Video Temporal Grounding on Charades-STA (R@1 and R@5 Metrics)
56.2R@1 (IoU=0.5)BM-DETR + Ours
Evaluation results
| Method | Links | ||||
|---|---|---|---|---|---|
| BM-DETR + OursSupervision=fully-supervised, Text Augmentation=false2026.05 | 56.2 | 33.51 | 92.15 | 60.92 | |
| G2L + OursSupervision=fully-supervised, Text Augmentation=false2026.05 | 55.77 | 32.97 | 91.38 | 60.39 | |
| BM-DETRSupervision=fully-supervised, Text Augmentation=false2026.05 | 54.42 | 33.84 | — | — | |
| Ours(Shapley)Type=WS2026.05 | 54.31 | 26.28 | 89.24 | 55.62 | |
| Ours(Banzhaf)Type=WS2026.05 | 54.17 | 26.46 | 88.93 | 55.79 | |
| DRNType=FS2026.05 | 53.09 | 31.75 | 89.06 | 60.05 | |
| DM2Type=WS2026.05 | 51.39 | 23.72 | — | — | |
| CPLType=WS2026.05 | 49.24 | 22.39 | 84.71 | 52.37 | |
| MMN + OursSupervision=fully-supervised, Text Augmentation=false2026.05 | 49.07 | 29.32 | 85.06 | 60.13 | |
| G2LSupervision=fully-supervised, Text Augmentation=false2026.05 | 47.91 | 28.42 | 84.8 | 59.33 | |
| MMNSupervision=fully-supervised, Text Augmentation=false2026.05 | 47.31 | 27.28 | 83.74 | 58.41 | |
| VCA + OursSupervision=weakly-supervised, Text Augmentation=false2026.05 | 40.95 | 20.31 | 80.42 | 39.26 | |
| 2D-TAN + OursSupervision=fully-supervised, Text Augmentation=false2026.05 | 40.27 | 24.95 | 82.96 | 53.28 | |
| 2DTANType=FS2026.05 | 39.81 | 23.25 | 79.33 | 51.15 | |
| 2D-TANSupervision=fully-supervised, Text Augmentation=false2026.05 | 39.81 | 23.25 | 79.33 | 52.15 | |
| LCNetType=WS2026.05 | 39.19 | 18.17 | 80.56 | 45.24 | |
| VCAType=WS2026.05 | 38.13 | 19.57 | 78.75 | 37.75 | |
| VCASupervision=weakly-supervised, Text Augmentation=false2026.05 | 38.13 | 19.57 | 78.75 | 37.75 | |
| ACNType=WS2026.05 | 37.02 | 15.26 | — | — | |
| MCMT + OursSupervision=weakly-supervised, Text Augmentation=false2026.05 | 36.81 | 17 | 78.59 | 45.27 | |
| MCMTSupervision=weakly-supervised, Text Augmentation=false2026.05 | 36.23 | 15.29 | — | — | |
| BM-DETR + OursSupervision=fully-supervised, Text Augmentation=true2026.05 | 35.75 | 28.74 | 75.13 | 47.82 | |
| CNM + OursSupervision=weakly-supervised, Text Augmentation=false2026.05 | 35.72 | 16.33 | 76.52 | 43.18 | |
| CNMType=WS2026.05 | 35.15 | 14.95 | — | — | |
| CNMSupervision=weakly-supervised, Text Augmentation=false2026.05 | 35.15 | 14.95 | — | — | |
| G2L + OursSupervision=fully-supervised, Text Augmentation=true2026.05 | 34.85 | 27.96 | 74.28 | 46.7 | |
| CRMType=WS2026.05 | 34.76 | 16.37 | — | — | |
| MARNType=WS2026.05 | 33.87 | 15.54 | 73.9 | 41.94 | |
| ICVCType=WS2026.05 | 31.02 | 16.53 | 77.53 | 41.91 | |
| WSTAN + OursSupervision=weakly-supervised, Text Augmentation=false2026.05 | 30.24 | 14.06 | 77.35 | 42.99 | |
| WSTANType=WS2026.05 | 29.35 | 12.28 | 76.13 | 41.53 | |
| WSTANSupervision=weakly-supervised, Text Augmentation=false2026.05 | 29.35 | 12.28 | 76.13 | 41.53 | |
| BM-DETRSupervision=fully-supervised, Text Augmentation=true2026.05 | 28.1 | 21.43 | 47.26 | 35.29 | |
| MMN + OursSupervision=fully-supervised, Text Augmentation=true2026.05 | 26.87 | 22.48 | 46.03 | 37.85 | |
| G2LSupervision=fully-supervised, Text Augmentation=true2026.05 | 26.54 | 19.85 | 48.06 | 36.7 | |
| MMNSupervision=fully-supervised, Text Augmentation=true2026.05 | 25.33 | 18.8 | 45.97 | 35.08 | |
| 2D-TAN + OursSupervision=fully-supervised, Text Augmentation=true2026.05 | 23.99 | 14.75 | 49.22 | 34.18 | |
| CTRLType=FS2026.05 | 23.63 | 8.89 | 58.92 | 29.52 | |
| SCNType=WS2026.05 | 23.58 | 9.97 | 71.8 | 38.87 | |
| 2D-TANSupervision=fully-supervised, Text Augmentation=true2026.05 | 20.18 | 11.35 | 47.05 | 33.82 | |
| VCA + OursSupervision=weakly-supervised, Text Augmentation=true2026.05 | 18.63 | 15.72 | 46.17 | 23.88 | |
| VCASupervision=weakly-supervised, Text Augmentation=true2026.05 | 17.87 | 12.39 | 45.7 | 22.13 | |
| MCMT + OursSupervision=weakly-supervised, Text Augmentation=true2026.05 | 17.53 | 13.24 | 46.82 | 22.87 | |
| CNM + OursSupervision=weakly-supervised, Text Augmentation=true2026.05 | 16.83 | 12.05 | 45.6 | 21.64 | |
| MCMTSupervision=weakly-supervised, Text Augmentation=true2026.05 | 15.75 | 9.84 | 44.21 | 19.67 | |
| CNMSupervision=weakly-supervised, Text Augmentation=true2026.05 | 14.34 | 9.65 | 43.88 | 18.79 | |
| WSTAN + OursSupervision=weakly-supervised, Text Augmentation=true2026.05 | 10.77 | 6.92 | 37.4 | 13.88 | |
| WSTANSupervision=weakly-supervised, Text Augmentation=true2026.05 | 8.15 | 5.43 | 35.27 | 11.86 |