| temporal-sentence-grounding-on-activitynet-captions-temporal-localization-val-2 | F2G (Qwen3-VL-8B) (extra data) | #3 | mIoU: 45.7R1@0.5: 46.1R1@0.7: 28.4 |
| temporal-sentence-grounding-on-activitynet-timelens | F2G (Qwen3-VL-8B, TimeLens-100K) (extra data) | #7 | mIoU: 54.1R@1 IoU=0.3: 69.8R@1 IoU=0.5: 59.4R@1 IoU=0.7: 42.3 |
| temporal-sentence-grounding-on-charades-timelens | F2G (Qwen3-VL-8B, TimeLens-100K) (extra data) | #7 | mIoU: 54.9R1@0.5: 63.1R1@0.7: 36.3R1@0.3: 74.2 |
| temporal-sentence-grounding-on-qvhighlights-timelens-validation | F2G (Qwen3-VL-8B, TimeLens-100K) (extra data) | #9 | mIoU: 64.1R@1 IoU=0.3: 79.6R@1 IoU=0.5: 70.4R@1 IoU=0.7: 54.5 |
| moment-retrieval-on-charades-sta | F2G (Qwen3-VL-8B, zero-shot) (extra data) | #56 | R@1 IoU=0.5: 50.4R@1 IoU=0.7: 25.7R@1 IoU=0.3: 71.3mIoU: 47.2 |