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 501–550 of 1488 papers

TitleStatusHype
Leveraging Virtual and Real Person for Unsupervised Person Re-identificationCode0
Deep Constrained Dominant Sets for Person Re-identificationCode0
Deep Co-attention based Comparators For Relative Representation Learning in Person Re-identificationCode0
Pyramidal Person Re-IDentification via Multi-Loss Dynamic TrainingCode0
Fast and Accurate Person Re-Identification with RMNetCode0
Learning Robust Visual-Semantic Embedding for Generalizable Person Re-identificationCode0
Deep Attention Aware Feature Learning for Person Re-IdentificationCode0
Unsupervised Cross-dataset Person Re-identification by Transfer Learning of Spatial-Temporal PatternsCode0
Deep Association Learning for Unsupervised Video Person Re-identificationCode0
Benchmarking person re-identification datasets and approaches for practical real-world implementationsCode0
Learning to Disentangle Scenes for Person Re-identificationCode0
Batch DropBlock Network for Person Re-identification and BeyondCode0
Learning from Synchronization: Self-Supervised Uncalibrated Multi-View Person Association in Challenging ScenesCode0
Learning Intra and Inter-Camera Invariance for Isolated Camera Supervised Person Re-identificationCode0
Additive Adversarial Learning for Unbiased AuthenticationCode0
DASK: Distribution Rehearsing via Adaptive Style Kernel Learning for Exemplar-Free Lifelong Person Re-IdentificationCode0
Learning Invariance from Generated Variance for Unsupervised Person Re-identificationCode0
Backbone Can Not be Trained at Once: Rolling Back to Pre-trained Network for Person Re-IdentificationCode0
Learning Deep Feature Representations with Domain Guided Dropout for Person Re-identificationCode0
Person Re-identification: Implicitly Defining the Receptive Fields of Deep Learning Classification FrameworksCode0
Learning Discriminative Features with Multiple Granularities for Person Re-IdentificationCode0
Frustratingly Easy Person Re-Identification: Generalizing Person Re-ID in PracticeCode0
LCM: Log Conformal Maps for Robust Representation Learning to Mitigate Perspective DistortionCode0
Cross-View Kernel Similarity Metric Learning Using Pairwise Constraints for Person Re-identificationCode0
Cross-view Asymmetric Metric Learning for Unsupervised Person Re-identificationCode0
Leaning Compact and Representative Features for Cross-Modality Person Re-IdentificationCode0
Learning Disentangled Representation for Robust Person Re-identificationCode0
Joint Progressive Knowledge Distillation and Unsupervised Domain AdaptationCode0
Jointly Attentive Spatial-Temporal Pooling Networks for Video-based Person Re-IdentificationCode0
Auto-ReID: Searching for a Part-aware ConvNet for Person Re-IdentificationCode0
Joint Detection and Identification Feature Learning for Person SearchCode0
Invisible Backdoor Attack with Dynamic Triggers against Person Re-identificationCode0
Knowledge Distillation for Multi-Target Domain Adaptation in Real-Time Person Re-IdentificationCode0
In Defense of the Triplet Loss for Person Re-IdentificationCode0
Interaction-and-Aggregation Network for Person Re-identificationCode0
In Defense of the Classification Loss for Person Re-IdentificationCode0
An Empirical Study of Person Re-Identification with AttributesCode0
In Defense of the Triplet Loss Again: Learning Robust Person Re-Identification with Fast Approximated Triplet Loss and Label DistillationCode0
Improved Person Re-Identification Based on Saliency and Semantic Parsing with Deep Neural Network ModelsCode0
BR-NPA: A Non-Parametric High-Resolution Attention Model to improve the Interpretability of AttentionCode0
Image-Image Domain Adaptation with Preserved Self-Similarity and Domain-Dissimilarity for Person Re-identificationCode0
Illumination Distillation Framework for Nighttime Person Re-Identification and A New BenchmarkCode0
GAF-Net: Video-Based Person Re-Identification via Appearance and Gait RecognitionsCode0
Improved Instance Discrimination and Feature Compactness for End-to-End Person SearchCode0
Incremental Learning in Person Re-IdentificationCode0
Invariance Matters: Exemplar Memory for Domain Adaptive Person Re-identificationCode0
IAUnet: Global Context-Aware Feature Learning for Person Re-IdentificationCode0
ID-aware Quality for Set-based Person Re-identificationCode0
Fusion for Visual-Infrared Person ReID in Real-World Surveillance Using Corrupted Multimodal DataCode0
HydraPlus-Net: Attentive Deep Features for Pedestrian AnalysisCode0
Show:102550
← PrevPage 11 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
10TransReID-SSL (ViT-B w/o 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
5RGT&RGPR (RK)mAP92.7—Unverified
6st-ReID(RE, RK,Cam)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