# Audio-to-Video Retrieval on AudioSet

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

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

Data updated: 2026-06-25T08:03:22.880Z

Evaluation of Audio-to-Video Retrieval performance on the AudioSet dataset, measured using recall metrics (R@K).

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 | Audio-to-Video Retrieval |
| Dataset (including any stated split) | AudioSet |
| Metric | R@1 |
| Unit | PERCENT |
| Direction | Higher is better |
| Results loaded | 7 of 7 |
| 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/audio-to-video-retrieval-on-audioset.md?metric=R%401>): Higher is better; unit: PERCENT.

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

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

## Recorded results

| Method | R@1 | Result date | Report paper |
| --- | --- | --- | --- |
| EquiAV | 29.6 | Not recorded | 68fa73c31e209131cea5e53c |
| EquiAV | 29.6 | Not recorded | 6a3cb63e206542251d7ca6ca |
| MJEPA | 29.3 | Not recorded | 6a3cb63e206542251d7ca6ca |
| CAV-MAE Sync | 27.9 | Not recorded | 6a3cb63e206542251d7ca6ca |
| CAV-MAE | 15.1 | Not recorded | 68fa73c31e209131cea5e53c |
| CAV-MAE | 15.1 | Not recorded | 6a3cb63e206542251d7ca6ca |
| CAV-MAE-Scale++ | 14.3 | Not recorded | 68fa73c31e209131cea5e53c |

### EquiAV

R@1: 29.6. Result ID: 699321ea3a6c31484913f004.

[Reporting paper](<https://www.sota2.com/research/paper/68fa73c31e209131cea5e53c.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa73c31e209131cea5e53c.md>)

[Implementation](<https://github.com/JongSuk1/EquiAV>)

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

### EquiAV

R@1: 29.6. Result ID: 6a3ce0b8fbc373592c51efb3.

[Reporting paper](<https://www.sota2.com/research/paper/6a3cb63e206542251d7ca6ca.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa73c31e209131cea5e53c.md>)

[Implementation](<https://github.com/JongSuk1/EquiAV>)

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

### MJEPA

R@1: 29.3. Result ID: 6a3ce0b8fbc373592c51efb4.

[Reporting paper](<https://www.sota2.com/research/paper/6a3cb63e206542251d7ca6ca.md>)

[Method origin paper](<https://www.sota2.com/research/paper/6a3cb63e206542251d7ca6ca.md>)

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

### CAV-MAE Sync

R@1: 27.9. Result ID: 6a3ce0b8fbc373592c51efb2.

[Reporting paper](<https://www.sota2.com/research/paper/6a3cb63e206542251d7ca6ca.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa78b41e209131cea79dbd.md>)

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

### CAV-MAE

R@1: 15.1. Result ID: 699321ea3a6c31484913f003.

[Reporting paper](<https://www.sota2.com/research/paper/68fa73c31e209131cea5e53c.md>)

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

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

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

### CAV-MAE

R@1: 15.1. Result ID: 6a3ce0b8fbc373592c51efb1.

[Reporting paper](<https://www.sota2.com/research/paper/6a3cb63e206542251d7ca6ca.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.

### CAV-MAE-Scale++

R@1: 14.3. Result ID: 699321ea3a6c31484913f002.

[Reporting paper](<https://www.sota2.com/research/paper/68fa73c31e209131cea5e53c.md>)

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

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

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

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