# Image-to-Audio Retrieval on AudioSet (val)

Source: [Image-to-Audio Retrieval on AudioSet (val)](<https://www.sota2.com/research/sota/image-to-audio-retrieval-on-audioset-val>)

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

Data updated: 2026-02-26T05:26:53.833Z

Evaluation of Image-to-Audio Retrieval performance on the validation split of the AudioSet dataset, measured using Acc @10.

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 | Image-to-Audio Retrieval |
| Dataset (including any stated split) | AudioSet (val) |
| Metric | Acc @10 |
| Unit | PERCENT |
| Direction | Higher is better |
| Results loaded | 3 of 3 |
| 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

- [Acc @10](<https://www.sota2.com/research/sota/image-to-audio-retrieval-on-audioset-val.md?metric=Acc%20%4010>): Higher is better; unit: PERCENT.

## Recorded results

| Method | Acc @10 | Result date | Report paper |
| --- | --- | --- | --- |
| DenseAV | 69.8 | Not recorded | 68fa73881e209131cea5d00d |
| ImageBind | 64.5 | Not recorded | 68fa73881e209131cea5d00d |
| CAVMAE | 55.7 | Not recorded | 68fa73881e209131cea5d00d |

### DenseAV

Acc @10: 69.8. Result ID: 6992e76e3a6c3148491245c5.

[Reporting paper](<https://www.sota2.com/research/paper/68fa73881e209131cea5d00d.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa73881e209131cea5d00d.md>)

[Implementation](<https://aka.ms/denseav>)

Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction.

### ImageBind

Acc @10: 64.5. Result ID: 6992e76e3a6c3148491245c4.

[Reporting paper](<https://www.sota2.com/research/paper/68fa73881e209131cea5d00d.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6f971e209131cea467c4.md>)

[Implementation](<https://facebookresearch.github.io/ImageBind>)

Recorded evaluation configuration: {"model\_size":"largest pretrained"}. This record does not assert independent reproduction.

### CAVMAE

Acc @10: 55.7. Result ID: 6992e76e3a6c3148491245c3.

[Reporting paper](<https://www.sota2.com/research/paper/68fa73881e209131cea5d00d.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6f041e209131cea4345b.md>)

[Implementation](<https://github.com/yuangongnd/cav-mae>)

Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction.

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