# Text-to-Image Retrieval on COCO-CN (test)

Source: [Text-to-Image Retrieval on COCO-CN (test)](<https://www.sota2.com/research/sota/text-to-image-retrieval-on-coco-cn-test>)

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

Data updated: 2026-02-26T05:59:26.283Z

Evaluation of Text-to-Image Retrieval performance on the test split of the COCO-CN dataset, measured using rank-based metrics (R@1, R@5, R@10, R@M).

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) | COCO-CN (test) |
| Metric | R@1 |
| Unit | PERCENT |
| Direction | Higher is better |
| Results loaded | 8 of 8 |
| 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-coco-cn-test.md?metric=R%401>): Higher is better; unit: PERCENT.

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

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

- [R@M](<https://www.sota2.com/research/sota/text-to-image-retrieval-on-coco-cn-test.md?metric=R%40M>): Higher is better; unit: PERCENT.

## Recorded results

| Method | R@1 | Result date | Report paper |
| --- | --- | --- | --- |
| R2D2 | 79.1 | Not recorded | 68fa71271e209131cea4f8eb |
| R2D2 | 76 | Not recorded | 68fa71271e209131cea4f8eb |
| Wukong | 74 | Not recorded | 68fa71271e209131cea4f8eb |
| FILIP | 72.2 | Not recorded | 68fa71271e209131cea4f8eb |
| CLIP | 70.1 | Not recorded | 68fa71271e209131cea4f8eb |
| CLIP | 68.9 | Not recorded | 68fa71271e209131cea4f8eb |
| Wukong | 67 | Not recorded | 68fa71271e209131cea4f8eb |
| FILIP | 56.2 | Not recorded | 68fa71271e209131cea4f8eb |

### R2D2

R@1: 79.1. Result ID: 69919eed3a6c314849096c74.

[Reporting paper](<https://www.sota2.com/research/paper/68fa71271e209131cea4f8eb.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa71271e209131cea4f8eb.md>)

[Implementation](<https://github.com/yuxie11/R2D2>)

Recorded evaluation configuration: {"Backbone":"ViT-L"}. This record does not assert independent reproduction.

### R2D2

R@1: 76. Result ID: 69919eed3a6c314849096c73.

[Reporting paper](<https://www.sota2.com/research/paper/68fa71271e209131cea4f8eb.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa71271e209131cea4f8eb.md>)

[Implementation](<https://github.com/yuxie11/R2D2>)

Recorded evaluation configuration: {"Backbone":"ViT-B"}. This record does not assert independent reproduction.

### Wukong

R@1: 74. Result ID: 69919eed3a6c314849096c72.

[Reporting paper](<https://www.sota2.com/research/paper/68fa71271e209131cea4f8eb.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6d821e209131cea3a343.md>)

[Implementation](<https://wukong-dataset.github.io/wukong-dataset/>)

Recorded evaluation configuration: {"Backbone":"ViT-L"}. This record does not assert independent reproduction.

### FILIP

R@1: 72.2. Result ID: 69919eed3a6c314849096c70.

[Reporting paper](<https://www.sota2.com/research/paper/68fa71271e209131cea4f8eb.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6b471e209131cea2d39b.md>)

Recorded evaluation configuration: {"Backbone":"ViT-L"}. This record does not assert independent reproduction.

### CLIP

R@1: 70.1. Result ID: 69919eed3a6c314849096c6e.

[Reporting paper](<https://www.sota2.com/research/paper/68fa71271e209131cea4f8eb.md>)

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

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

Recorded evaluation configuration: {"Backbone":"ViT-L"}. This record does not assert independent reproduction.

### CLIP

R@1: 68.9. Result ID: 69919eed3a6c314849096c6d.

[Reporting paper](<https://www.sota2.com/research/paper/68fa71271e209131cea4f8eb.md>)

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

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

Recorded evaluation configuration: {"Backbone":"ViT-B"}. This record does not assert independent reproduction.

### Wukong

R@1: 67. Result ID: 69919eed3a6c314849096c71.

[Reporting paper](<https://www.sota2.com/research/paper/68fa71271e209131cea4f8eb.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6d821e209131cea3a343.md>)

[Implementation](<https://wukong-dataset.github.io/wukong-dataset/>)

Recorded evaluation configuration: {"Backbone":"ViT-B"}. This record does not assert independent reproduction.

### FILIP

R@1: 56.2. Result ID: 69919eed3a6c314849096c6f.

[Reporting paper](<https://www.sota2.com/research/paper/68fa71271e209131cea4f8eb.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6b471e209131cea2d39b.md>)

Recorded evaluation configuration: {"Backbone":"ViT-B"}. This record does not assert independent reproduction.

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