# Text-to-Image Retrieval on Flickr8K-CN

Source: [Text-to-Image Retrieval on Flickr8K-CN](<https://www.sota2.com/research/sota/text-to-image-retrieval-on-flickr8k-cn>)

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

Data updated: 2026-02-26T05:59:23.895Z

Evaluation of Text-to-Image Retrieval performance on the Flickr8K-CN dataset, measured using R@K metrics and Mean Rank (MR).

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) | Flickr8K-CN |
| Metric | R@1 |
| Unit | PERCENT |
| Direction | Higher is better |
| Results loaded | 19 of 19 |
| 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-flickr8k-cn.md?metric=R%401>): Higher is better; unit: PERCENT.

- [R@5](<https://www.sota2.com/research/sota/text-to-image-retrieval-on-flickr8k-cn.md?metric=R%405>): Higher is better; unit: PERCENT.

- [R@10](<https://www.sota2.com/research/sota/text-to-image-retrieval-on-flickr8k-cn.md?metric=R%4010>): Higher is better; unit: PERCENT.

- [MR](<https://www.sota2.com/research/sota/text-to-image-retrieval-on-flickr8k-cn.md?metric=MR>): Lower is better; unit: SCALAR.

## Recorded results

| Method | R@1 | Result date | Report paper |
| --- | --- | --- | --- |
| Wukong\_ViT-L | 70.1 | Not recorded | 68fa6d821e209131cea3a343 |
| FILIP\_ViT-L | 68.5 | Not recorded | 68fa6d821e209131cea3a343 |
| CLIP\_ViT-L | 67.4 | Not recorded | 68fa6d821e209131cea3a343 |
| FILIP\_Swin-L | 61.5 | Not recorded | 68fa6d821e209131cea3a343 |
| CLIP\_ViT-B | 61.2 | Not recorded | 68fa6d821e209131cea3a343 |
| CLIP\_Swin-L | 59.3 | Not recorded | 68fa6d821e209131cea3a343 |
| Wukong\_ViT-B | 58.4 | Not recorded | 68fa6d821e209131cea3a343 |
| Wukong\_Swin-L | 57.9 | Not recorded | 68fa6d821e209131cea3a343 |
| FILIP | 53.5 | Not recorded | 68fa6d821e209131cea3a343 |
| CLIP | 50.5 | Not recorded | 68fa6d821e209131cea3a343 |
| FILIP\_ViT-B | 46.4 | Not recorded | 68fa6d821e209131cea3a343 |
| Wukong | 46 | Not recorded | 68fa6d821e209131cea3a343 |
| CLIP | 44.2 | Not recorded | 68fa6d821e209131cea3a343 |
| Wukong | 43.2 | Not recorded | 68fa6d821e209131cea3a343 |
| FILIP | 41.2 | Not recorded | 68fa6d821e209131cea3a343 |
| CLIP | 38.6 | Not recorded | 68fa6d821e209131cea3a343 |
| Wukong | 36.6 | Not recorded | 68fa6d821e209131cea3a343 |
| FILIP | 24 | Not recorded | 68fa6d821e209131cea3a343 |
| BriVL | 8 | Not recorded | 68fa6d821e209131cea3a343 |

### Wukong\_ViT-L

R@1: 70.1. Result ID: 698fa5533a6c314849facaf0.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6d821e209131cea3a343.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","Evaluation Protocol":"Fine-tuned"}. This record does not assert independent reproduction.

### FILIP\_ViT-L

R@1: 68.5. Result ID: 698fa5533a6c314849facaed.

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

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

Recorded evaluation configuration: {"Backbone":"ViT-L","Evaluation Protocol":"Fine-tuned"}. This record does not assert independent reproduction.

### CLIP\_ViT-L

R@1: 67.4. Result ID: 698fa5533a6c314849facaea.

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

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

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

Recorded evaluation configuration: {"Backbone":"ViT-L","Evaluation Protocol":"Fine-tuned"}. This record does not assert independent reproduction.

### FILIP\_Swin-L

R@1: 61.5. Result ID: 698fa5533a6c314849facaee.

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

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

Recorded evaluation configuration: {"Backbone":"Swin-L","Evaluation Protocol":"Fine-tuned"}. This record does not assert independent reproduction.

### CLIP\_ViT-B

R@1: 61.2. Result ID: 698fa5533a6c314849facae9.

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

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

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

Recorded evaluation configuration: {"Backbone":"ViT-B","Evaluation Protocol":"Fine-tuned"}. This record does not assert independent reproduction.

### CLIP\_Swin-L

R@1: 59.3. Result ID: 698fa5533a6c314849facaeb.

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

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

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

Recorded evaluation configuration: {"Backbone":"Swin-L","Evaluation Protocol":"Fine-tuned"}. This record does not assert independent reproduction.

### Wukong\_ViT-B

R@1: 58.4. Result ID: 698fa5533a6c314849facaef.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6d821e209131cea3a343.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","Evaluation Protocol":"Fine-tuned"}. This record does not assert independent reproduction.

### Wukong\_Swin-L

R@1: 57.9. Result ID: 698fa5533a6c314849facaf1.

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

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

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

Recorded evaluation configuration: {"Backbone":"Swin-L","Evaluation Protocol":"Fine-tuned"}. This record does not assert independent reproduction.

### FILIP

R@1: 53.5. Result ID: 698fa5533a6c314849faca45.

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

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

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

### CLIP

R@1: 50.5. Result ID: 698fa5533a6c314849faca42.

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

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

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

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

### FILIP\_ViT-B

R@1: 46.4. Result ID: 698fa5533a6c314849facaec.

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

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

Recorded evaluation configuration: {"Backbone":"ViT-B","Evaluation Protocol":"Fine-tuned"}. This record does not assert independent reproduction.

### Wukong

R@1: 46. Result ID: 698fa5533a6c314849faca48.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6d821e209131cea3a343.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","Zero-shot":true}. This record does not assert independent reproduction.

### CLIP

R@1: 44.2. Result ID: 698fa5533a6c314849faca41.

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

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

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

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

### Wukong

R@1: 43.2. Result ID: 698fa5533a6c314849faca47.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6d821e209131cea3a343.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","Zero-shot":true}. This record does not assert independent reproduction.

### FILIP

R@1: 41.2. Result ID: 698fa5533a6c314849faca46.

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

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

Recorded evaluation configuration: {"Backbone":"Swin-L","Zero-shot":true}. This record does not assert independent reproduction.

### CLIP

R@1: 38.6. Result ID: 698fa5533a6c314849faca43.

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

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

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

Recorded evaluation configuration: {"Backbone":"Swin-L","Zero-shot":true}. This record does not assert independent reproduction.

### Wukong

R@1: 36.6. Result ID: 698fa5533a6c314849faca49.

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

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

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

Recorded evaluation configuration: {"Backbone":"Swin-L","Zero-shot":true}. This record does not assert independent reproduction.

### FILIP

R@1: 24. Result ID: 698fa5533a6c314849faca44.

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

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

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

### BriVL

R@1: 8. Result ID: 698fa5533a6c314849faca40.

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

[Method origin paper](<https://www.sota2.com/research/paper/68fa6a5a1e209131cea27a5b.md>)

Recorded evaluation configuration: {"Backbone":"N/A","Zero-shot":true}. This record does not assert independent reproduction.

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