# Infrared-to-Real Person Re-identification on CUHK-PEDES (test) Source: [Infrared-to-Real Person Re-identification on CUHK-PEDES (test)]() Collection index: [llms.txt]() Data updated: 2026-02-26T06:01:05.403Z Evaluation of Infrared-to-Real Person Re-identification performance on the test split of the CUHK-PEDES dataset, measured using Rank 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) | CUHK-PEDES (test) | | Metric | Rank-1 Accuracy (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 Accuracy (R1)](): Higher is better; unit: PERCENT. - [Rank-5 Accuracy (R5)](): Higher is better; unit: PERCENT. - [Rank-10 Accuracy (R10)](): Higher is better; unit: PERCENT. - [Mean Average Precision (mAP)](): Higher is better; unit: PERCENT. - [Mean Intersection over Non-target Parts (mINP)](): Higher is better; unit: PERCENT. - [Average mAP (Avg. mAP)](): Higher is better; unit: PERCENT. ## Recorded results | Method | Rank-1 Accuracy (R1) | Result date | Report paper | | --- | --- | --- | --- | | MLLMEmbed-ReID | 92.87 | Not recorded | 6992a4769ebc499c97406bf4 | | MLLMEmbed-ReID | 90.45 | Not recorded | 6992a4769ebc499c97406bf4 | | MLLMEmbed-ReID | 89 | Not recorded | 6992a4769ebc499c97406bf4 | | FlexiReID | 85.26 | Not recorded | 6992a4769ebc499c97406bf4 | | SDCL | 84.57 | Not recorded | 6992a4769ebc499c97406bf4 | | GUR | 82.06 | Not recorded | 6992a4769ebc499c97406bf4 | ### MLLMEmbed-ReID Rank-1 Accuracy (R1): 92.87. Result ID: 699a60085698665ec4e7fe75. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Query-Gallery feature type (C2C/E2C/E2E)":"C2C"}. This record does not assert independent reproduction. ### MLLMEmbed-ReID Rank-1 Accuracy (R1): 90.45. Result ID: 699a60085698665ec4e7fe76. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Query-Gallery feature type (C2C/E2C/E2E)":"E2E"}. This record does not assert independent reproduction. ### MLLMEmbed-ReID Rank-1 Accuracy (R1): 89. Result ID: 699a60085698665ec4e7fe77. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Query-Gallery feature type (C2C/E2C/E2E)":"E2C"}. This record does not assert independent reproduction. ### FlexiReID Rank-1 Accuracy (R1): 85.26. Result ID: 699a60085698665ec4e7fe74. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Venue":"ICML2025"}. This record does not assert independent reproduction. ### SDCL Rank-1 Accuracy (R1): 84.57. Result ID: 699a60085698665ec4e7fe73. [Reporting paper]() Recorded evaluation configuration: {"Venue":"CVPR2024"}. This record does not assert independent reproduction. ### GUR Rank-1 Accuracy (R1): 82.06. Result ID: 699a60085698665ec4e7fe72. [Reporting paper]() 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.