# Person Re-identification on P-DukeMTMC-reID standard (test)

Source: [Person Re-identification on P-DukeMTMC-reID standard (test)](<https://www.sota2.com/research/sota/person-re-identification-on-p-dukemtmc-reid-standard-test>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2026-02-26T06:00:59.752Z

Evaluation of Person Re-identification performance on the specific 'standard (test)' split of the P-DukeMTMC-reID dataset, typically measured using Rank-1, Rank-5, Rank-10, and mAP.

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

| Scope | Recorded value |
| --- | --- |
| Task | Person Re-identification |
| Dataset (including any stated split) | P-DukeMTMC-reID standard (test) |
| Metric | Rank-1 |
| Unit | PERCENT |
| Direction | Higher is better |
| Results loaded | 9 of 9 |
| Coverage | All results currently returned for this benchmark |

Evaluation settings may differ between results. The original papers and recorded configurations are needed to establish comparability. A shared metric name alone does not establish an identical protocol.

## Metrics

- [Rank-1](<https://www.sota2.com/research/sota/person-re-identification-on-p-dukemtmc-reid-standard-test.md?metric=Rank-1>): Higher is better; unit: PERCENT.

- [Rank-5](<https://www.sota2.com/research/sota/person-re-identification-on-p-dukemtmc-reid-standard-test.md?metric=Rank-5>): Higher is better; unit: PERCENT.

- [Rank-10](<https://www.sota2.com/research/sota/person-re-identification-on-p-dukemtmc-reid-standard-test.md?metric=Rank-10>): Higher is better; unit: PERCENT.

- [mAP](<https://www.sota2.com/research/sota/person-re-identification-on-p-dukemtmc-reid-standard-test.md?metric=mAP>): Higher is better; unit: PERCENT.

## Recorded results

| Method | Rank-1 | Result date | Report paper |
| --- | --- | --- | --- |
| MHSA-Net\* | 70.7 | Not recorded | 68fa6c5a1e209131cea33856 |
| MHSA-Net | 69.6 | Not recorded | 68fa6c5a1e209131cea33856 |
| MHSA-Net^- | 67.9 | Not recorded | 68fa6c5a1e209131cea33856 |
| Baseline | 61 | Not recorded | 68fa6c5a1e209131cea33856 |
| PVPM+Aug | 51.5 | Not recorded | 68fa6c5a1e209131cea33856 |
| PGFA | 44.2 | Not recorded | 68fa6c5a1e209131cea33856 |
| PCB | 43.6 | Not recorded | 68fa6c5a1e209131cea33856 |
| PCB+RPP | 40.4 | Not recorded | 68fa6c5a1e209131cea33856 |
| OSNet | 33.7 | Not recorded | 68fa6c5a1e209131cea33856 |

### MHSA-Net\*

Rank-1: 70.7. Result ID: 698f09703a6c314849f5236b.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6c5a1e209131cea33856.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6c5a1e209131cea33856.md>)

Recorded evaluation configuration: {"K":8,"Local feature selection":"only use the key local feature p\*(x) from MHSAB+ACM"}. This record does not assert independent reproduction.

### MHSA-Net

Rank-1: 69.6. Result ID: 698f09703a6c314849f5236d.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6c5a1e209131cea33856.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6c5a1e209131cea33856.md>)

Recorded evaluation configuration: {"K":8}. This record does not assert independent reproduction.

### MHSA-Net^-

Rank-1: 67.9. Result ID: 698f09703a6c314849f5236c.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6c5a1e209131cea33856.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6c5a1e209131cea33856.md>)

Recorded evaluation configuration: {"K":8,"Training loss configuration":"drop the LCE in the training process"}. This record does not assert independent reproduction.

### Baseline

Rank-1: 61. Result ID: 698f09703a6c314849f5236a.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6c5a1e209131cea33856.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6c5a1e209131cea33856.md>)

Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction.

### PVPM+Aug

Rank-1: 51.5. Result ID: 698f09703a6c314849f52369.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6c5a1e209131cea33856.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa67551e209131cea15950.md>)

Recorded evaluation configuration: {"Data augmentation":"true"}. This record does not assert independent reproduction.

### PGFA

Rank-1: 44.2. Result ID: 698f09703a6c314849f52368.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6c5a1e209131cea33856.md>)

Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction.

### PCB

Rank-1: 43.6. Result ID: 698f09703a6c314849f52367.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6c5a1e209131cea33856.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa63ec1e209131cea017e9.md>)

Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction.

### PCB+RPP

Rank-1: 40.4. Result ID: 698f09703a6c314849f52366.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6c5a1e209131cea33856.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa63ec1e209131cea017e9.md>)

Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction.

### OSNet

Rank-1: 33.7. Result ID: 698f09703a6c314849f52365.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6c5a1e209131cea33856.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa69d81e209131cea248e6.md>)

[Implementation](<https://github.com/KaiyangZhou/deep-person-reid>)

Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction.

Page 1 of 1. This is an index page, not the full collection.
