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 1001–1050 of 1488 papers

TitleStatusHype
Beyond Universal Person Re-ID Attack—0
Hierarchical Clustering with Hard-batch Triplet Loss for Person Re-identification—0
Multi-Resolution Overlapping Stripes Network for Person Re-Identification—0
Learning Disentangled Representation for Robust Person Re-identificationCode0
Attend to the Difference: Cross-Modality Person Re-identification via Contrastive Correlation—0
Progressive Unsupervised Person Re-identification by Tracklet Association with Spatio-Temporal RegularizationCode0
An End-to-End Foreground-Aware Network for Person Re-Identification—0
Beyond Human Parts: Dual Part-Aligned Representations for Person Re-IdentificationCode0
Hetero-Center Loss for Cross-Modality Person Re-Identification—0
Video Person Re-Identification using Learned Clip Similarity Aggregation—0
Compact Network Training for Person ReID—0
RGB-Infrared Cross-Modality Person Re-Identification via Joint Pixel and Feature AlignmentCode0
CHD:Consecutive Horizontal Dropout for Human Gait Feature Extraction—0
Augmented Hard Example Mining for Generalizable Person Re-Identification—0
Multiple Kernel Fisher Discriminant Metric Learning for Person Re-identification—0
View Confusion Feature Learning for Person Re-identification—0
A Semi-Supervised Maximum Margin Metric Learning Approach for Small Scale Person Re-identification—0
Improved Res2Net model for Person re-identification—0
GetNet: Get Target Area for Image Pairing—0
Improving One-shot NAS by Suppressing the Posterior Fading—0
Unsupervised Person Re-Identification by Camera-Aware Similarity Consistency Learning—0
Instance-Guided Context Rendering for Cross-Domain Person Re-Identification—0
Self-Critical Attention Learning for Person Re-Identification—0
Pose-Guided Feature Alignment for Occluded Person Re-IdentificationCode0
Second-Order Non-Local Attention Networks for Person Re-Identification—0
Discriminative Feature Learning With Consistent Attention Regularization for Person Re-Identification—0
Unsupervised Graph Association for Person Re-IdentificationCode0
Deep Meta Metric LearningCode0
Deep Reinforcement Active Learning for Human-in-the-Loop Person Re-Identification—0
AlignedReID++: Dynamically matching local information for person re-identificationCode0
MVP Matching: A Maximum-Value Perfect Matching for Mining Hard Samples, With Application to Person Re-IdentificationCode0
Learning to Align Multi-Camera Domains using Part-Aware Clustering for Unsupervised Video Person Re-Identification—0
Video-Based Convolutional Attention for Person Re-Identification—0
Cross-View Kernel Similarity Metric Learning Using Pairwise Constraints for Person Re-identificationCode0
Unsupervised Few Shot Learning via Self-supervised Training—0
Single Camera Training for Person Re-identificationCode0
Cross-Dataset Person Re-Identification via Unsupervised Pose Disentanglement and Adaptation—0
Re-ID Driven Localization Refinement for Person Search—0
Running Event Visualization using Videos from Multiple Cameras—0
Adaptive Graph Representation Learning for Video Person Re-identificationCode0
Energy Clustering for Unsupervised Person Re-identification—0
Second-order Non-local Attention Networks for Person Re-identification—0
Push for Center Learning via Orthogonalization and Subspace Masking for Person Re-Identification—0
Segmentation Mask Guided End-to-End Person SearchCode0
Exploiting Global Camera Network Constraints for Unsupervised Video Person Re-identification—0
Intra-Camera Supervised Person Re-Identification: A New Benchmark—0
Global-Local Temporal Representations For Video Person Re-Identification—0
Unsupervised Domain-Adaptive Person Re-identification Based on Attributes—0
Learning adaptively from the unknown for few-example video person re-ID—0
advPattern: Physical-World Attacks on Deep Person Re-Identification via Adversarially Transformable PatternsCode0
Show:102550
← PrevPage 21 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