LV-VIS
Benchmarks
| Task Name | Dataset Name | SOTA Result | Trend | |
|---|---|---|---|---|
| Video Instance Segmentation | LV-VIS | AP30.3 | 7 | |
| Video Multimodal Interpretation | LV-VIS (val) | AP26 | 6 | |
| Video Captioning | LV-VIS | METEOR19.3 | 5 | |
| Controllable Video Segmentation | LV-VIS (test) | J&F Score87.8 | 3 |
Showing 4 of 4 rows