# Audio-visual Recognition on VGGSound GZSL

Source: [Audio-visual Recognition on VGGSound GZSL](<https://www.sota2.com/research/sota/audio-visual-recognition-on-vggsound-gzsl>)

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

Data updated: 2026-02-27T09:10:06.921Z

Evaluation of Audio-visual Recognition performance on the VGGSound dataset configured for Generalized Zero-Shot Learning (GZSL), typically measured using S, U, HM, and ZSL scores.

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-visual Recognition |
| Dataset (including any stated split) | VGGSound GZSL |
| Metric | S Score |
| Unit | SCALAR |
| Direction | Higher is better |
| Results loaded | 14 of 14 |
| 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

- [S Score](<https://www.sota2.com/research/sota/audio-visual-recognition-on-vggsound-gzsl.md?metric=S%20Score>): Higher is better; unit: SCALAR.

- [U Score](<https://www.sota2.com/research/sota/audio-visual-recognition-on-vggsound-gzsl.md?metric=U%20Score>): Higher is better; unit: SCALAR.

- [HM Score](<https://www.sota2.com/research/sota/audio-visual-recognition-on-vggsound-gzsl.md?metric=HM%20Score>): Higher is better; unit: SCALAR.

- [ZSL Score](<https://www.sota2.com/research/sota/audio-visual-recognition-on-vggsound-gzsl.md?metric=ZSL%20Score>): Higher is better; unit: SCALAR.

## Recorded results

| Method | S Score | Result date | Report paper |
| --- | --- | --- | --- |
| SJE | 48.33 | Not recorded | 68fa72f61e209131cea59938 |
| DEVISE | 36.22 | Not recorded | 68fa72f61e209131cea59938 |
| KDA | 24.1 | Not recorded | 68fa72f61e209131cea59938 |
| VIB-GZSL | 18.42 | Not recorded | 68fa72f61e209131cea59938 |
| AVGZSLNet | 18.05 | Not recorded | 68fa72f61e209131cea59938 |
| MDFT | 16.14 | Not recorded | 68fa72f61e209131cea59938 |
| ACFS | 15.2 | Not recorded | 68fa72f61e209131cea59938 |
| Hyper-multiple | 15.02 | Not recorded | 68fa72f61e209131cea59938 |
| AVCA | 14.9 | Not recorded | 68fa72f61e209131cea59938 |
| f-VAEGAN-D2 | 12.77 | Not recorded | 68fa72f61e209131cea59938 |
| TCaF | 9.64 | Not recorded | 68fa72f61e209131cea59938 |
| CJME | 8.69 | Not recorded | 68fa72f61e209131cea59938 |
| APN | 7.48 | Not recorded | 68fa72f61e209131cea59938 |
| ALE | 0.28 | Not recorded | 68fa72f61e209131cea59938 |

### SJE

S Score: 48.33. Result ID: 69a15f6935dfcabb00e69d68.

[Reporting paper](<https://www.sota2.com/research/paper/68fa72f61e209131cea59938.md>)

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

Recorded evaluation configuration: {"Venue":"CVPR’20","Feature Type":"main feature"}. This record does not assert independent reproduction.

### DEVISE

S Score: 36.22. Result ID: 69a15f6935dfcabb00e69d66.

[Reporting paper](<https://www.sota2.com/research/paper/68fa72f61e209131cea59938.md>)

Recorded evaluation configuration: {"Venue":"NeurIPS’13","Feature Type":"main feature"}. This record does not assert independent reproduction.

### KDA

S Score: 24.1. Result ID: 69a15f6935dfcabb00e69d73.

[Reporting paper](<https://www.sota2.com/research/paper/68fa72f61e209131cea59938.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa72f61e209131cea59938.md>)

[Implementation](<https://github.com/chenhaoxing/KDA>)

Recorded evaluation configuration: {"Venue":"Ours","Feature Type":"main feature"}. This record does not assert independent reproduction.

### VIB-GZSL

S Score: 18.42. Result ID: 69a15f6935dfcabb00e69d6f.

[Reporting paper](<https://www.sota2.com/research/paper/68fa72f61e209131cea59938.md>)

Recorded evaluation configuration: {"Venue":"ICME’23","Feature Type":"main feature"}. This record does not assert independent reproduction.

### AVGZSLNet

S Score: 18.05. Result ID: 69a15f6935dfcabb00e69d6b.

[Reporting paper](<https://www.sota2.com/research/paper/68fa72f61e209131cea59938.md>)

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

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

Recorded evaluation configuration: {"Venue":"WACV’21","Feature Type":"main feature"}. This record does not assert independent reproduction.

### MDFT

S Score: 16.14. Result ID: 69a15f6935dfcabb00e69d72.

[Reporting paper](<https://www.sota2.com/research/paper/68fa72f61e209131cea59938.md>)

Recorded evaluation configuration: {"Venue":"ACM MM’23","Feature Type":"main feature"}. This record does not assert independent reproduction.

### ACFS

S Score: 15.2. Result ID: 69a15f6935dfcabb00e69d70.

[Reporting paper](<https://www.sota2.com/research/paper/68fa72f61e209131cea59938.md>)

Recorded evaluation configuration: {"Venue":"IJCNN’23","Feature Type":"main feature"}. This record does not assert independent reproduction.

### Hyper-multiple

S Score: 15.02. Result ID: 69a15f6935dfcabb00e69d71.

[Reporting paper](<https://www.sota2.com/research/paper/68fa72f61e209131cea59938.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa71791e209131cea5176b.md>)

Recorded evaluation configuration: {"Venue":"ICCV’23","Feature Type":"main feature"}. This record does not assert independent reproduction.

### AVCA

S Score: 14.9. Result ID: 69a15f6935dfcabb00e69d6d.

[Reporting paper](<https://www.sota2.com/research/paper/68fa72f61e209131cea59938.md>)

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

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

Recorded evaluation configuration: {"Venue":"CVPR’22","Feature Type":"main feature"}. This record does not assert independent reproduction.

### f-VAEGAN-D2

S Score: 12.77. Result ID: 69a15f6935dfcabb00e69d69.

[Reporting paper](<https://www.sota2.com/research/paper/68fa72f61e209131cea59938.md>)

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

Recorded evaluation configuration: {"Venue":"CVPR’19","Feature Type":"main feature"}. This record does not assert independent reproduction.

### TCaF

S Score: 9.64. Result ID: 69a15f6935dfcabb00e69d6e.

[Reporting paper](<https://www.sota2.com/research/paper/68fa72f61e209131cea59938.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6d191e209131cea37ba4.md>)

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

Recorded evaluation configuration: {"Venue":"ECCV’22","Feature Type":"main feature"}. This record does not assert independent reproduction.

### CJME

S Score: 8.69. Result ID: 69a15f6935dfcabb00e69d6a.

[Reporting paper](<https://www.sota2.com/research/paper/68fa72f61e209131cea59938.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: {"Venue":"WACV’20","Feature Type":"main feature"}. This record does not assert independent reproduction.

### APN

S Score: 7.48. Result ID: 69a15f6935dfcabb00e69d6c.

[Reporting paper](<https://www.sota2.com/research/paper/68fa72f61e209131cea59938.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6c281e209131cea326a1.md>)

Recorded evaluation configuration: {"Venue":"IJCV’22","Feature Type":"main feature"}. This record does not assert independent reproduction.

### ALE

S Score: 0.28. Result ID: 69a15f6935dfcabb00e69d67.

[Reporting paper](<https://www.sota2.com/research/paper/68fa72f61e209131cea59938.md>)

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

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

Recorded evaluation configuration: {"Venue":"T-PAMI’15","Feature Type":"main feature"}. This record does not assert independent reproduction.

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