Person re-identification (Re-ID) is a research hotspot in the field of computer vision, it is the re-identification of the same person under different surveillance devices. Features from different parts of the person are independently extracted by most existing Re-ID models, the intrinsic connections between human body parts are not taken into account, the recognition rate is relatively low when pedestrians have multi-pose and viewpoint changes. Graph neural network (GNN) possess strong feature modeling capabilities for graph-structured data, the associated information between various nodes in the graph can be fully mined by GNN, thus, problems such as pedestrian occlusion, viewpoint and posture changes can be effectively solved to a certain extent. The key issues and technical bottlenecks in the current Re-ID field were first systematically sorted out. Core challenges including viewpoint changes and occlusion interference were covered. Then, the theoretical framework of GNN was outlined. On this basis, combined with international cutting-edge progress, the technical paths through which GNN enhance the correlation of pedestrian features were deeply analyzed. Meanwhile, the optimization strategies of existing methods were summarized. Finally, the future development directions of GNNs and person Re-ID technology were proposed.
LIU Guo-quan, CHEN Shang-liang, QIN Chen-xu, ZHOU Shu-min, ZHOU Huan-yin, WANG Xiao-gang.
Review of Person Re-identification Based on Graph Neural Network[J].
Science Technology and Engineering, 2026, 26(15): 6235-6249 DOI:10.12404/j.issn.1671-1815.2503176
XuL Q, HoggD C. Neural networks in human motion tracking—an experimental study[J]. Image and Vision Computing, 1997, 15(8): 607-615.
[2]
HintonG E. Reducing the dimensionality of data with neural networks[J]. Science, 2006, 313(5786): 504-507.
[3]
ZouQ, NiL, ZhangT, et al. Deep learning based feature selection for remote sensing scene classification[J]. IEEE Geoscience and Remote Sensing Letters, 2015, 12(11): 2321-2325.
[4]
ZhaoX, LiX, ZhangZ. Joint structural learning to rank with deep linear feature learning[J]. IEEE Transactions on Knowledge and Data Engineering, 2015, 27(10): 2756-2769.
[5]
GranotN, FeinsteinB, ShocherA, et al. Drop the GAN: in defense of patches nearest neighbors as single image generative models[C]// 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR). New York: IEEE, 2022: 13460-13469.
[6]
WangZ Q, LuY, LiQ, et al. CRIS: CLIP-driven referring image segmentation[C]// Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR). New York: IEEE, 2022: 11686-11695.
QinPeng, ChenGaohua, GuJiaxin. Occluded pedestrian re-identification based on foreground segmentation and multi-scale feature fusion[J]. Science Technology and Engineering, 2025, 25(21): 9002-9009.
[9]
YangH Q, CaiS J, ShengH L, et al. Balanced and hierarchical relation learning for one-shot object detection[C]// 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR). New York: IEEE, 2022: 7591-7600.
YuXian, DengHuijun. Multi scale detection method for forged face images based on residual graph neural network[J]. Journal of Hainan Tropical Ocean Institute, 2025, 32(5): 99-105.
[12]
YeM, ChenS, LiC, et al. Transformer for object re-identification: a survey[J]. International Journal of Computer Vision, 2025, 133(5): 2410-2440.
DengZiwen, DuanYong. Unsupervised pedestrian re identification based on deep clustering learning[J]. Journal of Electronic Measurement and Instrumentation, 2025, 39(3): 208-216.
[15]
YangZ Z, JinX, ZhengK C, et al. Unleashing potential of unsupervised pre-training with intra-identity regularization for person re-identification[C]// 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR). New York: IEEE, 2022: 14298-14307.
[16]
LiaoK, WangK, ZhengY, et al. Multi-scale saliency features fusion model for person re-identification[J]. Multimedia Tools and Applications, 2024, 83(22): 61605-61620.
[17]
JiaoS, WangJ, PanZ, et al. Multi-layer joint classification-metric deep learning for top view image person re-identification[C]// IEEE 2nd International Conference on Electronics and Communication Engineering (ICECE). Xi’an: IEEE, 2020: 47-50.
[18]
YuZ, LiL, XieJ, et al. Pedestrian 3D shape understanding for person re-identification via multi-view learning[J]. IEEE Transactions on Circuits and Systems for Video Technology, 2024, 34(7): 5589-5602.
[19]
ChangL, DengX M, ZhouM Q, et al. Convolutional neural networks in image understanding[J]. Acta Automatica Sinica, 2016, 42(9): 1300-1312.
LinJingdong, WuXinyi, ChaiYi, et al. Structure optimization of convolutional neural networks: a survey[J]. Acta Automatica Sinica, 2020, 46(1): 24-37.
[22]
KrizhevskyA, SutskeverI, HintonG E. ImageNet classification with deep convolutional neural networks[J]. Communications of the ACM, 2017, 60(6): 84-90.
[23]
LiY, HeJ, ZhangT, et al. Diverse part discovery: Occluded person re-identification with part-aware transformer[C]// Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. New York: IEEE, 2021: 2898-2907.
[24]
KansalK, VenkataS, PrasadD K, et al. CARF-Net: CNN attention and RNN fusion network for video-based person reidentification[J]. Journal of Electronic Imaging, 2019, 28(2): 023036.
[25]
ScarselliF, GoriM, TsoiA C, et al. Computational capabilities of graph neural networks[J]. IEEE Transactions on Neural Networks, 2009, 20(1): 81-102.
WangHongkun, FengMiaodi, LuWeiliang, et al. Research on malicious software family identification method based on graph neural network[J]. Network Security and Informatization, 2025(2): 46-48.
ZhongKai, ChenYing, YanChengzhi, et al. Three dimensional object detection algorithm based on graph neural network and dynamic sampling[J]. Progress in Laser and Optoelectronics, 2025, 62(14): 201-212.
[30]
HanG, LinM, LiZ, et al. Text-to-image person re-identification based on multimodal graph convolutional network[J]. IEEE Transactions on Multimedia, 2023, 26: 6025-6036.
[31]
ZhangY, ZhangF, JinY, et al. Local correlation ensemble with GCN based on attention features for cross-domain person re-ID[J]. ACM Transactions on Multimedia Computing, Communications and Applications, 2023, 19(2): 1-22.
[32]
PanH, BaiY, HeZ, et al. AAGCN: adjacency-aware graph convolutional network for person re-identification[J]. Knowledge-Based Systems, 2022, 236: 107300.
[33]
YeM, ShenJ, LinG, et al. Deep learning for person re-identification: a survey and outlook[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2021, 44(6): 2872-2893.
[34]
KhaldiK, MantiniP, ShahS K. Unsupervised person re-identification based on skeleton joints using graph convolutional networks[C]// International Conference on Image Analysis and Processing. Lecce: Spring, 2022: 135-146.
[35]
MengJ, ZhengW S, LaiJ H, et al. Deep graph metric learning for weakly supervised person re-identification[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2021, 44(10): 6074-6093.
[36]
RaoH, HuX, ChengJ, et al. SM-SGE: a self-supervised multi-scale skeleton graph encoding framework for person re-identification[C]// The 29th ACM International Conference on Multimedia. New York: ACM2021: 1812-1820.
[37]
RaoH, MiaoC. Skeleton prototype contrastive learning with multi-level graph relation modeling for unsupervised person re-identification[C]// International Conference on Heterogeneous Networking for Quality, Reliability, Security and Robustness. Cham: Springer, 2023: 196-218.
[38]
FengY, ChenF, JiY, et al. Efficient cross-modality graph reasoning for RGB-infrared person re-identification[J]. IEEE Signal Processing Letters, 2021, 28: 1425-1429.
[39]
WangY, LiX, JiangM, et al. Cross-view pedestrian clustering via graph convolution network for unsupervised person re-identification[J]. Journal of Intelligent & Fuzzy Systems, 2020, 39(3): 4453-4462.
[40]
AspertiA, FiorillaS, NardiS, et al. A review of recent techniques for person re-identification[J]. Machine Vision and Applications, 2025, 36(1): 25.
ChenYu, LiuHui, LiangDongsheng, et al. Person re-identification based on pose estimation and Transformer model[J]. Science Technology and Engineering, 2024, 24(12): 5051-5058.
[43]
YinJ, ZhangX, MaZ, et al. A real-time memory updating strategy for unsupervised person re-identification[J]. IEEE Transactions on Image Processing, 2023, 32: 2309-2321.
LiuZhongmin, LiFurui. Research on multi scale feature aggregation pedestrian re-identification model based on NAS[J/OL]. (2025-02-25)[2026-01-19]. https://doi.org/10.14107/j.cnki.kzgc.20240826.
LiuHaiyan, WangYong. Machine learning based facial recognition method for power safety control[J]. Electrical Technology and Economics, 2025(1): 7-10.
[48]
YangY, LinL. Automatic persons segmentation based on machine learning in surveillance video[C]// 2019 IEEE International Conference on Computational Electromagnetics (ICCEM). Shanghai: IEEE, 2019: 1-3.
[49]
WangY, WangP, SunB, et al. IInfoGAN: improved information maximizing generative adversarial networks[C]// 2020 5th International Conference on Mechanical, Control and Computer Engineering (ICMCCE). Harbin: IEEE, 2020: 1487-1490.
[50]
ZhangL, ZhangS, ZouB, et al. Unsupervised deep representation learning and few-shot classification of polsar images[J]. IEEE Transactions on Geoscience and Remote Sensing, 2022, 60: 1-16.
[51]
BenX, GongC, ZhangP, et al. Coupled patch alignment for matching cross-view gaits[J]. IEEE Transactions on Image Processing, 2019, 28(6): 3142-3157.
[52]
YuS, ChenH, GarciaR E B, et al. Gaitgan: invariant gait feature extraction using generative adversarial networks[C]// 2017 IEEE Conference on Computer Vision and Pattern Recognition Workshops. Honolulu: IEEE, 2017: 30-37.
[53]
AlganG, UlusoyI. Image classification with deep learning in the presence of noisy labels: a survey[J]. Knowledge-Based Systems, 2021, 215: 106771.
[54]
ZhangM, XuN, GengX. Feature-induced label distribution for learning with noisy labels[J]. Pattern Recognition Letters, 2022, 155: 107-113.
FuXing, WeiDan, LuoYiping. Unsupervised pedestrian recognition based on cross camera clustering comparison[J]. Computer and Digital Engineering, 2024, 52(11): 3297-3302, 3361.
WangHaowei, YanGang, GengShuze. Local representation learning based on feature fusion for pedestrian occlusion re recognition[J]. Software Engineering, 2025, 28(1): 19-22, 63.
[59]
YeM, ShenJ, LinG, et al. Deep learning for person re-identification: a survey and outlook[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2021, 44(6): 2872-2893.
[60]
SarkerP K, ZhaoQ, UddinM K. Transformer-based person re-identification: a comprehensive review[J]. IEEE Transactions on Intelligent Vehicles, 2024, 9(7): 5222-5239.
[61]
HuangY, ZhangZ, WuQ, et al. Enhancing person re-identification performance through in vivo learning[J]. IEEE Transactions on Image Processing, 2023, 33: 639-654.
[62]
ZhangW, CaoX, HuangL, et al. Domain-invariant multi-granularity feature learning for generalizable person re-identification[J]. Knowledge-Based Systems, 2025, 321: 113656.
[63]
LiuL, BlancaflorE, AbisadoM. Research on pedestrian re-identification based on enhanced residual attention network[J]. IEEE Access, 2025, 13: 27587-27595.
[64]
DingY, LiJ, WangH, et al. Attention-enhanced multimodal feature fusion network for clothes-changing person re-identification[J]. Complex & Intelligent Systems, 2025, 11(1): 2.
[65]
ZhangY, ZhangF, JinY, et al. Local correlation ensemble with GCN based on attention features for cross-domain person Re-ID[J]. ACM Transactions on Multimedia Computing, Communications and Applications, 2023, 19(2): 1-22.
[66]
YanD, CaoJ, XieW, et al. PersonalityGate: a general plug-and-play GNN gate to enhance cascade prediction with personality recognition task[J]. Expert Systems with Applications, 2022, 203: 117381.
[67]
RahmaniA, VenkitaramanA, FrossardP. A Meta-GNN approach to personalized seizure detection and classification[C]// ICASSP 2023—2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). New York: IEEE, 2023: 1-5.
[68]
ZhangL, ShiL, ZhaoJ, et al. A GNN-based multi-task learning framework for personalized video search[C]// Proceedings of the Fifteenth ACM International Conference on Web Search and Data Mining. New York: ACM, 2022: 1386-1394.
[69]
LuoD, ChengW, XuD, et al. Parameterized explainer for graph neural network[J]. Advances in Neural Information Processing Systems, 2020, 33: 19620-19631.
[70]
LiaoS C, ShaoL. Graph sampling based deep metric learning for generalizable person re-identification[C]// Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), New York: IEEE, 2022: 7359-7368.
[71]
ShenY, LiH, YiS, et al. Person re-identification with deep similarity-guided graph neural network[C]// Proceedings of the European Conference on Computer Vision (ECCV). Munich: ECCV, 2018: 486-504.
[72]
WuJ, YangY, LiuH, et al. Unsupervised graph association for person re-identification[C]// The IEEE/CVF International Conference on Computer Vision. New York: IEEE, 2019: 8321-8330.
[73]
WangJ, LongX, GaoY, et al. Graph-PCNN: two stage human pose estimation with graph pose refinement[C]// European Conference on Computer Vision. Cham: Springer International Publishing, 2020: 492-508.
[74]
YanY, ZhangQ, NiB, et al. Learning context graph for person search[C]// Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. New York: IEEE, 2019, 2158-2167.
[75]
YangJ, ZhengW S, YangQ, et al. Spatial-temporal graph convolutional network for video-based person re-identification[C]// The IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR). New York: IEEE, 2020: 3286-3296.
[76]
YanY, QinJ, ChenJ, et al. Learning multi-granular hypergraphs for video-based person re-identification[C]// Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR). New York: IEEE, 2020: 2896-2905.
[77]
BarmanA, ShahS K. Shape: a novel graph theoretic algorithm for making consensus-based decisions in person re-identification systems[C]// The IEEE International Conference on Computer Vision. New York: IEEE, 2017: 1115-1124.
[78]
KipfT N, WellingM. Semi-supervised classification with graph convolutional networks[C]// International Conference on Learning Representations. New York: IEEE, 2017: 1-14.
[79]
ZhangJ, LiX, ChenC, et al. Global-local graph convolutional network for cross-modality person re-identification[J]. Neurocomputing, 2021, 452: 137-146.
[80]
YeM, ShenJ, CrandallD, et al. Dynamic dual-attentive aggregation learning for visible-infrared person re-identification[C]// Computer Vision-ECCV 2020, Lecture Notes in Computer Science. Cham: Springer, 2020: 229-247.
[81]
HuangC. A relationship-aware feature update method for enhanced graph-based neural networks[J]. IEEE Access, 2025, 13: 37096-37107.
[82]
ZhangZ, ZhangH, LiuS, et al. Part-guided graph convolution networks for person re-identification[J]. Pattern Recognition, 2021, 120: 108155.
SongXiaoru, YangJia, GaoSong, et al. Person re-identification method based on attention mechanism and multi-scale feature fusion[J]. Science Technology and Engineering, 2022, 22(4): 1526-1533.
[85]
ChowdhuryP N, ShivakumaraP, KanchanS, et al. Graph attention network for detecting license plates in crowded street scenes[J]. Pattern Recognition Letters, 2020, 140: 18-25.
[86]
WuL, WangY, GaoJ, et al. Where-and-when to look: deep siamese attention networks for video-based person re-identification[J]. IEEE Transactions on Multimedia, 2018, 21(6): 1412-1424.
[87]
ZhouH, RenD, XiaH, et al. An attention-based spatio-temporal graph neural network for interaction-aware person trajectory prediction[J]. Neurocomputing, 2021, 445: 298-308.
[88]
ZhangH, LiY, ZhuangZ, et al. 3D-GAT: 3d-guided adversarial transform network for person re-identification in unseen domains[J]. Pattern Recognition, 2021, 112: 107799.
WangZhendong, XuZhenyu, LiDahai, et al. Construction and analysis of meta graph neural network for intrusion detection[J]. Acta Automatica Sinica, 2023, 49(7): 1530-1548.
[91]
GoodfellowI J, Pouget-AbadieJ, MirzaM, et al. Generative adversarial networks[J]. Advances in Neural Information Processing Systems, 2014, 3: 2672-2680.
[92]
WangH, WangJ, WangJ, et al. Learning graph representation with generative adversarial nets[J]. IEEE Transactions on Knowledge and Data Engineering, 2019, 33(8): 3090-3103.
[93]
FuX, LaiX. Unsupervised person re-identification via multi-order cross-view graph adversarial network[J]. IEEE Access, 2021, 9: 22264-22273.
[94]
WangH, WangJ, WangJ, et al. Graphgan: graph representation learning with generative adversarial nets[C]// Proceedings of the AAAI Conference on Artificial Intelligence. Hong Kong: AAAI, 2018: 2508-2515.
[95]
ChungD, TahboubK, DelpE J. A two stream siamese convolutional neural network for person re-identification[C]// Proceedings of the IEEE International Conference on Computer Vision. Venice: IEEE, 2017: 1992-2000.
[96]
YanS, XiongY, LinD. Spatial temporal graph convolutional networks for skeleton-based action recognition[C]// Association for the Advancement of Artficial Intelligence. Hong Kong: AAAI, 2018: 7444-7452.
[97]
ChoY J, YoonK J. Improving person re-identification via pose-aware multi-shot matching[C]// Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. Las Vegas: IEEE, 2016: 1354-1362.
[98]
ZhouH, RenD, XiaH, et al. AST-GNN: an attention-based spatio-temporal graph neural network for interaction-aware pedestrian trajectory prediction[J]. Neurocomputing, 2021, 445: 298-308.
LiuP, WangY, LiY, et al. Cross-domain person re-identification based on multi-branch pose-guided occlusion generation[J]. Sensors, 2025, 25(2): 473-473.
[101]
LiuG, WuJ. Video-based person re-identification by intra-frame and inter-frame graph neural network[J]. Image and Vision Computing, 2021, 106: 104068.
[102]
LiuH, XiaoZ, FanB, et al. PrGCN: probability prediction with graph convolutional network for person re-identification[J]. Neurocomputing, 2021, 423: 57-70.
[103]
ZhangJ, LiX, ChenC, et al. Global-local graph convolutional network for cross-modality person re-identification[J]. Neurocomputing, 2021, 452: 137-146.
[104]
SoniK, DograD P, SekhA A, et al. Person re-identification in indoor videos by information fusion using graph convolutional networks[J]. Expert Systems with Applications, 2022, 210: 118363.
[105]
QiY, GeH W, PeiW B, et al. Attention-guided spatial-temporal graph relation network for video-based person re-identification[J]. Neural Computing and Applications, 2023, 35(19): 14227-14241.