# Cross-modal classification (Visual to Audio) on VGGSound-AVEL 90K UCF to VGG

Source: [Cross-modal classification (Visual to Audio) on VGGSound-AVEL 90K UCF to VGG](<https://www.sota2.com/research/sota/cross-modal-classification-visual-to-audio-on-vggsound-avel-90k-ucf-to-vgg>)

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

Data updated: 2026-05-13T10:37:19.202Z

Evaluation of cross-modal classification performance, specifically mapping Visual inputs to Audio outputs, using the VGGSound-AVEL 90K UCF to VGG subset.

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 | Cross-modal classification (Visual to Audio) |
| Dataset (including any stated split) | VGGSound-AVEL 90K UCF to VGG |
| Metric | Precision |
| Unit | PERCENT |
| Direction | Higher is better |
| Results loaded | 4 of 4 |
| 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

- [Precision](<https://www.sota2.com/research/sota/cross-modal-classification-visual-to-audio-on-vggsound-avel-90k-ucf-to-vgg.md?metric=Precision>): Higher is better; unit: PERCENT.

## Recorded results

| Method | Precision | Result date | Report paper |
| --- | --- | --- | --- |
| MICU | 73.7 | Not recorded | 6a0405dadbc836b87d827861 |
| CoDAAR | 71.2 | Not recorded | 6a0405dadbc836b87d827861 |
| DCID | 69.9 | Not recorded | 6a0405dadbc836b87d827861 |
| Baseline | 19.2 | Not recorded | 6a0405dadbc836b87d827861 |

### MICU

Precision: 73.7. Result ID: 6a04544647f34ce924eae7f7.

[Reporting paper](<https://www.sota2.com/research/paper/6a0405dadbc836b87d827861.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa7a151e209131cea8108e.md>)

Recorded evaluation configuration: {"Pretraining Scale":"90K"}. This record does not assert independent reproduction.

### CoDAAR

Precision: 71.2. Result ID: 6a04544647f34ce924eae7f8.

[Reporting paper](<https://www.sota2.com/research/paper/6a0405dadbc836b87d827861.md>)

[Method origin paper](<https://www.sota2.com/research/paper/6a0405dadbc836b87d827861.md>)

Recorded evaluation configuration: {"Pretraining Scale":"90K"}. This record does not assert independent reproduction.

### DCID

Precision: 69.9. Result ID: 6a04544647f34ce924eae7f6.

[Reporting paper](<https://www.sota2.com/research/paper/6a0405dadbc836b87d827861.md>)

Recorded evaluation configuration: {"Pretraining Scale":"90K"}. This record does not assert independent reproduction.

### Baseline

Precision: 19.2. Result ID: 6a04544647f34ce924eae7f5.

[Reporting paper](<https://www.sota2.com/research/paper/6a0405dadbc836b87d827861.md>)

Recorded evaluation configuration: {"Pretraining Scale":"90K"}. This record does not assert independent reproduction.

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