| Task Name | Dataset Name | SOTA Result | Trend | |
|---|---|---|---|---|
| Audio-to-Video temporal grounding | ChronusAV | BLEU-41.4 | 17 | |
| Video-to-Audio temporal grounding | ChronusAV | BLEU-43.9 | 17 | |
| Text-to-Audio temporal grounding | ChronusAV | BLEU-47.4 | 17 | |
| Text-to-Video (T2V) Temporally Grounded Generation | ChronusAV | BLEU-41.4 | 9 | |
| Video-to-Text (V2T) Temporally Grounded Generation | ChronusAV | R@0.568.4 | 9 | |
| Dense video captioning | ChronusAV | F1 Score63.2 | 9 | |
| Audio-to-Text temporal grounding | ChronusAV | Recall@IoU=0.590.5 | 8 | |
| Text-to-Video temporal grounding | ChronusAV | BLEU-41.16 | 8 | |
| Video-to-Text temporal grounding | ChronusAV | Recall@IoU=0.563.15 | 8 | |
| Audio-to-Text (A2T) Temporally Grounded Generation | ChronusAV | Metric- | 0 |