SOTAVerified

Person Re-Identification

Person Re-Identification is a computer vision task in which the goal is to match a person's identity across different cameras or locations in a video or image sequence. It involves detecting and tracking a person and then using features such as appearance, body shape, and clothing to match their identity in different frames. The goal is to associate the same person across multiple non-overlapping camera views in a robust and efficient manner.

Papers

Recently AddedMost HypedMost ActiveNeeds VerificationMost Verified

Showing 1–50 of 1488 papers

TitleStatusHype
Deep Residual Learning for Image RecognitionCode4
Beyond Appearance: a Semantic Controllable Self-Supervised Learning Framework for Human-Centric Visual TasksCode3
Keypoint Promptable Re-IdentificationCode3
Cross-video Identity Correlating for Person Re-identification Pre-trainingCode2
Multi-Memory Matching for Unsupervised Visible-Infrared Person Re-IdentificationCode2
Instruct-ReID++: Towards Universal Purpose Instruction-Guided Person Re-identificationCode2
Semi-Supervised Domain Generalizable Person Re-IdentificationCode2
Large-Scale Pre-training for Person Re-identification with Noisy LabelsCode2
Random Erasing Data AugmentationCode2
View-decoupled Transformer for Person Re-identification under Aerial-ground Camera NetworkCode2
A Versatile Framework for Multi-scene Person Re-identificationCode2
Person Re-IdentificationCode2
A Strong Baseline and Batch Normalization Neck for Deep Person Re-identificationCode2
FastReID: A Pytorch Toolbox for General Instance Re-identificationCode2
From Poses to Identity: Training-Free Person Re-Identification via Feature CentralizationCode2
Exploring Color Invariance through Image-Level Ensemble LearningCode2
Joint Discriminative and Generative Learning for Person Re-identificationCode2
A Simple Framework for Contrastive Learning of Visual RepresentationsCode2
Pose-Normalized Image Generation for Person Re-identificationCode2
Learning Commonality, Divergence and Variety for Unsupervised Visible-Infrared Person Re-identificationCode2
Building Computationally Efficient and Well-Generalizing Person Re-Identification Models with Metric LearningCode2
The Balanced-Pairwise-Affinities Feature TransformCode2
Body Part-Based Representation Learning for Occluded Person Re-IdentificationCode2
Guided Saliency Feature Learning for Person Re-identification in Crowded ScenesCode2
CLIP-ReID: Exploiting Vision-Language Model for Image Re-Identification without Concrete Text LabelsCode2
Bag of Tricks and A Strong Baseline for Deep Person Re-identificationCode2
LLaVA-ReID: Selective Multi-image Questioner for Interactive Person Re-IdentificationCode2
ReID5o: Achieving Omni Multi-modal Person Re-identification in a Single ModelCode2
Harnessing the Power of MLLMs for Transferable Text-to-Image Person ReIDCode2
FD-GAN: Pose-guided Feature Distilling GAN for Robust Person Re-identificationCode2
Adaptive L2 Regularization in Person Re-IdentificationCode1
A Benchmark of Video-Based Clothes-Changing Person Re-IdentificationCode1
Anchor-Free Person SearchCode1
Cloth-Changing Person Re-identification from A Single Image with Gait Prediction and RegularizationCode1
Eliminate Deviation with Deviation for Data Augmentation and a General Multi-modal Data Learning MethodCode1
Clothes-Changing Person Re-identification with RGB Modality OnlyCode1
Cluster Contrast for Unsupervised Person Re-IdentificationCode1
CLIP-Driven Semantic Discovery Network for Visible-Infrared Person Re-IdentificationCode1
CLIP-Driven Fine-grained Text-Image Person Re-identificationCode1
CHIRLA: Comprehensive High-resolution Identification and Re-identification for Large-scale AnalysisCode1
Camera-aware Proxies for Unsupervised Person Re-IdentificationCode1
Circle Loss: A Unified Perspective of Pair Similarity OptimizationCode1
Cloning Outfits from Real-World Images to 3D Characters for Generalizable Person Re-IdentificationCode1
Cluster-level Feature Alignment for Person Re-identificationCode1
Bridging the Gap: Multi-Level Cross-Modality Joint Alignment for Visible-Infrared Person Re-IdentificationCode1
Bootstrap your own latent: A new approach to self-supervised LearningCode1
2nd Place Solution to Google Landmark Retrieval 2021Code1
Camera-aware Label Refinement for Unsupervised Person Re-identificationCode1
Camera-Conditioned Stable Feature Generation for Isolated Camera Supervised Person Re-IDentificationCode1
Bridging the Source-to-target Gap for Cross-domain Person Re-Identification with Intermediate DomainsCode1
Show:102550
← PrevPage 1 of 30Next →
All datasetsMarket-1501DukeMTMC-reIDMSMT17Occluded-DukeMTMCMarket-1501-CCUHK03 detectedCUHK03 labeledMARSCUHK03LTCCPRCCPRID2011

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1st-ReID(RE, RK)Rank-198—Unverified
2SSKD(GH)Rank-197.36—Unverified
3CLIP-ReID+Pose2ID (no RK)Rank-197.3—Unverified
4SOLIDER +UFFM+AMCRank-197—Unverified
5Unsupervised Pre-training (ResNet101+MGN)Rank-197—Unverified
6RGT&RGPR (RK)Rank-196.9—Unverified
7SOLIDERRank-196.9—Unverified
8LightMBN (RR)Rank-196.8—Unverified
9Viewpoint-Aware Loss(RK)Rank-196.79—Unverified
10SOLIDER (RK)Rank-196.7—Unverified
#ModelMetricClaimedVerifiedStatus
1DenseILmAP97.1—Unverified
2CTL Model (ResNet50, 256x128)mAP96.1—Unverified
3BPBreID (RK)mAP92.9—Unverified
4Unsupervised Pre-training (ResNet101+RK)mAP92.77—Unverified
5st-ReID(RE, RK,Cam)mAP92.7—Unverified
6RGT&RGPR (RK)mAP92.7—Unverified
7Viewpoint-Aware Loss(RK)mAP91.8—Unverified
8LDS (ResNet50 + RK)mAP91—Unverified
9Adaptive L2 Regularization (with re-ranking)mAP90.7—Unverified
10FlipReID (with re-ranking)mAP90.7—Unverified