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 1251–1300 of 1488 papers

TitleStatusHype
Beyond Domain Gap: Exploiting Subjectivity in Sketch-Based Person RetrievalCode0
Pseudo Labels Refinement with Intra-camera Similarity for Unsupervised Person Re-identificationCode0
Benchmarking person re-identification datasets and approaches for practical real-world implementationsCode0
MagnifierNet: Towards Semantic Adversary and Fusion for Person Re-identificationCode0
Look Closer to Your Enemy: Learning to Attack via Teacher-Student MimickingCode0
Person Re-identification: Implicitly Defining the Receptive Fields of Deep Learning Classification FrameworksCode0
Batch DropBlock Network for Person Re-identification and BeyondCode0
Leveraging Virtual and Real Person for Unsupervised Person Re-identificationCode0
Pyramidal Transformer with Conv-Patchify for Person Re-identificationCode0
Multi-Attribute Enhancement Network for Person SearchCode0
Triplet-based Deep Similarity Learning for Person Re-IdentificationCode0
Erasing, Transforming, and Noising Defense Network for Occluded Person Re-IdentificationCode0
Quality Aware Network for Set to Set RecognitionCode0
Adaptive Graph Representation Learning for Video Person Re-identificationCode0
Learning Transferable Pedestrian Representation from Multimodal Information SupervisionCode0
Learning to Disentangle Scenes for Person Re-identificationCode0
Spectral Enhancement and Pseudo-Anchor Guidance for Infrared-Visible Person Re-IdentificationCode0
Spectral Feature Transformation for Person Re-identificationCode0
Enhancing Person Re-identification in a Self-trained SubspaceCode0
Triplet Permutation Method for Deep Learning of Single-Shot Person Re-IdentificationCode0
Multi-granularity for knowledge distillationCode0
SphereReID: Deep Hypersphere Manifold Embedding for Person Re-IdentificationCode0
Ranking Aggregation with Interactive Feedback for Collaborative Person Re-identificationCode0
Ranking and Classification driven Feature Learning for Person Re_identificationCode0
End-to-End Deep Kronecker-Product Matching for Person Re-identificationCode0
Spindle Net: Person Re-Identification With Human Body Region Guided Feature Decomposition and FusionCode0
Learning Robust Visual-Semantic Embedding for Generalizable Person Re-identificationCode0
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
Try Harder: Hard Sample Generation and Learning for Clothes-Changing Person Re-IDCode0
READ: Reciprocal Attention Discriminator for Image-to-Video Re-IdentificationCode0
Learning Intra and Inter-Camera Invariance for Isolated Camera Supervised Person Re-identificationCode0
Video-based Person Re-identification with Accumulative Motion ContextCode0
Real-time Multiple People Tracking with Deeply Learned Candidate Selection and Person Re-IdentificationCode0
Unsupervised Person Re-identification: Clustering and Fine-tuningCode0
Backbone Can Not be Trained at Once: Rolling Back to Pre-trained Network for Person Re-IdentificationCode0
Leveraging Ensembles and Self-Supervised Learning for Fully-Unsupervised Person Re-Identification and Text Authorship AttributionCode0
Auto-ReID: Searching for a Part-aware ConvNet for Person Re-IdentificationCode0
Cross-View Kernel Similarity Metric Learning Using Pairwise Constraints for Person Re-identificationCode0
Multiregion Bilinear Convolutional Neural Networks for Person Re-IdentificationCode0
Recognizing Partial Biometric PatternsCode0
Understanding Humans in Crowded Scenes: Deep Nested Adversarial Learning and A New Benchmark for Multi-Human ParsingCode0
Attribute De-biased Vision Transformer (AD-ViT) for Long-Term Person Re-identificationCode0
Cross-view Asymmetric Metric Learning for Unsupervised Person Re-identificationCode0
Aggregating Deep Pyramidal Representations for Person Re-IdenfiticationCode0
Effective Dual-Region Augmentation for Reduced Reliance on Large Amounts of Labeled DataCode0
Style Interleaved Learning for Generalizable Person Re-identificationCode0
Learning from Synchronization: Self-Supervised Uncalibrated Multi-View Person Association in Challenging ScenesCode0
Cross-dataset Person Re-Identification Using Similarity Preserved Generative Adversarial NetworksCode0
Style Variable and Irrelevant Learning for Generalizable Person Re-identificationCode0
Show:102550
← PrevPage 26 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