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

Showing 501525 of 1488 papers

TitleStatusHype
Deep Co-attention based Comparators For Relative Representation Learning in Person Re-identificationCode0
Pyramidal Person Re-IDentification via Multi-Loss Dynamic TrainingCode0
Deep Attention Aware Feature Learning for Person Re-IdentificationCode0
Deep Association Learning for Unsupervised Video Person Re-identificationCode0
Fast and Accurate Person Re-Identification with RMNetCode0
Benchmarking person re-identification datasets and approaches for practical real-world implementationsCode0
Joint Progressive Knowledge Distillation and Unsupervised Domain AdaptationCode0
Knowledge Distillation for Multi-Target Domain Adaptation in Real-Time Person Re-IdentificationCode0
Learning Disentangled Representation for Robust Person Re-identificationCode0
Joint Detection and Identification Feature Learning for Person SearchCode0
Batch DropBlock Network for Person Re-identification and BeyondCode0
Invisible Backdoor Attack with Dynamic Triggers against Person Re-identificationCode0
Additive Adversarial Learning for Unbiased AuthenticationCode0
DASK: Distribution Rehearsing via Adaptive Style Kernel Learning for Exemplar-Free Lifelong Person Re-IdentificationCode0
Interaction-and-Aggregation Network for Person Re-identificationCode0
Invariance Matters: Exemplar Memory for Domain Adaptive Person Re-identificationCode0
In Defense of the Classification Loss for Person Re-IdentificationCode0
Backbone Can Not be Trained at Once: Rolling Back to Pre-trained Network for Person Re-IdentificationCode0
In Defense of the Triplet Loss Again: Learning Robust Person Re-Identification with Fast Approximated Triplet Loss and Label DistillationCode0
Person Re-identification: Implicitly Defining the Receptive Fields of Deep Learning Classification FrameworksCode0
Incremental Learning in Person Re-IdentificationCode0
In Defense of the Triplet Loss for Person Re-IdentificationCode0
Frustratingly Easy Person Re-Identification: Generalizing Person Re-ID in PracticeCode0
BR-NPA: A Non-Parametric High-Resolution Attention Model to improve the Interpretability of AttentionCode0
Cross-View Kernel Similarity Metric Learning Using Pairwise Constraints for Person Re-identificationCode0
Show:102550
← PrevPage 21 of 60Next →

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1st-ReID(RE, RK)Rank-198Unverified
2SSKD(GH)Rank-197.36Unverified
3CLIP-ReID+Pose2ID (no RK)Rank-197.3Unverified
4SOLIDER +UFFM+AMCRank-197Unverified
5Unsupervised Pre-training (ResNet101+MGN)Rank-197Unverified
6RGT&RGPR (RK)Rank-196.9Unverified
7SOLIDERRank-196.9Unverified
8LightMBN (RR)Rank-196.8Unverified
9Viewpoint-Aware Loss(RK)Rank-196.79Unverified
10TransReID-SSL (ViT-B w/o RK)Rank-196.7Unverified
#ModelMetricClaimedVerifiedStatus
1DenseILmAP97.1Unverified
2CTL Model (ResNet50, 256x128)mAP96.1Unverified
3BPBreID (RK)mAP92.9Unverified
4Unsupervised Pre-training (ResNet101+RK)mAP92.77Unverified
5RGT&RGPR (RK)mAP92.7Unverified
6st-ReID(RE, RK,Cam)mAP92.7Unverified
7Viewpoint-Aware Loss(RK)mAP91.8Unverified
8LDS (ResNet50 + RK)mAP91Unverified
9Adaptive L2 Regularization (with re-ranking)mAP90.7Unverified
10FlipReID (with re-ranking)mAP90.7Unverified