Person Re-identification: Past, Present and Future

Abstract

Person re-identification (re-ID) has become increasingly popular in the community due to its application and research significance. It aims at spotting a person of interest in other cameras. In the early days, hand-crafted algorithms and small-scale evaluation were predominantly reported. Recent years have witnessed the emergence of large-scale datasets and deep learning systems which make use of large data volumes. Considering different tasks, we classify most current re-ID methods into two classes, i.e., image-based and video-based; in both tasks, hand-crafted and deep learning systems will be reviewed. Moreover, two new re-ID tasks which are much closer to real-world applications are described and discussed, i.e., end-to-end re-ID and fast re-ID in very large galleries. This paper: 1) introduces the history of person re-ID and its relationship with image classification and instance retrieval; 2) surveys a broad selection of the hand-crafted systems and the large-scale methods in both image- and video-based re-ID; 3) describes critical future directions in end-to-end re-ID and fast retrieval in large galleries; and 4) finally briefs some important yet under-developed issues.

20 pages, 5 tables, 10 images

References in corpus (5)

• Very Deep Convolutional Networks for Large-Scale Image Recognition
• MOTChallenge 2015: Towards a Benchmark for Multi-Target Tracking
• Deep Semantic Ranking Based Hashing for Multi-Label Image Retrieval
• Temporal Pyramid Pooling Based Convolutional Neural Networks for Action Recognition
• Open-set Person Re-identification

Cited by in corpus (102)

• Random Erasing Data Augmentation
• AlignedReID: Surpassing Human-Level Performance in Person Re-Identification
• Avoiding Overfitting: A Survey on Regularization Methods for Convolutional Neural Networks
• Deep Transfer Learning for Person Re-identification
• Pose Invariant Embedding for Deep Person Re-identification
• Beyond Part Models: Person Retrieval with Refined Part Pooling (and a Strong Convolutional Baseline)
• Margin Sample Mining Loss: A Deep Learning Based Method for Person Re-identification
• Learning Deep Context-aware Features over Body and Latent Parts for Person Re-identification
• Complementary Pseudo Labels For Unsupervised Domain Adaptation On Person Re-identification
• Unsupervised Person Re-identification by Soft Multilabel Learning
• PoNA: Pose-guided Non-local Attention for Human Pose Transfer
• RGB-Infrared Cross-Modality Person Re-Identification via Joint Pixel and Feature Alignment
• Invariance Matters: Exemplar Memory for Domain Adaptive Person Re-identification
• Cross-Modality Paired-Images Generation for RGB-Infrared Person Re-Identification
• EANet: Enhancing Alignment for Cross-Domain Person Re-identification
• Diverse Part Discovery: Occluded Person Re-identification with Part-Aware Transformer
• Optimizing Performance of Federated Person Re-identification: Benchmarking and Analysis
• A Video Is Worth Three Views: Trigeminal Transformers for Video-based Person Re-identification
• Graph Neural Based End-to-end Data Association Framework for Online Multiple-Object Tracking
• Sampling Agnostic Feature Representation for Long-Term Person Re-identification
• Divide and Fuse: A Re-ranking Approach for Person Re-identification
• Survey on Reliable Deep Learning-Based Person Re-Identification Models: Are We There Yet?
• Locality Aware Appearance Metric for Multi-Target Multi-Camera Tracking
• Cross-Spectrum Dual-Subspace Pairing for RGB-infrared Cross-Modality Person Re-Identification
• A heterogeneous branch and multi-level classification network for person re-identification
• Asymmetric Co-Teaching for Unsupervised Cross Domain Person Re-Identification
• Hyperbolic Deep Neural Networks: A Survey
• A New Evaluation Protocol and Benchmarking Results for Extendable Cross-media Retrieval
• Watching You: Global-guided Reciprocal Learning for Video-based Person Re-identification
• Adaptively Connected Neural Networks
• An Introduction to Person Re-identification with Generative Adversarial Networks
• Enhancing the Discriminative Feature Learning for Visible-Thermal Cross-Modality Person Re-Identification
• Hetero-Center Loss for Cross-Modality Person Re-Identification
• In Defense of the Triplet Loss Again: Learning Robust Person Re-Identification with Fast Approximated Triplet Loss and Label Distillation
• FPB: Feature Pyramid Branch for Person Re-Identification
• Attention: A Big Surprise for Cross-Domain Person Re-Identification
• Lifelong Person Re-Identification via Adaptive Knowledge Accumulation
• DF^2AM: Dual-level Feature Fusion and Affinity Modeling for RGB-Infrared Cross-modality Person Re-identification
• Semantics-Guided Clustering with Deep Progressive Learning for Semi-Supervised Person Re-identification
• Memorizing Comprehensively to Learn Adaptively: Unsupervised Cross-Domain Person Re-ID with Multi-level Memory
• Do Not Disturb Me: Person Re-identification Under the Interference of Other Pedestrians
• IDM: An Intermediate Domain Module for Domain Adaptive Person Re-ID
• Person Re-identification with Metric Learning using Privileged Information
• Global Distance-distributions Separation for Unsupervised Person Re-identification
• Grafted network for person re-identification
• Surpassing Real-World Source Training Data: Random 3D Characters for Generalizable Person Re-Identification
• Unity Style Transfer for Person Re-Identification
• Deep Feature Learning via Structured Graph Laplacian Embedding for Person Re-Identification
• Dual Gaussian-based Variational Subspace Disentanglement for Visible-Infrared Person Re-Identification
• CL2R: Compatible Lifelong Learning Representations
• Unsupervised Data Uncertainty Learning in Visual Retrieval Systems
• Weakly Supervised Open-set Domain Adaptation by Dual-domain Collaboration
• Apparel-invariant Feature Learning for Apparel-changed Person Re-identification
• Pedestrian re-identification based on Tree branch network with local and global learning
• Backbone Can Not be Trained at Once: Rolling Back to Pre-trained Network for Person Re-Identification
• Progressive and Aligned Pose Attention Transfer for Person Image Generation
• Learning to Learn in a Semi-Supervised Fashion
• Transferable, Controllable, and Inconspicuous Adversarial Attacks on Person Re-identification With Deep Mis-Ranking
• Exploring Uncertainty in Conditional Multi-Modal Retrieval Systems
• Diversity-Achieving Slow-DropBlock Network for Person Re-Identification
• Branch-Cooperative OSNet for Person Re-Identification
• Robust Person Re-Identification through Contextual Mutual Boosting
• Deep Active Learning for Video-based Person Re-identification
• Faster Person Re-Identification
• Unsupervised Disentanglement GAN for Domain Adaptive Person Re-Identification
• Wide-Baseline Multi-Camera Calibration using Person Re-Identification
• Re-Identification Supervised Texture Generation
• Effective Image Retrieval via Multilinear Multi-index Fusion
• Stronger Baseline for Person Re-Identification
• ID-aware Quality for Set-based Person Re-identification
• Rank Persistence: Assessing the Temporal Performance of Real-World Person Re-Identification
• Person image generation with semantic attention network for person re-identification
• Large-Scale Unsupervised Person Re-Identification with Contrastive Learning
• Additive Adversarial Learning for Unbiased Authentication
• Temporal Self-Ensembling Teacher for Semi-Supervised Object Detection
• Towards a Principled Integration of Multi-Camera Re-Identification and Tracking through Optimal Bayes Filters
• Hierarchical Gaussian Descriptors with Application to Person Re-Identification
• Camera On-boarding for Person Re-identification using Hypothesis Transfer Learning
• End-to-End Training of CNN Ensembles for Person Re-Identification
• Perceive Where to Focus: Learning Visibility-aware Part-level Features for Partial Person Re-identification
• Unsupervised Person Re-Identification with Multi-Label Learning Guided Self-Paced Clustering
• Weakly supervised discriminative feature learning with state information for person identification
• GaitSet: Cross-view Gait Recognition through Utilizing Gait as a Deep Set
• Progressive Unsupervised Person Re-identification by Tracklet Association with Spatio-Temporal Regularization
• Low Resolution Information Also Matters: Learning Multi-Resolution Representations for Person Re-Identification
• Deep High-Resolution Representation Learning for Cross-Resolution Person Re-identification
• Cross-Correlated Attention Networks for Person Re-Identification
• Pose-Guided Feature Learning with Knowledge Distillation for Occluded Person Re-Identification
• Copy and Paste method based on Pose for Re-identification
• Video-Based Convolutional Attention for Person Re-Identification
• Pseudo-positive regularization for deep person re-identification
• Unsupervised Person Re-identification via Multi-Label Prediction and Classification based on Graph-Structural Insight
• Adaptive Deep Metric Embeddings for Person Re-Identification under Occlusions
• Single Camera Training for Person Re-identification
• Pose Invariant Person Re-Identification using Robust Pose-transformation GAN
• Hierarchical Cross Network for Person Re-identification
• Learning Posterior and Prior for Uncertainty Modeling in Person Re-Identification
• FTN: Foreground-Guided Texture-Focused Person Re-Identification
• Person Re-identification with Adversarial Triplet Embedding
• Resolution-invariant Person ReID Based on Feature Transformation and Self-weighted Attention
• Domain Agnostic Learning for Unbiased Authentication
• Set Augmented Triplet Loss for Video Person Re-Identification