Progressive Context-Aware Graph Feature Learning for Target Re-Identification

被引:5
作者
Cao, Min [1 ]
Ding, Cong [1 ]
Chen, Chen [2 ]
Dou, Hao [2 ]
Hu, Xiyuan [3 ]
Yan, Junchi [4 ,5 ]
机构
[1] Soochow Univ, Sch Comp Sci & Technol, Suzhou 215006, Peoples R China
[2] Chinese Acad Sci, Inst Automat, Beijing 100190, Peoples R China
[3] Nanjing Univ Sci & Technol, Sch Comp Sci & Engn, Nanjing 210093, Jiangsu, Peoples R China
[4] Shanghai Jiao Tong Univ, AI Inst, Dept Comp Sci & Engn, Shanghai 200240, Peoples R China
[5] Shanghai Jiao Tong Univ, AI Inst, MoE Key Lab Artificial Intelligence, Shanghai 200240, Peoples R China
基金
美国国家科学基金会;
关键词
Target re-identification; graph convolutional network; feature learning; contextual information; graph feature learning; PERSON REIDENTIFICATION; NEURAL-NETWORK;
D O I
10.1109/TMM.2022.3140647
中图分类号
TP [自动化技术、计算机技术];
学科分类号
0812 ;
摘要
This paper aims at robust and discriminative feature learning for target re-identification (Re-ID). In addition to paying attention to the individual appearance information as in most Re-ID methods, we further utilize the abundant contextual information as additional clues to guide the feature learning. Graph as a format of structured data is used to represent the target sample with its context. It describes the first-order appearance information of the samples and the second-order topological relationship information among samples, based on which we compute the feature representation by learning a graph feature embedding. We provide a detailed analysis of graph convolutional network mechanism applied in target Re-ID and propose a novel progressive context-aware graph feature learning method, in which the message passing is dominated by a pre-defined adjacency relationship followed by a learned relationship in a self-adaptive way. The proposed method fully exploits and utilizes contextual information at a low cost for Re-ID. Extensive experiments on five Re-ID benchmarks demonstrate the state-of-the-art performance of the proposed method.
引用
收藏
页码:1230 / 1242
页数:13
相关论文
共 79 条
[1]  
Bai S., 2017, P IEEE C COMP VIS PA, P2530
[2]   Re-ranking via Metric Fusion for Object Retrieval and Person Re-identification [J].
Bai, Song ;
Tang, Peng ;
Torr, Philip H. S. ;
Latecki, Longin Jan .
2019 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR 2019), 2019, :740-749
[3]   SimGNN: A Neural Network Approach to Fast Graph Similarity Computation [J].
Bai, Yunsheng ;
Ding, Hao ;
Bian, Song ;
Chen, Ting ;
Sun, Yizhou ;
Wang, Wei .
PROCEEDINGS OF THE TWELFTH ACM INTERNATIONAL CONFERENCE ON WEB SEARCH AND DATA MINING (WSDM'19), 2019, :384-392
[4]   Masked Graph Attention Network for Person Re-identification [J].
Bao, Liqiang ;
Ma, Bingpeng ;
Chang, Hong ;
Chen, Xilin .
2019 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION WORKSHOPS (CVPRW 2019), 2019, :1496-1505
[5]   Line Graph Neural Networks for Link Prediction [J].
Cai, Lei ;
Li, Jundong ;
Wang, Jie ;
Ji, Shuiwang .
IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE, 2022, 44 (09) :5103-5113
[6]   Progressive Bilateral-Context Driven Model for Post-Processing Person Re-Identification [J].
Cao, Min ;
Chen, Chen ;
Dou, Hao ;
Hu, Xiyuan ;
Peng, Silong ;
Kuijper, Arjan .
IEEE TRANSACTIONS ON MULTIMEDIA, 2021, 23 :1239-1251
[7]   Towards fast and kernelized orthogonal discriminant analysis on person re-identification [J].
Cao, Min ;
Chen, Chen ;
Hu, Xiyuan ;
Peng, Silong .
PATTERN RECOGNITION, 2019, 94 :218-229
[8]   From Groups to Co-traveler Sets: Pair Matching based Person Re-identification Framework [J].
Cao, Min ;
Chen, Chen ;
Hu, Xiyuan ;
Peng, Silong .
2017 IEEE INTERNATIONAL CONFERENCE ON COMPUTER VISION WORKSHOPS (ICCVW 2017), 2017, :2573-2582
[9]   Learning 3D Shape Feature for Texture-insensitive Person Re-identification [J].
Chen, Jiaxing ;
Jiang, Xinyang ;
Wang, Fudong ;
Zhang, Jun ;
Zheng, Feng ;
Sun, Xing ;
Zheng, Wei-Shi .
2021 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION, CVPR 2021, 2021, :8142-8151
[10]   ABD-Net: Attentive but Diverse Person Re-Identification [J].
Chen, Tianlong ;
Ding, Shaojin ;
Xie, Jingyi ;
Yuan, Ye ;
Chen, Wuyang ;
Yang, Yang ;
Ren, Zhou ;
Wang, Zhangyang .
2019 IEEE/CVF INTERNATIONAL CONFERENCE ON COMPUTER VISION (ICCV 2019), 2019, :8350-8360