# Text-to-Image Retrieval on MS-COCO 5K full set (test)

Source: [Text-to-Image Retrieval on MS-COCO 5K full set (test)](<https://www.sota2.com/research/sota/text-to-image-retrieval-on-ms-coco-5k-full-set-test>)

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

Data updated: 2026-07-03T06:49:30.455Z

Evaluation of Text-to-Image Retrieval performance on the specific 5K full test subset of the MS-COCO dataset, measured using R@K and rSum metrics.

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 Retrieval |
| Dataset (including any stated split) | MS-COCO 5K full set (test) |
| Metric | R@1 |
| Unit | PERCENT |
| Direction | Higher is better |
| Results loaded | 4 of 4 |
| 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

- [R@1](<https://www.sota2.com/research/sota/text-to-image-retrieval-on-ms-coco-5k-full-set-test.md?metric=R%401>): Higher is better; unit: PERCENT.

- [R@5](<https://www.sota2.com/research/sota/text-to-image-retrieval-on-ms-coco-5k-full-set-test.md?metric=R%405>): Higher is better; unit: PERCENT.

- [R@10](<https://www.sota2.com/research/sota/text-to-image-retrieval-on-ms-coco-5k-full-set-test.md?metric=R%4010>): Higher is better; unit: PERCENT.

- [rSum](<https://www.sota2.com/research/sota/text-to-image-retrieval-on-ms-coco-5k-full-set-test.md?metric=rSum>): Higher is better; unit: SCALAR.

## Recorded results

| Method | R@1 | Result date | Report paper |
| --- | --- | --- | --- |
| SEPS | 78.5 | Not recorded | 690988853ef7ccd74e5e5c23 |
| SEPS | 73.5 | Not recorded | 690988853ef7ccd74e5e5c23 |
| SEPS | 70.3 | Not recorded | 690988853ef7ccd74e5e5c23 |
| SEPS | 66.8 | Not recorded | 690988853ef7ccd74e5e5c23 |

### SEPS

R@1: 78.5. Result ID: 6a475b5c60b88bb339922c71.

[Reporting paper](<https://www.sota2.com/research/paper/690988853ef7ccd74e5e5c23.md>)

[Method origin paper](<https://www.sota2.com/research/paper/690988853ef7ccd74e5e5c23.md>)

Recorded evaluation configuration: {"Visual Encoder":"ViT-Base-384","Textual Encoder":"BERT-base","Image Resolution":"384x384","Patch Size":"24x24","Fine-Grained Alignment (FG)":"true"}. This record does not assert independent reproduction.

### SEPS

R@1: 73.5. Result ID: 6a475b5c60b88bb339922c70.

[Reporting paper](<https://www.sota2.com/research/paper/690988853ef7ccd74e5e5c23.md>)

[Method origin paper](<https://www.sota2.com/research/paper/690988853ef7ccd74e5e5c23.md>)

Recorded evaluation configuration: {"Visual Encoder":"ViT-Base-224","Textual Encoder":"BERT-base","Image Resolution":"224x224","Patch Size":"14x14","Fine-Grained Alignment (FG)":"true"}. This record does not assert independent reproduction.

### SEPS

R@1: 70.3. Result ID: 6a475b5c60b88bb339922c73.

[Reporting paper](<https://www.sota2.com/research/paper/690988853ef7ccd74e5e5c23.md>)

[Method origin paper](<https://www.sota2.com/research/paper/690988853ef7ccd74e5e5c23.md>)

Recorded evaluation configuration: {"Visual Encoder":"Swin-Base-384","Textual Encoder":"BERT-base","Image Resolution":"384x384","Patch Size":"12x12","Fine-Grained Alignment (FG)":"true"}. This record does not assert independent reproduction.

### SEPS

R@1: 66.8. Result ID: 6a475b5c60b88bb339922c72.

[Reporting paper](<https://www.sota2.com/research/paper/690988853ef7ccd74e5e5c23.md>)

[Method origin paper](<https://www.sota2.com/research/paper/690988853ef7ccd74e5e5c23.md>)

Recorded evaluation configuration: {"Visual Encoder":"Swin-Base-224","Textual Encoder":"BERT-base","Image Resolution":"224x224","Patch Size":"7x7","Fine-Grained Alignment (FG)":"true"}. This record does not assert independent reproduction.

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