# Infrared-to-Real Person Re-identification on ICFG-PEDES (test)

Source: [Infrared-to-Real Person Re-identification on ICFG-PEDES (test)](<https://www.sota2.com/research/sota/infrared-to-real-person-re-identification-on-icfg-pedes-test>)

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

Data updated: 2026-02-26T06:01:01.853Z

Evaluation of Infrared-to-Real Person Re-identification performance on the test split of the ICFG-PEDES dataset, measured using Rank-based metrics (R1, R5, R10), mAP, mINP, and Avg. 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 | Infrared-to-Real Person Re-identification |
| Dataset (including any stated split) | ICFG-PEDES (test) |
| Metric | Rank-1 (R1) |
| Unit | PERCENT |
| Direction | Higher is better |
| Results loaded | 6 of 6 |
| 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 (R1)](<https://www.sota2.com/research/sota/infrared-to-real-person-re-identification-on-icfg-pedes-test.md?metric=Rank-1%20(R1)>): Higher is better; unit: PERCENT.

- [Rank-5 (R5)](<https://www.sota2.com/research/sota/infrared-to-real-person-re-identification-on-icfg-pedes-test.md?metric=Rank-5%20(R5)>): Higher is better; unit: PERCENT.

- [Rank-10 (R10)](<https://www.sota2.com/research/sota/infrared-to-real-person-re-identification-on-icfg-pedes-test.md?metric=Rank-10%20(R10)>): Higher is better; unit: PERCENT.

- [mAP](<https://www.sota2.com/research/sota/infrared-to-real-person-re-identification-on-icfg-pedes-test.md?metric=mAP>): Higher is better; unit: PERCENT.

- [mINP](<https://www.sota2.com/research/sota/infrared-to-real-person-re-identification-on-icfg-pedes-test.md?metric=mINP>): Higher is better; unit: PERCENT.

- [Avg. mAP](<https://www.sota2.com/research/sota/infrared-to-real-person-re-identification-on-icfg-pedes-test.md?metric=Avg.%20mAP>): Higher is better; unit: PERCENT.

## Recorded results

| Method | Rank-1 (R1) | Result date | Report paper |
| --- | --- | --- | --- |
| MLLMEmbed-ReID | 88.95 | Not recorded | 6992a4769ebc499c97406bf4 |
| MLLMEmbed-ReID | 86.77 | Not recorded | 6992a4769ebc499c97406bf4 |
| MLLMEmbed-ReID | 82.81 | Not recorded | 6992a4769ebc499c97406bf4 |
| FlexiReID | 82.03 | Not recorded | 6992a4769ebc499c97406bf4 |
| SDCL | 81.36 | Not recorded | 6992a4769ebc499c97406bf4 |
| GUR | 80.31 | Not recorded | 6992a4769ebc499c97406bf4 |

### MLLMEmbed-ReID

Rank-1 (R1): 88.95. Result ID: 699a60085698665ec4e7fe7c.

[Reporting paper](<https://www.sota2.com/research/paper/6992a4769ebc499c97406bf4.md>)

[Method origin paper](<https://www.sota2.com/research/paper/6992a4769ebc499c97406bf4.md>)

Recorded evaluation configuration: {"Query-Gallery feature type (C2C/E2E/E2C)":"E2E"}. This record does not assert independent reproduction.

### MLLMEmbed-ReID

Rank-1 (R1): 86.77. Result ID: 699a60085698665ec4e7fe7b.

[Reporting paper](<https://www.sota2.com/research/paper/6992a4769ebc499c97406bf4.md>)

[Method origin paper](<https://www.sota2.com/research/paper/6992a4769ebc499c97406bf4.md>)

Recorded evaluation configuration: {"Query-Gallery feature type (C2C/E2C/E2E)":"C2C"}. This record does not assert independent reproduction.

### MLLMEmbed-ReID

Rank-1 (R1): 82.81. Result ID: 699a60085698665ec4e7fe7d.

[Reporting paper](<https://www.sota2.com/research/paper/6992a4769ebc499c97406bf4.md>)

[Method origin paper](<https://www.sota2.com/research/paper/6992a4769ebc499c97406bf4.md>)

Recorded evaluation configuration: {"Query-Gallery feature type (C2C/E2E/E2C)":"E2C"}. This record does not assert independent reproduction.

### FlexiReID

Rank-1 (R1): 82.03. Result ID: 699a60085698665ec4e7fe7a.

[Reporting paper](<https://www.sota2.com/research/paper/6992a4769ebc499c97406bf4.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa7c471e209131cea8d5c1.md>)

Recorded evaluation configuration: {"Venue":"ICML2025"}. This record does not assert independent reproduction.

### SDCL

Rank-1 (R1): 81.36. Result ID: 699a60085698665ec4e7fe79.

[Reporting paper](<https://www.sota2.com/research/paper/6992a4769ebc499c97406bf4.md>)

Recorded evaluation configuration: {"Venue":"CVPR2024"}. This record does not assert independent reproduction.

### GUR

Rank-1 (R1): 80.31. Result ID: 699a60085698665ec4e7fe78.

[Reporting paper](<https://www.sota2.com/research/paper/6992a4769ebc499c97406bf4.md>)

Recorded evaluation configuration: {"Venue":"ICCV2023"}. This record does not assert independent reproduction.

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