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 1151–1200 of 1488 papers

TitleStatusHype
Attribute-Aware Attention Model for Fine-grained Representation LearningCode0
EANet: Enhancing Alignment for Cross-Domain Person Re-identificationCode0
Spatial and Temporal Mutual Promotion for Video-based Person Re-identificationCode0
3D PersonVLAD: Learning Deep Global Representations for Video-based Person Re-identification—0
EgoReID Dataset: Person Re-identification in Videos Acquired by Mobile Devices with First-Person Point-of-View—0
A Deep Four-Stream Siamese Convolutional Neural Network with Joint Verification and Identification Loss for Person Re-detection—0
Cluster Loss for Person Re-Identification—0
Densely Semantically Aligned Person Re-Identification—0
Learning Incremental Triplet Margin for Person Re-identification—0
Deep Active Learning for Video-based Person Re-identification—0
Omni-directional Feature Learning for Person Re-identification—0
Spatial-Temporal Person Re-identificationCode0
Optimizing speed/accuracy trade-off for person re-identification via knowledge distillation—0
Fast and Accurate Person Re-Identification with RMNetCode0
Dissecting Person Re-identification from the Viewpoint of ViewpointCode0
Accelerating Large Scale Knowledge Distillation via Dynamic Importance Sampling—0
Parameter-Free Spatial Attention Network for Person Re-IdentificationCode0
Spectral Feature Transformation for Person Re-identificationCode0
Identity Preserving Generative Adversarial Network for Cross-Domain Person Re-identification—0
Similarity-preserving Image-image Domain Adaptation for Person Re-identification—0
Self-similarity Grouping: A Simple Unsupervised Cross Domain Adaptation Approach for Person Re-identificationCode0
Adaptive Re-ranking of Deep Feature for Person Re-identification—0
Sequence-based Person Attribute Recognition with Joint CTC-Attention Model—0
Factorized Distillation: Training Holistic Person Re-identification Model by Distilling an Ensemble of Partial ReID Models—0
Multi-scale 3D Convolution Network for Video Based Person Re-Identification—0
Re-Identification with Consistent Attentive Siamese Networks—0
CA3Net: Contextual-Attentional Attribute-Appearance Network for Person Re-Identification—0
iQIYI-VID: A Large Dataset for Multi-modal Person Identification—0
Batch DropBlock Network for Person Re-identification and BeyondCode0
CAN: Composite Appearance Network for Person Tracking and How to Model Errors in a Tracking System—0
Multiple People Tracking Using Hierarchical Deep Tracklet Re-identification—0
STA: Spatial-Temporal Attention for Large-Scale Video-based Person Re-Identification—0
M2M-GAN: Many-to-Many Generative Adversarial Transfer Learning for Person Re-Identification—0
Hide-and-Seek: A Data Augmentation Technique for Weakly-Supervised Localization and BeyondCode0
Leveraging Virtual and Real Person for Unsupervised Person Re-identificationCode0
Query Adaptive Late Fusion for Image Retrieval—0
Pyramidal Person Re-IDentification via Multi-Loss Dynamic TrainingCode0
Cross-Modal Distillation for RGB-Depth Person Re-Identification—0
Video-based Person Re-identification Using Spatial-Temporal Attention NetworksCode0
Cross-Resolution Person Re-identification with Deep Antithetical Learning—0
Deep Person Re-identification for Probabilistic Data Association in Multiple Pedestrian Tracking—0
Recognizing Partial Biometric PatternsCode0
SCPNet: Spatial-Channel Parallelism Network for Joint Holistic and Partial Person Re-Identification—0
Attention Driven Person Re-identification—0
Image-to-Video Person Re-Identification by Reusing Cross-modal Embeddings—0
Random Occlusion-recovery for Person Re-identification—0
Self Attention Grid for Person Re-IdentificationCode0
Devil in the Details: Towards Accurate Single and Multiple Human ParsingCode0
In Defense of the Classification Loss for Person Re-IdentificationCode0
Sparse Label Smoothing Regularization for Person Re-IdentificationCode0
Show:102550
← PrevPage 24 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