| TransReID: Transformer-based Object Re-Identification | ✓ Link | 53.19 | 27.38 | 1.98 | | | | TransReID | 2021-02-08 |
| Devil in the Details: Towards Accurate Single and Multiple Human Parsing | ✓ Link | 42.92 | 18.24 | 0.67 | | | | CaceNet | 2018-09-17 |
| Learning Diverse Features with Part-Level Resolution for Person Re-Identification | ✓ Link | 37.56 | 14.23 | 0.48 | | | | PLR-OS | 2020-01-21 |
| Relation Network for Person Re-identification | ✓ Link | 36.57 | 14.23 | 0.48 | | | | RRID | 2019-11-21 |
| Pyramidal Person Re-IDentification via Multi-Loss Dynamic Training | ✓ Link | 35.72 | 12.75 | 0.36 | | | | Pyramid | 2018-10-29 |
| Beyond Part Models: Person Retrieval with Refined Part Pooling (and a Strong Convolutional Baseline) | ✓ Link | 34.93 | 12.72 | 0.41 | | | | PCB | 2017-11-26 |
| FastReID: A Pytorch Toolbox for General Instance Re-identification | ✓ Link | 34.13 | 11.54 | 0.29 | | | | SBS (ResNet-50) | 2020-06-04 |
| Batch DropBlock Network for Person Re-identification and Beyond | ✓ Link | 33.79 | 10.95 | 0.32 | | | | BDB | 2018-11-17 |
| Mixed High-Order Attention Network for Person Re-Identification | ✓ Link | 33.29 | 10.69 | 0.38 | | | | MHN | 2019-08-16 |
| Deep Learning for Person Re-identification: A Survey and Outlook | ✓ Link | 31.90 | 12.13 | 0.35 | | | | AGW (ResNet-50) | 2020-01-13 |
| Joint Discriminative and Generative Learning for Person Re-identification | ✓ Link | 31.75 | 9.96 | 0.35 | | | | DG-Net | 2019-04-15 |
| Perceive Where to Focus: Learning Visibility-aware Part-level Features for Partial Person Re-identification | ✓ Link | 31.17 | 10.15 | 0.31 | | | | VPM | 2019-04-01 |
| AlignedReID: Surpassing Human-Level Performance in Person Re-Identification | ✓ Link | 31.00 | 10.95 | 0.32 | | | | Aligned++ | 2017-11-22 |
| Omni-Scale Feature Learning for Person Re-Identification | ✓ Link | 30.94 | 10.37 | 0.23 | | | | OS-Net | 2019-05-02 |
| ABD-Net: Attentive but Diverse Person Re-Identification | ✓ Link | 29.65 | 9.81 | 0.26 | | | | ABD-Net | 2019-08-03 |
| Learning Discriminative Features with Multiple Granularities for Person Re-Identification | ✓ Link | 29.56 | 9.72 | 0.29 | | | | MGN | 2018-04-04 |
| A Person Re-identification Data Augmentation Method with Adversarial Defense Effect | ✓ Link | 29.35 | 9.08 | 0.23 | | | | F-LGPR | 2021-01-21 |
| Top-DB-Net: Top DropBlock for Activation Enhancement in Person Re-Identification | ✓ Link | 28.56 | 8.90 | 0.20 | | | | TDB | 2020-10-12 |
| A Person Re-identification Data Augmentation Method with Adversarial Defense Effect | ✓ Link | 27.72 | 8.26 | 0.24 | | | | LGPR | 2021-01-21 |
| Bag of Tricks and A Strong Baseline for Deep Person Re-identification | ✓ Link | 27.05 | 8.42 | 0.20 | | | | BoT (ResNet-50) | 2019-03-17 |
| Benchmarks for Corruption Invariant Person Re-identification | ✓ Link | | | | 55.57 | 28.03 | 1.76 | CIL (ResNet-50) | 2021-11-01 |
| Unsupervised Pre-training for Person Re-identification | ✓ Link | | | | 32.22 | 10.37 | 0.29 | LUPerson | 2020-12-07 |