETECTION ; MULTISCALE |
| 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] |
| WOS研究方向 | Computer Science |
| 语种 | 英语 |
| 出版者 | ELSEVIER |
| WOS记录号 | WOS:000599837600006 |
| 资助机构 | Scientific and Technological Innovation Team Support Program ; National Natural Science Foundation of China ; Beijing Natural Science Foundation ; Young Elite Scientists Sponsorship Program by CAST |
| 源URL | [http://ir.ia.ac.cn/handle/173211/42761]  |
| 专题 | 类脑芯片与系统研究 |
| 通讯作者 | Fan, Bin |
| 作者单位 | 1.Chinese Acad Sci, Inst Automat, Natl Lab Pattern Recognit, Beijing, Peoples R China 2.Henan Polytech Univ, Sch Comp Sci & Technol, Jiaozuo, Henan, Peoples R China 3.Univ Sci & Technol Beijing, Sch Automat & Elect Engn, 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. |
入库方式： OAI收割
来源：自动化研究所
浏览0
下载0
收藏0
其他版本
除非特别说明，本系统中所有内容都受版权保护，并保留所有权利。