| Task Name | Dataset Name | SOTA Result | Trend | |
|---|---|---|---|---|
| Unsupervised Video Object Segmentation | Video Dataset 11-frame sequences | mBO-V46.9 | 7 | |
| Unsupervised Video Object Segmentation | Video Dataset 7-frame sequences | mBO-V48.5 | 7 | |
| Controllable Video Segmentation and Captioning | Video Dataset | FPS10.61 | 6 | |
| Video Generation | 6M video dataset | FVD47.81 | 6 | |
| Scene Editing | synthetic video dataset | PSNR29.186 | 5 | |
| Predicted Occupancy Grid Estimation | Video Dataset YouTube car-bicycle crash scenarios (test) | Epsilon Error (Low)0.0576 | 3 | |
| Intra-creator embedding similarity | Video Dataset Overall | Intra-creator Embedding Similarity77 | 2 | |
| Intra-creator embedding similarity | Video Dataset Same & Next Day | Intra-creator Similarity91 | 2 | |
| Intra-creator embedding similarity | Video Dataset (Same Day) | Intra-creator Similarity91 | 2 |