VidSTG
Benchmarks
| Task Name | Dataset Name | SOTA Result | Trend | |
|---|---|---|---|---|
| Spatio-temporal Video Grounding | VidSTG Interrogative Sentences (test) | m_vIoU31.3 | 47 | |
| Spatio-temporal Video Grounding | VidSTG Declarative Sentences (test) | m_vIoU37.2 | 24 | |
| Spatio-Temporal Video Grounding | VidSTG Declarative Sentences | m_vIoU34.4 | 20 | |
| Spatio-temporal Video Grounding | VidSTG (test) | m_vIoU34.67 | 16 | |
| Spatio-Temporal Video Grounding | VidSTG Declarative (test) | m_vIoU34 | 14 | |
| Spatio-temporal video grounding | VidSTG (test) | Declarative m_vIoU34.8 | 11 | |
| Spatio-Temporal Video Grounding | VidSTG Declarative Sentences 1.0 (test) | Mean vIoU34 | 9 | |
| Dense Video Object Captioning | VidSTG | CapA Score55.4 | 8 | |
| Spatio-Temporal Video Grounding | VidSTG Interrogative Sentence | m_vIoU29.5 | 8 | |
| Spatio-temporal video grounding | VidSTG (leaderboard) | mtIoU31.35 | 7 | |
| Video Spatio-Temporal Grounding | VidSTG Declarative Sentences Mixed-Quality (test) | Mean Temporal IoU (mIoU)50.81 | 7 | |
| Video Spatio-Temporal Grounding | VidSTG HQ and LQ Interrogative Sentences v1 (test) | Delta Mean Temporal IoU0.71 | 6 | |
| Video Spatio-Temporal Grounding | VidSTG HQ and LQ Declarative Sentences v1 (test) | Delta Mean Temporal IoU1.17 | 6 | |
| Dense Video Object Captioning | VidSTG (test) | CapA43.9 | 5 | |
| Spatio-temporal video grounding | VidSTG Interrogative | m_tIoU47.3 | 3 | |
| Spatio-temporal video grounding | VidSTG Declarative | m_tIoU49 | 3 |
Showing 16 of 16 rows