# Text-to-Image Person Retrieval on RSTPReid (test)

Source: [Text-to-Image Person Retrieval on RSTPReid (test)](<https://www.sota2.com/research/sota/text-to-image-person-retrieval-on-rstpreid-test>)

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

Data updated: 2026-04-30T07:28:29.619Z

Evaluation of Text-to-Image Person Retrieval performance on the test split of the RSTPReid dataset, measured using Rank-1, Rank-5, Rank-10 accuracy, 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 | Text-to-Image Person Retrieval |
| Dataset (including any stated split) | RSTPReid (test) |
| Metric | Rank-1 Accuracy |
| Unit | PERCENT |
| Direction | Higher is better |
| Results loaded | 27 of 27 |
| 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 Accuracy](<https://www.sota2.com/research/sota/text-to-image-person-retrieval-on-rstpreid-test.md?metric=Rank-1%20Accuracy>): Higher is better; unit: PERCENT.

- [Rank-5 Accuracy](<https://www.sota2.com/research/sota/text-to-image-person-retrieval-on-rstpreid-test.md?metric=Rank-5%20Accuracy>): Higher is better; unit: PERCENT.

- [Rank-10 Accuracy](<https://www.sota2.com/research/sota/text-to-image-person-retrieval-on-rstpreid-test.md?metric=Rank-10%20Accuracy>): Higher is better; unit: PERCENT.

- [mAP](<https://www.sota2.com/research/sota/text-to-image-person-retrieval-on-rstpreid-test.md?metric=mAP>): Higher is better; unit: PERCENT.

- [mINP](<https://www.sota2.com/research/sota/text-to-image-person-retrieval-on-rstpreid-test.md?metric=mINP>): Higher is better; unit: PERCENT.

- [Retrieval Accuracy](<https://www.sota2.com/research/sota/text-to-image-person-retrieval-on-rstpreid-test.md?metric=Retrieval%20Accuracy>): Higher is better; unit: PERCENT.

## Recorded results

| Method | Rank-1 Accuracy | Result date | Report paper |
| --- | --- | --- | --- |
| CADA | 69.6 | Not recorded | 68fa71571e209131cea50ab8 |
| CADA | 61.5 | Not recorded | 68fa71571e209131cea50ab8 |
| IRRA | 60.2 | Not recorded | 68fa71571e209131cea50ab8 |
| Ours | 58.05 | Not recorded | 695c96f753fdd5c3617435ee |
| RDE | 54.9 | Not recorded | 695c96f753fdd5c3617435ee |
| IRRA | 53.25 | Not recorded | 695c96f753fdd5c3617435ee |
| CLIP | 52.55 | Not recorded | 695c96f753fdd5c3617435ee |
| Ours | 51.3 | Not recorded | 695c96f753fdd5c3617435ee |
| CFine | 50.55 | Not recorded | 68fa71571e209131cea50ab8 |
| RDE | 49.25 | Not recorded | 695c96f753fdd5c3617435ee |
| ACSA | 48.4 | Not recorded | 68fa71571e209131cea50ab8 |
| CLIP | 47.45 | Not recorded | 695c96f753fdd5c3617435ee |
| IVT | 46.7 | Not recorded | 68fa71571e209131cea50ab8 |
| LBUL | 45.55 | Not recorded | 68fa71571e209131cea50ab8 |
| IRRA | 45.3 | Not recorded | 695c96f753fdd5c3617435ee |
| SSAN | 43.5 | Not recorded | 68fa71571e209131cea50ab8 |
| DSSL | 39.05 | Not recorded | 68fa71571e209131cea50ab8 |

### CADA

Rank-1 Accuracy: 69.6. Result ID: 6991c68b3a6c3148490a83cf.

[Reporting paper](<https://www.sota2.com/research/paper/68fa71571e209131cea50ab8.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa71571e209131cea50ab8.md>)

Recorded evaluation configuration: {"Type":"Local-matching"}. This record does not assert independent reproduction.

### CADA

Rank-1 Accuracy: 61.5. Result ID: 6991c68b3a6c3148490a83ce.

[Reporting paper](<https://www.sota2.com/research/paper/68fa71571e209131cea50ab8.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa71571e209131cea50ab8.md>)

Recorded evaluation configuration: {"Type":"Global-matching"}. This record does not assert independent reproduction.

### IRRA

Rank-1 Accuracy: 60.2. Result ID: 6991c68b3a6c3148490a83cd.

[Reporting paper](<https://www.sota2.com/research/paper/68fa71571e209131cea50ab8.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6ecd1e209131cea423e9.md>)

[Implementation](<https://github.com/anosorae/IRRA>)

Recorded evaluation configuration: {"Type":"Global-matching"}. This record does not assert independent reproduction.

### Ours

Rank-1 Accuracy: 58.05. Result ID: 6997f0b65698665ec449ff9d.

[Reporting paper](<https://www.sota2.com/research/paper/695c96f753fdd5c3617435ee.md>)

[Method origin paper](<https://www.sota2.com/research/paper/695c96f753fdd5c3617435ee.md>)

Recorded evaluation configuration: {"Training Set":"CUHK-PEDES"}. This record does not assert independent reproduction.

### RDE

Rank-1 Accuracy: 54.9. Result ID: 6997f0b65698665ec449ff9c.

[Reporting paper](<https://www.sota2.com/research/paper/695c96f753fdd5c3617435ee.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa72ac1e209131cea57c03.md>)

[Implementation](<https://github.com/QinYang79/RDE>)

Recorded evaluation configuration: {"Training Set":"CUHK-PEDES"}. This record does not assert independent reproduction.

### IRRA

Rank-1 Accuracy: 53.25. Result ID: 6997f0b65698665ec449ff9b.

[Reporting paper](<https://www.sota2.com/research/paper/695c96f753fdd5c3617435ee.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6ecd1e209131cea423e9.md>)

[Implementation](<https://github.com/anosorae/IRRA>)

Recorded evaluation configuration: {"Training Set":"CUHK-PEDES"}. This record does not assert independent reproduction.

### CLIP

Rank-1 Accuracy: 52.55. Result ID: 6997f0b65698665ec449ff9a.

[Reporting paper](<https://www.sota2.com/research/paper/695c96f753fdd5c3617435ee.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa69581e209131cea21ad0.md>)

[Implementation](<https://github.com/OpenAI/CLIP>)

Recorded evaluation configuration: {"Training Set":"CUHK-PEDES"}. This record does not assert independent reproduction.

### Ours

Rank-1 Accuracy: 51.3. Result ID: 6997f0b65698665ec449ff95.

[Reporting paper](<https://www.sota2.com/research/paper/695c96f753fdd5c3617435ee.md>)

[Method origin paper](<https://www.sota2.com/research/paper/695c96f753fdd5c3617435ee.md>)

Recorded evaluation configuration: {"Training Set":"ICFG-PEDES"}. This record does not assert independent reproduction.

### CFine

Rank-1 Accuracy: 50.55. Result ID: 6991c68b3a6c3148490a83cc.

[Reporting paper](<https://www.sota2.com/research/paper/68fa71571e209131cea50ab8.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6daa1e209131cea3b477.md>)

Recorded evaluation configuration: {"Type":"Global-matching"}. This record does not assert independent reproduction.

### RDE

Rank-1 Accuracy: 49.25. Result ID: 6997f0b65698665ec449ff94.

[Reporting paper](<https://www.sota2.com/research/paper/695c96f753fdd5c3617435ee.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa72ac1e209131cea57c03.md>)

[Implementation](<https://github.com/QinYang79/RDE>)

Recorded evaluation configuration: {"Training Set":"ICFG-PEDES"}. This record does not assert independent reproduction.

### ACSA

Rank-1 Accuracy: 48.4. Result ID: 6991c68b3a6c3148490a83cb.

[Reporting paper](<https://www.sota2.com/research/paper/68fa71571e209131cea50ab8.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6e3e1e209131cea3e9df.md>)

Recorded evaluation configuration: {"Type":"Local-matching"}. This record does not assert independent reproduction.

### CLIP

Rank-1 Accuracy: 47.45. Result ID: 6997f0b65698665ec449ff93.

[Reporting paper](<https://www.sota2.com/research/paper/695c96f753fdd5c3617435ee.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa69581e209131cea21ad0.md>)

[Implementation](<https://github.com/OpenAI/CLIP>)

Recorded evaluation configuration: {"Training Set":"ICFG-PEDES"}. This record does not assert independent reproduction.

### IVT

Rank-1 Accuracy: 46.7. Result ID: 6991c68b3a6c3148490a83ca.

[Reporting paper](<https://www.sota2.com/research/paper/68fa71571e209131cea50ab8.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6d491e209131cea38c97.md>)

Recorded evaluation configuration: {"Type":"Global-matching"}. This record does not assert independent reproduction.

### LBUL

Rank-1 Accuracy: 45.55. Result ID: 6991c68b3a6c3148490a83c9.

[Reporting paper](<https://www.sota2.com/research/paper/68fa71571e209131cea50ab8.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6d661e209131cea39879.md>)

Recorded evaluation configuration: {"Type":"Local-matching"}. This record does not assert independent reproduction.

### IRRA

Rank-1 Accuracy: 45.3. Result ID: 6997f0b65698665ec449ff92.

[Reporting paper](<https://www.sota2.com/research/paper/695c96f753fdd5c3617435ee.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6ecd1e209131cea423e9.md>)

[Implementation](<https://github.com/anosorae/IRRA>)

Recorded evaluation configuration: {"Training Set":"ICFG-PEDES"}. This record does not assert independent reproduction.

### SSAN

Rank-1 Accuracy: 43.5. Result ID: 6991c68b3a6c3148490a83c8.

[Reporting paper](<https://www.sota2.com/research/paper/68fa71571e209131cea50ab8.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6a791e209131cea28668.md>)

[Implementation](<https://github.com/zifyloo/SSAN>)

Recorded evaluation configuration: {"Type":"Local-matching"}. This record does not assert independent reproduction.

### DSSL

Rank-1 Accuracy: 39.05. Result ID: 6991c68b3a6c3148490a83c7.

[Reporting paper](<https://www.sota2.com/research/paper/68fa71571e209131cea50ab8.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6ab41e209131cea29e6e.md>)

[Implementation](<https://github.com/NjtechCVLab/RSTPReid-Dataset>)

Recorded evaluation configuration: {"Type":"Local-matching"}. This record does not assert independent reproduction.

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