# Audio-Visual Semantic Segmentation on AVSS

Source: [Audio-Visual Semantic Segmentation on AVSS](<https://www.sota2.com/research/sota/audio-visual-semantic-segmentation-on-avss>)

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

Data updated: 2026-05-12T09:51:10.661Z

Evaluation of Audio-Visual Semantic Segmentation performance on the AVSS dataset, reporting MJ and MF 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 Semantic Segmentation |
| Dataset (including any stated split) | AVSS |
| Metric | MJ Score |
| Unit | PERCENT |
| Direction | Higher is better |
| Results loaded | 7 of 7 |
| 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

- [MJ Score](<https://www.sota2.com/research/sota/audio-visual-semantic-segmentation-on-avss.md?metric=MJ%20Score>): Higher is better; unit: PERCENT.

- [MF Score](<https://www.sota2.com/research/sota/audio-visual-semantic-segmentation-on-avss.md?metric=MF%20Score>): Higher is better; unit: PERCENT.

## Recorded results

| Method | MJ Score | Result date | Report paper |
| --- | --- | --- | --- |
| SelM | 31.9 | Not recorded | 6a02b403dbc836b87d8245ce |
| LightAVSeg | 30.6 | Not recorded | 6a02b403dbc836b87d8245ce |
| AVSegFormer | 24.9 | Not recorded | 6a02b403dbc836b87d8245ce |
| SelM | 20.6 | Not recorded | 6a02b403dbc836b87d8245ce |
| AVSBench | 20.2 | Not recorded | 6a02b403dbc836b87d8245ce |
| AVSegFormer | 15.8 | Not recorded | 6a02b403dbc836b87d8245ce |
| AVSBench | 10 | Not recorded | 6a02b403dbc836b87d8245ce |

### SelM

MJ Score: 31.9. Result ID: 6a02f80e47f34ce924e62dd7.

[Reporting paper](<https://www.sota2.com/research/paper/6a02b403dbc836b87d8245ce.md>)

Recorded evaluation configuration: {"Visual Backbone":"R50","Audio Backbone":"VGGish"}. This record does not assert independent reproduction.

### LightAVSeg

MJ Score: 30.6. Result ID: 6a02f80e47f34ce924e62ddb.

[Reporting paper](<https://www.sota2.com/research/paper/6a02b403dbc836b87d8245ce.md>)

[Method origin paper](<https://www.sota2.com/research/paper/6a02b403dbc836b87d8245ce.md>)

Recorded evaluation configuration: {"Visual Backbone":"Sea","Audio Backbone":"MNetV2"}. This record does not assert independent reproduction.

### AVSegFormer

MJ Score: 24.9. Result ID: 6a02f80e47f34ce924e62dd6.

[Reporting paper](<https://www.sota2.com/research/paper/6a02b403dbc836b87d8245ce.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa71791e209131cea5174e.md>)

Recorded evaluation configuration: {"Visual Backbone":"R50","Audio Backbone":"VGGish"}. This record does not assert independent reproduction.

### SelM

MJ Score: 20.6. Result ID: 6a02f80e47f34ce924e62dda.

[Reporting paper](<https://www.sota2.com/research/paper/6a02b403dbc836b87d8245ce.md>)

Recorded evaluation configuration: {"Visual Backbone":"Sea","Audio Backbone":"MNetV2"}. This record does not assert independent reproduction.

### AVSBench

MJ Score: 20.2. Result ID: 6a02f80e47f34ce924e62dd5.

[Reporting paper](<https://www.sota2.com/research/paper/6a02b403dbc836b87d8245ce.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6e8e1e209131cea408f0.md>)

Recorded evaluation configuration: {"Visual Backbone":"R50","Audio Backbone":"VGGish"}. This record does not assert independent reproduction.

### AVSegFormer

MJ Score: 15.8. Result ID: 6a02f80e47f34ce924e62dd9.

[Reporting paper](<https://www.sota2.com/research/paper/6a02b403dbc836b87d8245ce.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa71791e209131cea5174e.md>)

Recorded evaluation configuration: {"Visual Backbone":"Sea","Audio Backbone":"MNetV2"}. This record does not assert independent reproduction.

### AVSBench

MJ Score: 10. Result ID: 6a02f80e47f34ce924e62dd8.

[Reporting paper](<https://www.sota2.com/research/paper/6a02b403dbc836b87d8245ce.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6e8e1e209131cea408f0.md>)

Recorded evaluation configuration: {"Visual Backbone":"Sea","Audio Backbone":"MNetV2"}. This record does not assert independent reproduction.

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