# Audio-Visual Generalized Zero-Shot Learning on UCF-GZSL (main feature test)

Source: [Audio-Visual Generalized Zero-Shot Learning on UCF-GZSL (main feature test)](<https://www.sota2.com/research/sota/audio-visual-generalized-zero-shot-learning-on-ucf-gzsl-main-feature-test>)

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

Data updated: 2026-02-27T09:10:06.890Z

Evaluation of Audio-Visual Generalized Zero-Shot Learning performance using the main feature set on the test split of the UCF-GZSL dataset. Metrics reported include 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 Generalized Zero-Shot Learning |
| Dataset (including any stated split) | UCF-GZSL main feature (test) |
| Metric | S (Seen Accuracy) |
| Unit | PERCENT |
| Direction | Higher is better |
| Results loaded | 16 of 16 |
| 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 (Seen Accuracy)](<https://www.sota2.com/research/sota/audio-visual-generalized-zero-shot-learning-on-ucf-gzsl-main-feature-test.md?metric=S%20(Seen%20Accuracy)>): Higher is better; unit: PERCENT.

- [U (Unseen Accuracy)](<https://www.sota2.com/research/sota/audio-visual-generalized-zero-shot-learning-on-ucf-gzsl-main-feature-test.md?metric=U%20(Unseen%20Accuracy)>): Higher is better; unit: PERCENT.

- [HM (Harmonic Mean)](<https://www.sota2.com/research/sota/audio-visual-generalized-zero-shot-learning-on-ucf-gzsl-main-feature-test.md?metric=HM%20(Harmonic%20Mean)>): Higher is better; unit: PERCENT.

- [ZSL Score](<https://www.sota2.com/research/sota/audio-visual-generalized-zero-shot-learning-on-ucf-gzsl-main-feature-test.md?metric=ZSL%20Score>): Higher is better; unit: PERCENT.

## Recorded results

| Method | S (Seen Accuracy) | Result date | Report paper |
| --- | --- | --- | --- |
| KDA | 80.03 | Not recorded | 68fa72f61e209131cea59938 |
| AVGZSLNet | 74.79 | Not recorded | 68fa72f61e209131cea59938 |
| Hyper-multiple | 74.26 | Not recorded | 68fa72f61e209131cea59938 |
| TCaF | 67.14 | Not recorded | 68fa72f61e209131cea59938 |
| AVCA | 63.15 | Not recorded | 68fa72f61e209131cea59938 |
| Hyper-multiple | 63.08 | Not recorded | 68fa71791e209131cea5176b |
| Hyper-alignment | 57.28 | Not recorded | 68fa71791e209131cea5176b |
| ACFS | 54.57 | Not recorded | 68fa72f61e209131cea59938 |
| Hyper-single | 52.67 | Not recorded | 68fa71791e209131cea5176b |
| AVGZSLNet | 52.52 | Not recorded | 68fa71791e209131cea5176b |
| AVCA | 51.53 | Not recorded | 68fa71791e209131cea5176b |
| CJME | 33.89 | Not recorded | 68fa72f61e209131cea59938 |
| DEVISE | 29.58 | Not recorded | 68fa72f61e209131cea59938 |
| CJME | 26.04 | Not recorded | 68fa71791e209131cea5176b |
| SJE | 19.39 | Not recorded | 68fa72f61e209131cea59938 |
| APN | 13.54 | Not recorded | 68fa72f61e209131cea59938 |

### KDA

S (Seen Accuracy): 80.03. Result ID: 69a15f6935dfcabb00e69d8b.

[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"}. This record does not assert independent reproduction.

### AVGZSLNet

S (Seen Accuracy): 74.79. Result ID: 69a15f6935dfcabb00e69d85.

[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"}. This record does not assert independent reproduction.

### Hyper-multiple

S (Seen Accuracy): 74.26. Result ID: 69a15f6935dfcabb00e69d8a.

[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"}. This record does not assert independent reproduction.

### TCaF

S (Seen Accuracy): 67.14. Result ID: 69a15f6935dfcabb00e69d88.

[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"}. This record does not assert independent reproduction.

### AVCA

S (Seen Accuracy): 63.15. Result ID: 69a15f6935dfcabb00e69d87.

[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"}. This record does not assert independent reproduction.

### Hyper-multiple

S (Seen Accuracy): 63.08. Result ID: 6991d0bd3a6c3148490ac1c6.

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

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

Recorded evaluation configuration: {"Feature type":"main","Number of adaptive curvatures (Ne)":3}. This record does not assert independent reproduction.

### Hyper-alignment

S (Seen Accuracy): 57.28. Result ID: 6991d0bd3a6c3148490ac1c4.

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

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

Recorded evaluation configuration: {"Feature type":"main","Curvature (c)":-0.2}. This record does not assert independent reproduction.

### ACFS

S (Seen Accuracy): 54.57. Result ID: 69a15f6935dfcabb00e69d89.

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

Recorded evaluation configuration: {"Venue":"IJCNN’23"}. This record does not assert independent reproduction.

### Hyper-single

S (Seen Accuracy): 52.67. Result ID: 6991d0bd3a6c3148490ac1c5.

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

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

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

### AVGZSLNet

S (Seen Accuracy): 52.52. Result ID: 6991d0bd3a6c3148490ac1c2.

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

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

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

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

### AVCA

S (Seen Accuracy): 51.53. Result ID: 6991d0bd3a6c3148490ac1c3.

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

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

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

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

### CJME

S (Seen Accuracy): 33.89. Result ID: 69a15f6935dfcabb00e69d84.

[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"}. This record does not assert independent reproduction.

### DEVISE

S (Seen Accuracy): 29.58. Result ID: 69a15f6935dfcabb00e69d82.

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

Recorded evaluation configuration: {"Venue":"NeurIPS’13"}. This record does not assert independent reproduction.

### CJME

S (Seen Accuracy): 26.04. Result ID: 6991d0bd3a6c3148490ac1c1.

[Reporting paper](<https://www.sota2.com/research/paper/68fa71791e209131cea5176b.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: {"Feature type":"main"}. This record does not assert independent reproduction.

### SJE

S (Seen Accuracy): 19.39. Result ID: 69a15f6935dfcabb00e69d83.

[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"}. This record does not assert independent reproduction.

### APN

S (Seen Accuracy): 13.54. Result ID: 69a15f6935dfcabb00e69d86.

[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"}. This record does not assert independent reproduction.

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