Published: 09 Oct 2015 Category: deep_learning



Method backbone test size Market1501 CUHK03 (detected) CUHK03 (detected/new) CUHK03 (labeled/new) CUHK-SYSU DukeMTMC-reID MARS
      rank1 / mAP rank1/rank5/rank10 rank1 / mAP rank1 / mAP rank1 / mAP   rank1 / mAP
DG-Net ResNet-50 256×128 94.8/ 86.0   65.6/61.1     86.6/74.8  
AlignedReID ResNet50-X   92.6 / 82.3 91.9 / 98.7 / 99.4   86.8 / 79.1     95.3 / 93.7
Deep-Person ResNet-50 256×128 92.31 / 79.58 89.4 / 98.2 / 99.1         80.90 / 64.80
PCB ResNet-50 384x128 92.4 / 77.3   61.3 / 54.2     81.9 / 65.3  
PCB+RPP ResNet-50 384x128 93.8 / 81.6   63.7 / 57.5     83.3 / 69.2  
PN-GAN ResNet-50   89.43 / 72.58 79.76 / 96.24 / 98.56       73.58 / 53.20  
MGN ResNet-50   95.7 / 86.9   66.8 / 66.0 68.0 / 67.4   88.7 / 78.4  
HPM ResNet-50 384x128 94.2 / 82.7   63.1 / 57.5     86.6 / 74.3  
HPM+HRE ResNet-50 384x128 93.9 / 83.1   63.2 / 59.7     86.3 / 74.5  
SphereReID ResNet-50 288×144 94.4 / 83.6 93.1 / 98.7 / 99.4 63.2 / 59.7   95.4 / 93.9 83.9 / 68.5  
Auto-ReID   384x128 94.5 / 85.1   73.3 / 69.3 77.9 / 73.0   88.5 / 75.1  


Method backbone CUHK-SYSU PRW PRW-mini
    top1 / mAP top1 / mAP top1 / mAP
Joint Detection and Identification Feature Learning for Person Search ResNet-50 78.7 / 75.5 – / – – / –
Learning Context Graph for Person Search ResNet-50 86.5 / 84.1 73.6 / 33.4 – / –
Knowledge Distillation for End-to-End Person Search ResNet-50 88.5 / 87.2 – / – 70.0 / 33.1
Query-guided End-to-End Person Search ResNet-50 89.1 / 88.9 76.7 / 37.1 80.0 / 39.1
Fast Person Search Pipeline ResNet-50 89.87 / 86.99 70.58/ 44.45 – / –
End-to-End Thorough Body Perception for Person Search ResNet-50 90.5 / 88.4 68.9 / 42.9 – / –
Re-ID Driven Localization Refinement for Person Search ResNet-50 94.2 / 93.0 70.2 / 42.9 – / –


Uncertainty-Aware Multi-Shot Knowledge Distillation for Image-Based Object Re-Identification

Robust Re-Identification by Multiple Views Knowledge Distillation

Self-paced Contrastive Learning with Hybrid Memory for Domain Adaptive Object Re-ID

Context-Aware Graph Convolution Network for Target Re-identification

Person Re-identification / Person Retrieval

DeepReID: Deep Filter Pairing Neural Network for Person Re-Identification

An Improved Deep Learning Architecture for Person Re-Identification

Deep Ranking for Person Re-identification via Joint Representation Learning

PersonNet: Person Re-identification with Deep Convolutional Neural Networks

Learning Deep Feature Representations with Domain Guided Dropout for Person Re-identification

Person Re-Identification by Multi-Channel Parts-Based CNN with Improved Triplet Loss Function

Joint Learning of Single-image and Cross-image Representations for Person Re-identification

End-to-End Comparative Attention Networks for Person Re-identification

A Multi-task Deep Network for Person Re-identification

A Siamese Long Short-Term Memory Architecture for Human Re-Identification

Gated Siamese Convolutional Neural Network Architecture for Human Re-Identification

Deep Neural Networks with Inexact Matching for Person Re-Identification

Person Re-identification: Past, Present and Future

Deep Learning Prototype Domains for Person Re-Identification

Deep Transfer Learning for Person Re-identification

A Discriminatively Learned CNN Embedding for Person Re-identification

Person Re-Identification via Recurrent Feature Aggregation

Structured Deep Hashing with Convolutional Neural Networks for Fast Person Re-identification

SVDNet for Pedestrian Retrieval

In Defense of the Triplet Loss for Person Re-Identification

Beyond triplet loss: a deep quadruplet network for person re-identification

Quality Aware Network for Set to Set Recognition

Learning Deep Context-aware Features over Body and Latent Parts for Person Re-identification

Point to Set Similarity Based Deep Feature Learning for Person Re-identification

Scalable Person Re-identification on Supervised Smoothed Manifold

Attention-based Natural Language Person Retrieval

Part-based Deep Hashing for Large-scale Person Re-identification

Deep Person Re-Identification with Improved Embedding

Deep Person Re-Identification with Improved Embedding and Efficient Training

Towards a Principled Integration of Multi-Camera Re-Identification and Tracking through Optimal Bayes Filters

Person Re-Identification by Deep Joint Learning of Multi-Loss Classification

Deep Representation Learning with Part Loss for Person Re-Identification

Pedestrian Alignment Network for Large-scale Person Re-identification

Learning Efficient Image Representation for Person Re-Identification

Person Re-identification Using Visual Attention

What-and-Where to Match: Deep Spatially Multiplicative Integration Networks for Person Re-identification

Deep Feature Learning via Structured Graph Laplacian Embedding for Person Re-Identification

Large Margin Learning in Set to Set Similarity Comparison for Person Re-identification

Multi-scale Deep Learning Architectures for Person Re-identification

Person Re-Identification by Deep Learning Multi-Scale Representations

Person Re-Identification with Vision and Language

Margin Sample Mining Loss: A Deep Learning Based Method for Person Re-identification

Pseudo-positive regularization for deep person re-identification

Let Features Decide for Themselves: Feature Mask Network for Person Re-identification

AlignedReID: Surpassing Human-Level Performance in Person Re-Identification

Deep Cosine Metric Learning for Person Re-Identification

Region-based Quality Estimation Network for Large-scale Person Re-identification

Beyond Part Models: Person Retrieval with Refined Part Pooling

Deep-Person: Learning Discriminative Deep Features for Person Re-Identification

Hierarchical Cross Network for Person Re-identification

Re-ID done right: towards good practices for person re-identification

Triplet-based Deep Similarity Learning for Person Re-Identification

Group Consistent Similarity Learning via Deep CRFs for Person Re-Identification

Image-Image Domain Adaptation with Preserved Self-Similarity and Domain-Dissimilarity for Person Re-identification

  • intro: CVPR 2018
  • keywords: similarity preserving generative adversarial network (SPGAN), Siamese network, CycleGAN, domain adaptation
  • arxiv:

Similarity-preserving Image-image Domain Adaptation for Person Re-identification

Harmonious Attention Network for Person Re-Identification

Camera Style Adaptation for Person Re-identfication

Image-Image Domain Adaptation with Preserved Self-Similarity and Domain-Dissimilarity for Person Re-identification

Dual Attention Matching Network for Context-Aware Feature Sequence based Person Re-Identification

Multi-Level Factorisation Net for Person Re-Identification

Features for Multi-Target Multi-Camera Tracking and Re-Identification

Good Appearance Features for Multi-Target Multi-Camera Tracking

Mask-guided Contrastive Attention Model for Person Re-Identification

Efficient and Deep Person Re-Identification using Multi-Level Similarity

Person Re-identification with Cascaded Pairwise Convolutions

Attention-Aware Compositional Network for Person Re-identification

  • intro: CVPR 2018
  • intro: Sensets Technology Limited & University of Sydney
  • keywords: Attention-Aware Compositional Network (AACN), Pose-guided Part Attention (PPA), Attention-aware Feature Composition (AFC)
  • arxiv:

Deep Group-shuffling Random Walk for Person Re-identification

Adversarially Occluded Samples for Person Re-identification

Easy Identification from Better Constraints: Multi-Shot Person Re-Identification from Reference Constraints

Eliminating Background-bias for Robust Person Re-identification

End-to-End Deep Kronecker-Product Matching for Person Re-identification

Exploiting Transitivity for Learning Person Re-identification Models on a Budget

Resource Aware Person Re-identification across Multiple Resolutions

Multi-Channel Pyramid Person Matching Network for Person Re-Identification

  • intro: 32nd AAAI Conference on Artificial Intelligence
  • keywords: Multi-Channel deep convolutional Pyramid Person Matching Network (MC-PPMN)
  • arxiv:

Pyramid Person Matching Network for Person Re-identification

Virtual CNN Branching: Efficient Feature Ensemble for Person Re-Identification

Weighted Bilinear Coding over Salient Body Parts for Person Re-identification

Adversarial Binary Coding for Efficient Person Re-identification

Learning View-Specific Deep Networks for Person Re-Identification

  • intro: IEEE Transactions on image processing. Sun Yat-Sen University
  • keywords: cross-view Euclidean constraint (CV-EC), cross-view center loss (CV-CL)
  • arxiv:

Learning Discriminative Features with Multiple Granularities for Person Re-Identification

Recurrent Neural Networks for Person Re-identification Revisited

MaskReID: A Mask Based Deep Ranking Neural Network for Person Re-identification

Horizontal Pyramid Matching for Person Re-identification

Deep Co-attention based Comparators For Relative Representation Learning in Person Re-identification

Feature Affinity based Pseudo Labeling for Semi-supervised Person Re-identification

Semantically Selective Augmentation for Deep Compact Person Re-Identification

SphereReID: Deep Hypersphere Manifold Embedding for Person Re-Identification

Multi-task Mid-level Feature Alignment Network for Unsupervised Cross-Dataset Person Re-Identification

Discriminative Feature Learning with Foreground Attention for Person Re-Identification

Part-Aligned Bilinear Representations for Person Re-identification

Mancs: A Multi-task Attentional Network with Curriculum Sampling for Person Re-identification

  • intro: ECCV 2018. Huazhong University of Science and Technology & Horizon Robotics Inc.

Improving Deep Visual Representation for Person Re-identification by Global and Local Image-language Association

Deep Sequential Multi-camera Feature Fusion for Person Re-identification

Improving Deep Models of Person Re-identification for Cross-Dataset Usage

Measuring the Temporal Behavior of Real-World Person Re-Identification

Alignedreid++: Dynamically Matching Local Information for Person Re-Identification

Sparse Label Smoothing for Semi-supervised Person Re-Identification

In Defense of the Classification Loss for Person Re-Identification

FD-GAN: Pose-guided Feature Distilling GAN for Robust Person Re-identification

Image-to-Video Person Re-Identification by Reusing Cross-modal Embeddings

Attention Driven Person Re-identification

A Coarse-to-fine Pyramidal Model for Person Re-identification via Multi-Loss Dynamic Training

M2M-GAN: Many-to-Many Generative Adversarial Transfer Learning for Person Re-Identification

Batch Feature Erasing for Person Re-identification and Beyond

Re-Identification with Consistent Attentive Siamese Networks

One Shot Domain Adaptation for Person Re-Identification

Parameter-Free Spatial Attention Network for Person Re-Identification

Spectral Feature Transformation for Person Re-identification

Identity Preserving Generative Adversarial Network for Cross-Domain Person Re-identification

Dissecting Person Re-identification from the Viewpoint of Viewpoint

Fast and Accurate Person Re-Identification with RMNet

Spatial-Temporal Person Re-identification

Omni-directional Feature Learning for Person Re-identification

Learning Incremental Triplet Margin for Person Re-identification

Densely Semantically Aligned Person Re-Identification

EANet: Enhancing Alignment for Cross-Domain Person Re-identification

Backbone Can Not be Trained at Once: Rolling Back to Pre-trained Network for Person Re-Identification

Ensemble Feature for Person Re-Identification

Adversarial Metric Attack for Person Re-identification

Discovering Underlying Person Structure Pattern with Relative Local Distance for Person Re-identification

Attributes-aided Part Detection and Refinement for Person Re-identification

Bags of Tricks and A Strong Baseline for Deep Person Re-identification

Auto-ReID: Searching for a Part-aware ConvNet for Person Re-Identification

Perceive Where to Focus: Learning Visibility-aware Part-level Features for Partial Person Re-identification

Pedestrian re-identification based on Tree branch network with local and global learning

Invariance Matters: Exemplar Memory for Domain Adaptive Person Re-identification

Person Re-identification with Bias-controlled Adversarial Training

Relation-Aware Global Attention for Person Re-identification

Person Re-identification with Metric Learning using Privileged Information

Multi-Scale Body-Part Mask Guided Attention for Person Re-identification

Deep Constrained Dominant Sets for Person Re-identification

Illumination-Adaptive Person Re-identification

Domain Adaptive Person Re-Identification via Camera Style Generation and Label Propagation

Beyond Intra-modality Discrepancy: A Comprehensive Survey of Heterogeneous Person Re-identification

Deep Multi-Index Hashing for Person Re-Identification

Attention: A Big Surprise for Cross-Domain Person Re-Identification

Semantics-Aligned Representation Learning for Person Re-identification

Rethinking Person Re-Identification with Confidence

CDPM: Convolutional Deformable Part Models for Person Re-identification

Resolution-invariant Person Re-Identification

Interaction-and-Aggregation Network for Person Re-identification

Distilled Person Re-identification: Towards a More Scalable System

Universal Person Re-Identification

ABD-Net: Attentive but Diverse Person Re-Identification

Fairest of Them All: Establishing a Strong Baseline for Cross-Domain Person ReID

Progressive Cross-camera Soft-label Learning for Semi-supervised Person Re-identification

Mixed High-Order Attention Network for Person Re-Identification

Recover and Identify: A Generative Dual Model for Cross-Resolution Person Re-Identification

HorNet: A Hierarchical Offshoot Recurrent Network for Improving Person Re-ID via Image Captioning

Temporal Knowledge Propagation for Image-to-Video Person Re-identification

SBSGAN: Suppression of Inter-Domain Background Shift for Person Re-Identification

Learning Deep Representations by Mutual Information for Person Re-identification

Orthogonal Center Learning with Subspace Masking for Person Re-Identification

Adaptive Graph Representation Learning for Video Person Re-identification

POD: Practical Object Detection with Scale-Sensitive Network

Second-order Non-local Attention Networks for Person Re-identification

Cross-Dataset Person Re-Identification via Unsupervised Pose Disentanglement and Adaptation

View Confusion Feature Learning for Person Re-identification

Augmented Hard Example Mining for Generalizable Person Re-Identification

Learning Generalisable Omni-Scale Representations for Person Re-Identification

Attention Network Robustification for Person ReID

Beyond Human Parts: Dual Part-Aligned Representations for Person Re-Identification

An End-to-End Foreground-Aware Network for Person Re-Identification

Learning Disentangled Representation for Robust Person Re-identification

ID-aware Quality for Set-based Person Re-identification

Calibrated Domain-Invariant Learning for Highly Generalizable Large Scale Re-Identification

Collaborative Attention Network for Person Re-identification

Viewpoint-Aware Loss with Angular Regularization for Person Re-Identification

AANet: Attribute Attention Network for Person Re-Identifications

In Defense of the Triplet Loss Again: Learning Robust Person Re-Identification with Fast Approximated Triplet Loss and Label Distillation

Rethinking the Distribution Gap of Person Re-identification with Camera-based Batch Normalization

Intra-Camera Supervised Person Re-Identification

Towards Precise Intra-camera Supervised Person Re-identification

Diversity-Achieving Slow-DropBlock Network for Person Re-Identification

MagnifierNet: Towards Semantic Regularization and Fusion for Person Re-identification

Triplet Online Instance Matching Loss for Person Re-identification

When Person Re-identification Meets Changing Clothes

Multi-task Learning with Coarse Priors for Robust Part-aware Person Re-identification

Transferable, Controllable, and Inconspicuous Adversarial Attacks on Person Re-identification With Deep Mis-Ranking

Real-world Person Re-Identification via Degradation Invariance Learning

Person Re-identification in the 3D Space

Rethinking Classification Loss Designs for Person Re-identification with a Unified View

Multiple Expert Brainstorming for Domain Adaptive Person Re-identification

ESA-ReID: Entropy-Based Semantic Feature Alignment for Person re-ID

Joint Disentangling and Adaptation for Cross-Domain Person Re-Identification

Dual Distribution Alignment Network for Generalizable Person Re-Identification

Hierarchical Bi-Directional Feature Perception Network for Person Re-Identification

Black Re-ID: A Head-shoulder Descriptor for the Challenging Problem of Person Re-Identification

Faster Person Re-Identification

Do Not Disturb Me: Person Re-identification Under the Interference of Other Pedestrians

Apparel-invariant Feature Learning for Apparel-changed Person Re-identification

Cluster-level Feature Alignment for Person Re-identification

Self-Supervised Gait Encoding with Locality-Aware Attention for Person Re-Identification

Receptive Multi-granularity Representation for Person Re-Identification

Proxy Task Learning For Cross-Domain Person Re-Identification

Progressive Bilateral-Context Driven Model for Post-Processing Person Re-Identification

Devil’s in the Detail: Graph-based Key-point Alignment and Embedding for Person Re-ID

Hybrid-Attention Guided Network with Multiple Resolution Features for Person Re-Identification

Beyond Triplet Loss: Person Re-identification with Fine-grained Difference-aware Pairwise Loss

Batch Coherence-Driven Network for Part-aware Person Re-Identification

FTN: Foreground-Guided Texture-Focused Person Re-Identification

Improve Person Re-Identification With Part Awareness Learning

Performance Optimization for Federated Person Re-identification via Benchmark Analysis

DomainMix: Learning Generalizable Person Re-Identification Without Human Annotations

Multi-Domain Adversarial Feature Generalization for Person Re-Identification

Learning to Generalize Unseen Domains via Memory-based Multi-Source Meta-Learning for Person Re-Identification

Unsupervised Pre-training for Person Re-identification

UnrealPerson: An Adaptive Pipeline towards Costless Person Re-identification

One for More: Selecting Generalizable Samples for Generalizable ReID Model

Exploiting Sample Uncertainty for Domain Adaptive Person Re-Identification

Camera-aware Proxies for Unsupervised Person Re-Identification

1st Place Solution to VisDA-2020: Bias Elimination for Domain Adaptive Pedestrian Re-identification

HAVANA: Hierarchical and Variation-Normalized Autoencoder for Person Re-identification

AXM-Net: Cross-Modal Context Sharing Attention Network for Person Re-ID

TransReID: Transformer-based Object Re-Identification

Deep Miner: A Deep and Multi-branch Network which Mines Rich and Diverse Features for Person Re-identification

AttriMeter: An Attribute-guided Metric Interpreter for Person Re-Identification

Watching You: Global-guided Reciprocal Learning for Video-based Person Re-identification

Lifelong Person Re-Identification via Adaptive Knowledge Accumulation

Spatiotemporal Transformer for Video-based Person Re-identification

  • intro: Beihang University & Pengcheng Laboratory & Tsinghua University & University of Science and Technology of China & Xidian University
  • arxiv:

AAformer: Auto-Aligned Transformer for Person Re-Identification

Combined Depth Space based Architecture Search For Person Re-identification

Graph-based Person Signature for Person Re-Identifications

Unsupervised Multi-Source Domain Adaptation for Person Re-Identification

Person Search

End-to-End Deep Learning for Person Search

Joint Detection and Identification Feature Learning for Person Search

Person Re-identification in the Wild

IAN: The Individual Aggregation Network for Person Search

Neural Person Search Machines

Efficient Person Search via Expert-Guided Knowledge Distillation

End-to-End Detection and Re-identification Integrated Net for Person Search

Person Search via A Mask-guided Two-stream CNN Model

Person Search by Multi-Scale Matching

  • intro: ECCV 2018
  • intro: Queen Mary University of London & Vision Semantics Ltd
  • keywords: Cross-Level Semantic Alignment (CLSA)
  • arxiv:

RCAA: Relational Context-Aware Agents for Person Search

Fast Person Search Pipeline

Learning Context Graph for Person Search

Query-guided End-to-End Person Search

Knowledge Distillation for End-to-End Person Search

Re-ID Driven Localization Refinement for Person Search

  • intro: ICCV 2019
  • intro: Huazhong University of Science and Technology & Peking University & Shanghai Jiao Tong University & Megvii Technology
  • arxiv:

End-to-End Thorough Body Perception for Person Search

Hierarchical Online Instance Matching for Person Search

Robust Partial Matching for Person Search in the Wild

Joint Person Objectness and Repulsion for Person Search

Norm-Aware Embedding for Efficient Person Search

A Multi-task Joint Framework for Real-time Person Search

Diverse Knowledge Distillation for End-to-End Person Search

Multi-Attribute Enhancement Network for Person Search

Sequential End-to-end Network for Efficient Person Search

Anchor-Free Person Search

Pose / Viewpoint for Re-ID

Pose Invariant Embedding for Deep Person Re-identification

Deeply-Learned Part-Aligned Representations for Person Re-Identification

Spindle Net: Person Re-identification with Human Body Region Guided Feature Decomposition and Fusion

Pose-driven Deep Convolutional Model for Person Re-identification

A Pose-Sensitive Embedding for Person Re-Identification with Expanded Cross Neighborhood Re-Ranking

Pose-Driven Deep Models for Person Re-Identification

Pose Transferrable Person Re-Identification

Person re-identification with fusion of hand-crafted and deep pose-based body region features

GAN for Re-ID

Unlabeled Samples Generated by GAN Improve the Person Re-identification Baseline in vitro

Person Transfer GAN to Bridge Domain Gap for Person Re-Identification

Pose-Normalized Image Generation for Person Re-identification

Multi-pseudo Regularized Label for Generated Samples in Person Re-Identification

Joint Discriminative and Generative Learning for Person Re-identification

Human Parsing for Re-ID

Human Semantic Parsing for Person Re-identification

Improved Person Re-Identification Based on Saliency and Semantic Parsing with Deep Neural Network Models

Identity-Guided Human Semantic Parsing for Person Re-Identification

Human Parsing Based Alignment with Multi-task Learning for Occluded Person Re-identification

Partial Person Re-ID

Partial Person Re-identification

Deep Spatial Feature Reconstruction for Partial Person Re-identification: Alignment-Free Approach

Occluded Person Re-identification

Partial Person Re-identification with Alignment and Hallucination

SCPNet: Spatial-Channel Parallelism Network for Joint Holistic and Partial Person Re-Identification

STNReID : Deep Convolutional Networks with Pairwise Spatial Transformer Networks for Partial Person Re-identification

Foreground-aware Pyramid Reconstruction for Alignment-free Occluded Person Re-identification

A Novel Teacher-Student Learning Framework For Occluded Person Re-Identification

VRSTC: Occlusion-Free Video Person Re-Identification

Pose-Guided Feature Alignment for Occluded Person Re-Identification

High-Order Information Matters: Learning Relation and Topology for Occluded Person Re-Identification

Pose-guided Visible Part Matching for Occluded Person ReID

MHSA-Net: Multi-Head Self-Attention Network for Occluded Person Re-Identification

Holistic Guidance for Occluded Person Re-Identification

Cross-modality Re-ID


RGB-Infrared Cross-Modality Person Re-Identification

RGB-Infrared Cross-Modality Person Re-Identification via Joint Pixel and Feature Alignment

Depth-Based Re-ID

Reinforced Temporal Attention and Split-Rate Transfer for Depth-Based Person Re-Identification

A Cross-Modal Distillation Network for Person Re-identification in RGB-Depth

Low Resolution Re-ID

Multi-scale Learning for Low-resolution Person Re-identification

Cascaded SR-GAN for Scale-Adaptive Low Resolution Person Re-identification

Deep Low-Resolution Person Re-Identification

Reinforcement Learning for Re-ID

Deep Reinforcement Learning Attention Selection for Person Re-Identification

Attributes Prediction for Re-ID

Multi-Task Learning with Low Rank Attribute Embedding for Person Re-identification

Deep Attributes Driven Multi-Camera Person Re-identification

Improving Person Re-identification by Attribute and Identity Learning

Person Re-identification by Deep Learning Attribute-Complementary Information

CA3Net: Contextual-Attentional Attribute-Appearance Network for Person Re-Identification

Attribute analysis with synthetic dataset for person re-identification

Taking A Closer Look at Synthesis: Fine-grained Attribute Analysis for Person Re-Identification

Video Person Re-Identification

Recurrent Convolutional Network for Video-based Person Re-Identification

Deep Recurrent Convolutional Networks for Video-based Person Re-identification: An End-to-End Approach

Jointly Attentive Spatial-Temporal Pooling Networks for Video-based Person Re-Identification

Three-Stream Convolutional Networks for Video-based Person Re-Identification

LVreID: Person Re-Identification with Long Sequence Videos

Multi-shot Pedestrian Re-identification via Sequential Decision Making

Learning Distributional Representation and Set Distance for Multi-shot Person Re-identification

LVreID: Person Re-Identification with Long Sequence Videos

Diversity Regularized Spatiotemporal Attention for Video-based Person Re-identification

Video Person Re-identification with Competitive Snippet-similarity Aggregation and Co-attentive Snippet Embedding

Exploit the Unknown Gradually: One-Shot Video-Based Person Re-Identification by Stepwise Learning

Video Person Re-Identification With Competitive Snippet-Similarity Aggregation and Co-Attentive Snippet Embedding

Revisiting Temporal Modeling for Video-based Person ReID

Video Person Re-identification by Temporal Residual Learning

A Spatial and Temporal Features Mixture Model with Body Parts for Video-based Person Re-Identification

Video-based Person Re-identification via 3D Convolutional Networks and Non-local Attention

Spatial-Temporal Synergic Residual Learning for Video Person Re-Identification

SCAN: Self-and-Collaborative Attention Network for Video Person Re-identification

Where-and-When to Look: Deep Siamese Attention Networks for Video-based Person Re-identification

STA: Spatial-Temporal Attention for Large-Scale Video-based Person Re-Identification

Multi-scale 3D Convolution Network for Video Based Person Re-Identification

Deep Active Learning for Video-based Person Re-identification

Spatial and Temporal Mutual Promotion for Video-based Person Re-identification

3D PersonVLAD: Learning Deep Global Representations for Video-based Person Re-identification

GAN-based Pose-aware Regulation for Video-based Person Re-identification

  • intro: Heriot-Watt University & University of Edinburgh & Queen’s University Belfast & Anyvision
  • keywords: Weighted Fusion (WF) & Weighted-Pose Regulation (WPR)
  • arxiv:

Convolutional Temporal Attention Model for Video-based Person Re-identification

Video Person Re-Identification using Learned Clip Similarity Aggregation

Video Person Re-ID: Fantastic Techniques and Where to Find Them

Multi-Granularity Reference-Aided Attentive Feature Aggregation for Video-based Person Re-identification

Appearance-Preserving 3D Convolution for Video-based Person Re-identification

Temporal Complementary Learning for Video Person Re-Identification

Reference-Aided Part-Aligned Feature Disentangling for Video Person Re-Identification

Spatial-Temporal Correlation and Topology Learning for Person Re-Identification in Videos


Divide and Fuse: A Re-ranking Approach for Person Re-identification

Re-ranking Person Re-identification with k-reciprocal Encoding

A Pose-Sensitive Embedding for Person Re-Identification with Expanded Cross Neighborhood Re-Ranking

Adaptive Re-ranking of Deep Feature for Person Re-identification

Unsupervised Re-ID

Unsupervised Person Re-identification: Clustering and Fine-tuning

Stepwise Metric Promotion for Unsupervised Video Person Re-identification

Dynamic Label Graph Matching for Unsupervised Video Re-Identification

Unsupervised Cross-dataset Person Re-identification by Transfer Learning of Spatio-temporal Patterns

Cross-dataset Person Re-Identification Using Similarity Preserved Generative Adversarial Networks

Unsupervised Cross-dataset Person Re-identification by Transfer Learning of Spatial-Temporal Patterns

Transferable Joint Attribute-Identity Deep Learning for Unsupervised Person Re-Identification

Adaptation and Re-Identification Network: An Unsupervised Deep Transfer Learning Approach to Person Re-Identification

  • intro: CVPR 2018 workshop. National Taiwan University & Umbo Computer Vision
  • keywords: adaptation and re-identification network (ARN)
  • arxiv:

Domain Adaptation through Synthesis for Unsupervised Person Re-identification

Unsupervised Domain Adaptive Re-Identification: Theory and Practice

Deep Association Learning for Unsupervised Video Person Re-identification

Support Neighbor Loss for Person Re-Identification

Unsupervised Person Re-identification by Deep Learning Tracklet Association

Self-similarity Grouping: A Simple Unsupervised Cross Domain Adaptation Approach for Person Re-identification

Unsupervised Tracklet Person Re-Identification

Unsupervised Person Re-identification by Deep Asymmetric Metric Embedding

Unsupervised Person Re-identification by Soft Multilabel Learning

A Bottom-up Clustering Approach to Unsupervised Person Re-identification

A Novel Unsupervised Camera-aware Domain Adaptation Framework for Person Re-identification

Towards better Validity: Dispersion based Clustering for Unsupervised Person Re-identification

PAC-GAN: An Effective Pose Augmentation Scheme for Unsupervised Cross-View Person Re-identification

Adaptive Exploration for Unsupervised Person Re-Identification

Learning to Adapt Invariance in Memory for Person Re-identification

Consistent Cross-view Matching for Unsupervised Person Re-identification

Learning to Align Multi-Camera Domain for Unsupervised Video Person Re-Identification

Progressive Unsupervised Person Re-identification by Tracklet Association with Spatio-Temporal Regularization

Asymmetric Co-Teaching for Unsupervised Cross Domain Person Re-Identification

Memorizing Comprehensively to Learn Adaptively: Unsupervised Cross-Domain Person Re-ID with Multi-level Memory

Unsupervised Domain Adaptation in the Dissimilarity Space for Person Re-identification

Unsupervised Attention Based Instance Discriminative Learning for Person Re-Identification

Joint Generative and Contrastive Learning for Unsupervised Person Re-identification

Joint Noise-Tolerant Learning and Meta Camera Shift Adaptation for Unsupervised Person Re-Identification

Cluster Contrast for Unsupervised Person Re-Identification

Intra-Inter Camera Similarity for Unsupervised Person Re-Identification

Group-aware Label Transfer for Domain Adaptive Person Re-identification

Weakly Supervised Person Re-identification

Weakly Supervised Person Re-Identification

Weakly Supervised Person Re-identification: Cost-effective Learning with A New Benchmark

Weakly Supervised Tracklet Person Re-Identification by Deep Feature-wise Mutual Learning

Vehicle Re-ID

Learning Deep Neural Networks for Vehicle Re-ID with Visual-spatio-temporal Path Proposals

Viewpoint-Aware Attentive Multi-View Inference for Vehicle Re-Identification

RAM: A Region-Aware Deep Model for Vehicle Re-Identification

Vehicle Re-Identification in Context

Vehicle Re-identification Using Quadruple Directional Deep Learning Features

Coarse-to-fine: A RNN-based hierarchical attention model for vehicle re-identification

Vehicle Re-Identification: an Efficient Baseline Using Triplet Embedding

A Two-Stream Siamese Neural Network for Vehicle Re-Identification by Using Non-Overlapping Cameras

CityFlow: A City-Scale Benchmark for Multi-Target Multi-Camera Vehicle Tracking and Re-Identification

  • intro: Accepted for oral presentation at CVPR 2019 with review ratings of 2 strong accepts and 1 accept (work done during an internship at NVIDIA)
  • arxiv:

Vehicle Re-identification in Aerial Imagery: Dataset and Approach

Attributes Guided Feature Learning for Vehicle Re-identification

A unified neural network for object detection, multiple object tracking and vehicle re-identification

Part-Guided Attention Learning for Vehicle Re-Identification

Vehicle Re-identification with Viewpoint-aware Metric Learning

  • intro: ICCV 2019
  • intro: Beihang University & Tsinghua University & Megvii Technology
  • keywords: Viewpoint-Aware Network (VANet)
  • arxiv:

PAMTRI: Pose-Aware Multi-Task Learning for Vehicle Re-Identification Using Highly Randomized Synthetic Data

Stripe-based and Attribute-aware Network: A Two-Branch Deep Model for Vehicle Re-identification

Background Segmentation for Vehicle Re-Identification

Vehicle Re-ID Collection


DCDLearn: Multi-order Deep Cross-distance Learning for Vehicle Re-Identification

Parsing-based View-aware Embedding Network for Vehicle Re-Identification

Multi-Domain Learning and Identity Mining for Vehicle Re-Identification

VOC-ReID: Vehicle Re-identification based on Vehicle-Orientation-Camera

VehicleNet: Learning Robust Visual Representation for Vehicle Re-identification

Viewpoint-Aware Channel-Wise Attentive Network for Vehicle Re-Identification

Self-Supervised Visual Attention Learning for Vehicle Re-Identification

AttributeNet: Attribute Enhanced Vehicle Re-Identification

A Strong Baseline for Vehicle Re-Identification

Deep Metric Learning

Deep Metric Learning for Person Re-Identification

Deep Metric Learning for Practical Person Re-Identification

Constrained Deep Metric Learning for Person Re-identification

Embedding Deep Metric for Person Re-identication A Study Against Large Variations

DarkRank: Accelerating Deep Metric Learning via Cross Sample Similarities Transfer


Open-ReID: Open source person re-identification library in python

FastReID: A Pytorch Toolbox for Real-world Person Re-identification

light-reid: a toolbox of light reid for fast feature extraction and search






A PyTorch based strong baseline for person search




DukeMTMC-reID_baseline (Matlab)

Code for IDE baseline on Market-1501


1st Workshop on Target Re-Identification and Multi-Target Multi-Camera Tracking

Target Re-Identification and Multi-Target Multi-Camera Tracking


Re-id Resources

Person Re-Identification - Papers With Code

Awesome Person Re-Identification