# Audio-to-Video Retrieval on CrossTask

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

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

Data updated: 2026-02-26T06:01:22.946Z

Evaluation of Audio-to-Video Retrieval performance on the CrossTask dataset, measured using metrics such as R@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 | Audio-to-Video Retrieval |
| Dataset (including any stated split) | CrossTask |
| Metric | Recall@1 |
| 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

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

## Recorded results

| Method | Recall@1 | Result date | Report paper |
| --- | --- | --- | --- |
| TVLT | 15.3 | Not recorded | 68fa6dda1e209131cea3c6fe |
| TVLT | 14.9 | Not recorded | 68fa6dda1e209131cea3c6fe |
| AVLnet | 13.8 | Not recorded | 68fa6dda1e209131cea3c6fe |

### TVLT

Recall@1: 15.3. Result ID: 698fec1f3a6c314849fccf29.

[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: 14.9. Result ID: 698fec1f3a6c314849fccf28.

[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: 13.8. Result ID: 698fec1f3a6c314849fccf27.

[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.

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