# Video-to-Audio Retrieval on AudioCaps V→A

Source: [Video-to-Audio Retrieval on AudioCaps V→A](<https://www.sota2.com/research/sota/video-to-audio-retrieval-on-audiocaps-v-a>)

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

Data updated: 2026-02-27T12:33:39.458Z

Evaluation of Video-to-Audio Retrieval performance on the AudioCaps V→A configuration, measured using Recall@1.

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 | Video-to-Audio Retrieval |
| Dataset (including any stated split) | AudioCaps V→A |
| Metric | Recall@1 |
| Unit | PERCENT |
| Direction | Higher is better |
| Results loaded | 10 of 10 |
| 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

- [Recall@1](<https://www.sota2.com/research/sota/video-to-audio-retrieval-on-audiocaps-v-a.md?metric=Recall%401>): Higher is better; unit: PERCENT.

## Recorded results

| Method | Recall@1 | Result date | Report paper |
| --- | --- | --- | --- |
| PEAV L | 88.3 | Not recorded | 694a22519eebe296e72aab56 |
| PEAV L | 86.1 | Not recorded | 694a22519eebe296e72aab56 |
| PEAV L-OOD | 86.1 | Not recorded | 694a22519eebe296e72aab56 |
| PEAV B | 83.7 | Not recorded | 694a22519eebe296e72aab56 |
| PEAV L (PT) | 83.3 | Not recorded | 694a22519eebe296e72aab56 |
| PEAV B | 80.6 | Not recorded | 694a22519eebe296e72aab56 |
| PEAV S | 77.4 | Not recorded | 694a22519eebe296e72aab56 |
| PEAV S | 75.4 | Not recorded | 694a22519eebe296e72aab56 |
| ImageBind | 51.3 | Not recorded | 694a22519eebe296e72aab56 |
| LangBind | 9.1 | Not recorded | 694a22519eebe296e72aab56 |

### PEAV L

Recall@1: 88.3. Result ID: 69a18f0d35dfcabb00e7d129.

[Reporting paper](<https://www.sota2.com/research/paper/694a22519eebe296e72aab56.md>)

[Method origin paper](<https://www.sota2.com/research/paper/694a22519eebe296e72aab56.md>)

Recorded evaluation configuration: {"A-Enc Params.":"1.1B","Data (M)":"124","Sampling":"30 FPS"}. This record does not assert independent reproduction.

### PEAV L

Recall@1: 86.1. Result ID: 69a18f0d35dfcabb00e7d124.

[Reporting paper](<https://www.sota2.com/research/paper/694a22519eebe296e72aab56.md>)

[Method origin paper](<https://www.sota2.com/research/paper/694a22519eebe296e72aab56.md>)

Recorded evaluation configuration: {"A-Enc Params.":"1.1B","Data (M)":"124","Sampling":"16 Frames"}. This record does not assert independent reproduction.

### PEAV L-OOD

Recall@1: 86.1. Result ID: 69a18f0d35dfcabb00e7d125.

[Reporting paper](<https://www.sota2.com/research/paper/694a22519eebe296e72aab56.md>)

[Method origin paper](<https://www.sota2.com/research/paper/694a22519eebe296e72aab56.md>)

Recorded evaluation configuration: {"A-Enc Params.":"1.1B","Data (M)":"114","Sampling":"30 FPS","OOD":true}. This record does not assert independent reproduction.

### PEAV B

Recall@1: 83.7. Result ID: 69a18f0d35dfcabb00e7d127.

[Reporting paper](<https://www.sota2.com/research/paper/694a22519eebe296e72aab56.md>)

[Method origin paper](<https://www.sota2.com/research/paper/694a22519eebe296e72aab56.md>)

Recorded evaluation configuration: {"A-Enc Params.":"0.2B","Data (M)":"124","Sampling":"30 FPS"}. This record does not assert independent reproduction.

### PEAV L (PT)

Recall@1: 83.3. Result ID: 69a18f0d35dfcabb00e7d128.

[Reporting paper](<https://www.sota2.com/research/paper/694a22519eebe296e72aab56.md>)

[Method origin paper](<https://www.sota2.com/research/paper/694a22519eebe296e72aab56.md>)

Recorded evaluation configuration: {"A-Enc Params.":"1.1B","Data (M)":"92","Sampling":"30 FPS","PT":true}. This record does not assert independent reproduction.

### PEAV B

Recall@1: 80.6. Result ID: 69a18f0d35dfcabb00e7d123.

[Reporting paper](<https://www.sota2.com/research/paper/694a22519eebe296e72aab56.md>)

[Method origin paper](<https://www.sota2.com/research/paper/694a22519eebe296e72aab56.md>)

Recorded evaluation configuration: {"A-Enc Params.":".2B","Data (M)":"124","Sampling":"16 Frames"}. This record does not assert independent reproduction.

### PEAV S

Recall@1: 77.4. Result ID: 69a18f0d35dfcabb00e7d126.

[Reporting paper](<https://www.sota2.com/research/paper/694a22519eebe296e72aab56.md>)

[Method origin paper](<https://www.sota2.com/research/paper/694a22519eebe296e72aab56.md>)

Recorded evaluation configuration: {"A-Enc Params.":".09B","Data (M)":"124","Sampling":"30 FPS"}. This record does not assert independent reproduction.

### PEAV S

Recall@1: 75.4. Result ID: 69a18f0d35dfcabb00e7d122.

[Reporting paper](<https://www.sota2.com/research/paper/694a22519eebe296e72aab56.md>)

[Method origin paper](<https://www.sota2.com/research/paper/694a22519eebe296e72aab56.md>)

Recorded evaluation configuration: {"A-Enc Params.":".09B","Data (M)":"124","Sampling":"16 Frames"}. This record does not assert independent reproduction.

### ImageBind

Recall@1: 51.3. Result ID: 69a18f0d35dfcabb00e7d120.

[Reporting paper](<https://www.sota2.com/research/paper/694a22519eebe296e72aab56.md>)

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

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

Recorded evaluation configuration: {"A-Enc Params.":".09B","Data (M)":"3"}. This record does not assert independent reproduction.

### LangBind

Recall@1: 9.1. Result ID: 69a18f0d35dfcabb00e7d121.

[Reporting paper](<https://www.sota2.com/research/paper/694a22519eebe296e72aab56.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa71f31e209131cea53b97.md>)

[Implementation](<https://github.com/PKU-YuanGroup/LanguageBind>)

Recorded evaluation configuration: {"A-Enc Params.":"0.3B","Data (M)":"10"}. This record does not assert independent reproduction.

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