AVISeg
Benchmarks
| Task Name | Dataset Name | SOTA Result | Trend | |
|---|---|---|---|---|
| Video Instance Segmentation | AVISeg (test) | FSLA42.78 | 7 | |
| Audio-referred visual grounding | AVISeg (test) | FSLA18.55 | 4 | |
| Audio-Visual Sound Segmentation | AVISeg (test) | FSLA39.49 | 2 |
Showing 3 of 3 rows
| Task Name | Dataset Name | SOTA Result | Trend | |
|---|---|---|---|---|
| Video Instance Segmentation | AVISeg (test) | FSLA42.78 | 7 | |
| Audio-referred visual grounding | AVISeg (test) | FSLA18.55 | 4 | |
| Audio-Visual Sound Segmentation | AVISeg (test) | FSLA39.49 | 2 |