# Generalized Zero-Shot Video Classification on VGGSound

Source: [Generalized Zero-Shot Video Classification on VGGSound](<https://www.sota2.com/research/sota/generalized-zero-shot-video-classification-on-vggsound>)

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

Data updated: 2026-02-27T07:10:54.537Z

Evaluation of video classification models on the VGGSound dataset under Generalized Zero-Shot Learning (GZSL) conditions, typically measured using metrics like Seen (S), Unseen (U), and Harmonic Mean (HM) performance.

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 Classification |
| Dataset (including any stated split) | VGGSound GZSL |
| Metric | Seen Accuracy |
| Unit | PERCENT |
| Direction | Higher is better |
| Results loaded | 8 of 8 |
| 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

- [Seen Accuracy](<https://www.sota2.com/research/sota/generalized-zero-shot-video-classification-on-vggsound.md?metric=Seen%20Accuracy>): Higher is better; unit: PERCENT.

- [Unseen Score](<https://www.sota2.com/research/sota/generalized-zero-shot-video-classification-on-vggsound.md?metric=Unseen%20Score>): Higher is better; unit: SCALAR.

- [Harmonic Mean](<https://www.sota2.com/research/sota/generalized-zero-shot-video-classification-on-vggsound.md?metric=Harmonic%20Mean>): Higher is better; unit: PERCENT.

## Recorded results

| Method | Seen Accuracy | Result date | Report paper |
| --- | --- | --- | --- |
| SJE | 48.33 | Not recorded | 68fa6c341e209131cea32cb4 |
| DEVISE | 36.22 | Not recorded | 68fa6c341e209131cea32cb4 |
| AVGZSLNet | 18.05 | Not recorded | 68fa6c341e209131cea32cb4 |
| AVCA | 14.9 | Not recorded | 68fa6c341e209131cea32cb4 |
| f-VAEGAN-D2 | 12.77 | Not recorded | 68fa6c341e209131cea32cb4 |
| CJME | 8.69 | Not recorded | 68fa6c341e209131cea32cb4 |
| APN | 7.48 | Not recorded | 68fa6c341e209131cea32cb4 |
| ALE | 0.28 | Not recorded | 68fa6c341e209131cea32cb4 |

### SJE

Seen Accuracy: 48.33. Result ID: 69a1437e35dfcabb00e5dece.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6c341e209131cea32cb4.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa62641e209131ce9f90f8.md>)

Recorded evaluation configuration: {"Method type":"ZSL"}. This record does not assert independent reproduction.

### DEVISE

Seen Accuracy: 36.22. Result ID: 69a1437e35dfcabb00e5decf.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6c341e209131cea32cb4.md>)

Recorded evaluation configuration: {"Method type":"ZSL"}. This record does not assert independent reproduction.

### AVGZSLNet

Seen Accuracy: 18.05. Result ID: 69a1437e35dfcabb00e5ded3.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6c341e209131cea32cb4.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa68c11e209131cea1e112.md>)

[Implementation](<https://github.com/krantiparida/AudioSetZSL>)

Recorded evaluation configuration: {"Method type":"Audio-visual ZSL"}. This record does not assert independent reproduction.

### AVCA

Seen Accuracy: 14.9. Result ID: 69a1437e35dfcabb00e5ded4.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6c341e209131cea32cb4.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6c341e209131cea32cb4.md>)

[Implementation](<https://github.com/ExplainableML/AVCA-GZSL>)

Recorded evaluation configuration: {"Method type":"Audio-visual ZSL"}. This record does not assert independent reproduction.

### f-VAEGAN-D2

Seen Accuracy: 12.77. Result ID: 69a1437e35dfcabb00e5ded1.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6c341e209131cea32cb4.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa65821e209131cea0aacd.md>)

Recorded evaluation configuration: {"Method type":"ZSL"}. This record does not assert independent reproduction.

### CJME

Seen Accuracy: 8.69. Result ID: 69a1437e35dfcabb00e5ded2.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6c341e209131cea32cb4.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa66931e209131cea1106d.md>)

[Implementation](<https://www.cse.iitk.ac.in/users/kranti/avzsl.html>)

Recorded evaluation configuration: {"Method type":"Audio-visual ZSL"}. This record does not assert independent reproduction.

### APN

Seen Accuracy: 7.48. Result ID: 69a1437e35dfcabb00e5ded0.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6c341e209131cea32cb4.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa69eb1e209131cea24ee0.md>)

Recorded evaluation configuration: {"Method type":"ZSL"}. This record does not assert independent reproduction.

### ALE

Seen Accuracy: 0.28. Result ID: 69a1437e35dfcabb00e5decd.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6c341e209131cea32cb4.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa62d31e209131ce9fb5fb.md>)

[Implementation](<https://code.google.com/p/word2vec/>)

Recorded evaluation configuration: {"Method type":"ZSL"}. This record does not assert independent reproduction.

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