# Audio-to-Video Retrieval on MSR-VTT

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

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

Data updated: 2026-02-26T06:01:25.234Z

Evaluation of Audio-to-Video Retrieval performance using the MSR-VTT dataset.

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) | MSR-VTT |
| Metric | Recall@1 |
| Unit | PERCENT |
| Direction | Higher is better |
| Results loaded | 13 of 13 |
| 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/audio-to-video-retrieval-on-msr-vtt.md?metric=Recall%401>): Higher is better; unit: PERCENT.

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

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

## Recorded results

| Method | Recall@1 | Result date | Report paper |
| --- | --- | --- | --- |
| TVLT | 23.8 | Not recorded | 68fa6dda1e209131cea3c6fe |
| TVLT | 22.6 | Not recorded | 68fa6dda1e209131cea3c6fe |
| AVLnet | 20.1 | Not recorded | 68fa6dda1e209131cea3c6fe |
| AVLnet | 17.8 | Not recorded | 68fa73c31e209131cea5e53c |
| EquiAV | 14.4 | Not recorded | 68fa73c31e209131cea5e53c |
| Aranjelovic | 12.6 | Not recorded | 68fa73c31e209131cea5e53c |
| VAB-DAC | 12 | Not recorded | 68fa74f81e209131cea64f3f |
| VAB-Encodec | 9.6 | Not recorded | 68fa74f81e209131cea64f3f |
| Boggust | 7.6 | Not recorded | 68fa73c31e209131cea5e53c |
| CAV-MAE | 7.6 | Not recorded | 68fa73c31e209131cea5e53c |
| CAV-MAE | 7.6 | Not recorded | 68fa74f81e209131cea64f3f |
| ImageBind | 6 | Not recorded | 68fa74f81e209131cea64f3f |
| LanguageBind | 1.2 | Not recorded | 68fa74f81e209131cea64f3f |

### TVLT

Recall@1: 23.8. Result ID: 698fec1f3a6c314849fccf23.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6dda1e209131cea3c6fe.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6dda1e209131cea3c6fe.md>)

[Implementation](<https://github.com/zinengtang/TVLT>)

Recorded evaluation configuration: {"Vision Input":"true","Audio Input":"true","Pretrain Datasets":"YTT-S"}. This record does not assert independent reproduction.

### TVLT

Recall@1: 22.6. Result ID: 698fec1f3a6c314849fccf22.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6dda1e209131cea3c6fe.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6dda1e209131cea3c6fe.md>)

[Implementation](<https://github.com/zinengtang/TVLT>)

Recorded evaluation configuration: {"Vision Input":"true","Audio Input":"true","Pretrain Datasets":"HT100M"}. This record does not assert independent reproduction.

### AVLnet

Recall@1: 20.1. Result ID: 698fec1f3a6c314849fccf21.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6dda1e209131cea3c6fe.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6a451e209131cea2736c.md>)

Recorded evaluation configuration: {"Vision Input":"true","Audio Input":"true","Pretrain Datasets":"HT100M"}. This record does not assert independent reproduction.

### AVLnet

Recall@1: 17.8. Result ID: 699321ea3a6c31484913effc.

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

[Method origin paper](<https://www.sota2.com/research/paper/68fa639f1e209131ce9ffc68.md>)

Recorded evaluation configuration: {"Zero-shot":true,"Pre-train":"HowTo100M"}. This record does not assert independent reproduction.

### EquiAV

Recall@1: 14.4. Result ID: 699321ea3a6c31484913effe.

[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.

### Aranjelovic

Recall@1: 12.6. Result ID: 699321ea3a6c31484913effb.

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

[Method origin paper](<https://www.sota2.com/research/paper/68fa638a1e209131ce9ff616.md>)

Recorded evaluation configuration: {"Zero-shot":true,"Pre-train":"HowTo100M"}. This record does not assert independent reproduction.

### VAB-DAC

Recall@1: 12. Result ID: 69936d343a6c31484915dbe7.

[Reporting paper](<https://www.sota2.com/research/paper/68fa74f81e209131cea64f3f.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa74f81e209131cea64f3f.md>)

Recorded evaluation configuration: {"Direction":"Audio -\> Video","Zero-shot":true}. This record does not assert independent reproduction.

### VAB-Encodec

Recall@1: 9.6. Result ID: 69936d343a6c31484915dbe8.

[Reporting paper](<https://www.sota2.com/research/paper/68fa74f81e209131cea64f3f.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa74f81e209131cea64f3f.md>)

Recorded evaluation configuration: {"Direction":"Audio -\> Video","Zero-shot":true}. This record does not assert independent reproduction.

### Boggust

Recall@1: 7.6. Result ID: 699321ea3a6c31484913effa.

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

Recorded evaluation configuration: {"Zero-shot":true,"Pre-train":"HowTo100M"}. This record does not assert independent reproduction.

### CAV-MAE

Recall@1: 7.6. Result ID: 699321ea3a6c31484913effd.

[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

Recall@1: 7.6. Result ID: 69936d343a6c31484915dbe6.

[Reporting paper](<https://www.sota2.com/research/paper/68fa74f81e209131cea64f3f.md>)

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

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

Recorded evaluation configuration: {"Direction":"Audio -\> Video","Zero-shot":true}. This record does not assert independent reproduction.

### ImageBind

Recall@1: 6. Result ID: 69936d343a6c31484915dbe5.

[Reporting paper](<https://www.sota2.com/research/paper/68fa74f81e209131cea64f3f.md>)

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

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

Recorded evaluation configuration: {"Direction":"Audio -\> Video","Zero-shot":true}. This record does not assert independent reproduction.

### LanguageBind

Recall@1: 1.2. Result ID: 69936d343a6c31484915dbe4.

[Reporting paper](<https://www.sota2.com/research/paper/68fa74f81e209131cea64f3f.md>)

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

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

Recorded evaluation configuration: {"Direction":"Audio -\> Video","Zero-shot":true}. This record does not assert independent reproduction.

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