Video Grounding on MAD 1.0 (test)
11.26R@1 (IoU=0.3)HieraMamba
Evaluation results
| Method | Links | |||||||||||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| HieraMambaFeatures=CLIP ViT-B/322025.10 | 11.26 | — | — | — | — | — | 23.49 | — | — | — | 7.22 | 16.81 | — | — | — | 14.7 | — | |
| DeCafNetFeatures=CLIP ViT-B/322025.10 | 10.96 | — | — | — | — | — | 23.68 | — | — | — | 7.06 | 16.13 | — | — | — | 14.46 | — | |
| RGNetNaQ=false2023.12 | 9.48 | 12.43 | 25.12 | — | — | — | 18.72 | — | — | — | 5.61 | 10.86 | — | — | — | 13.7 | 17.8 | |
| RGNetNaQ=true2023.12 | 9.48 | 12.43 | 25.12 | — | — | — | 18.72 | — | — | — | 5.61 | 10.86 | — | — | — | 13.7 | 19.33 | |
| RGNetFeatures=CLIP ViT-B/322025.10 | 9.48 | — | — | — | — | — | 18.72 | — | — | — | 5.61 | 10.86 | — | — | — | 11.17 | — | |
| DenoiseLocfirst-stage model=true2023.04 | 9.08 | 11.59 | 30.35 | 41.44 | 66.07 | 73.62 | 23.33 | 31.57 | 49.9 | 55.68 | 5.63 | 14.03 | 18.69 | 29.12 | 32.51 | — | — | |
| SOONetNaQ=false2023.12 | 9 | 11.26 | 23.21 | — | — | — | 19.64 | — | — | — | 5.32 | 13.14 | — | — | — | 13.59 | 12.45 | |
| SOONetFeatures=CLIP ViT-B/322025.10 | 9 | — | — | — | — | — | 19.64 | — | — | — | 5.32 | 3.14 | — | — | — | 9.28 | — | |
| SnAGFeatures=CLIP ViT-B/322025.10 | 8.46 | — | — | — | — | — | 20.6 | — | — | — | 5.55 | 13.75 | — | — | — | 12.09 | — | |
| CONEfirst-stage model=true2023.04 | 6.87 | 8.9 | 20.51 | 27.2 | 43.36 | — | 16.11 | 21.53 | 34.73 | — | 4.1 | 9.59 | 12.82 | 20.56 | — | — | — | |
| CONENaQ=false2023.12 | 6.87 | 8.9 | 20.51 | — | — | — | 16.11 | — | — | — | 4.1 | 9.59 | — | — | — | 11.01 | 14.34 | |
| CONEFeatures=CLIP ViT-B/322025.10 | 6.87 | — | — | — | — | — | 16.11 | — | — | — | 4.1 | 9.59 | — | — | — | 9.17 | — | |
| Zero-shot CLIPfirst-stage model=true2023.04 | 4.65 | 9.3 | 18.96 | 24.3 | 39.79 | 47.35 | 13.06 | 17.73 | 32.23 | 39.58 | 2.16 | 7.4 | 11.09 | 23.21 | 29.68 | — | — | |
| M-GuideNaQ=false2023.12 | 4.65 | 9.3 | 18.96 | — | — | — | 13.06 | — | — | — | 2.16 | 7.4 | — | — | — | 9.26 | — | |
| VLG-Netfirst-stage model=true2023.04 | 4.28 | 5.6 | 16.07 | 23.64 | 45.35 | 55.59 | 13.14 | 19.86 | 39.77 | 49.38 | 2.48 | 8.78 | 13.72 | 30.22 | 39.12 | — | — | |
| Moment-DETRfirst-stage model=true2023.04 | 3.82 | 5.07 | 16.3 | 24.79 | 50.06 | 61.79 | 12.6 | 19.43 | 40.52 | 50.35 | 2.39 | 7.9 | 12.06 | 24.87 | 30.81 | — | — | |
| Zero-shot CLIPfirst-stage model=false2023.04 | 3.13 | 6.57 | 15.05 | 20.26 | 37.92 | 47.73 | 9.85 | 14.13 | 28.71 | 36.98 | 1.39 | 5.44 | 8.38 | 18.8 | 24.99 | — | — | |
| M-DETRNaQ=false2023.12 | 2.81 | 3.6 | 12.98 | — | — | — | 9.86 | — | — | — | 1.67 | 5.58 | — | — | — | 6.08 | 9.27 | |
| M-DETRFeatures=CLIP ViT-B/322025.10 | 2.81 | — | — | — | — | — | 9.86 | — | — | — | 1.67 | 5.58 | — | — | — | 4.98 | — | |
| VLG-NetNaQ=false2023.12 | 2.76 | 3.64 | 11.66 | — | — | — | 9.31 | — | — | — | 1.65 | 5.99 | — | — | — | 5.84 | — | |
| VLG-NetFeatures=CLIP ViT-B/322025.10 | 2.76 | — | — | — | — | — | 9.31 | — | — | — | 1.65 | 5.99 | — | — | — | 4.93 | — | |
| VLG-Netfirst-stage model=false2023.04 | 2.63 | 3.5 | 11.74 | 18.32 | 38.41 | 49.65 | 9.49 | 15.2 | 33.68 | 43.95 | 1.61 | 6.23 | 10.18 | 25.33 | 34.18 | — | — | |
| 2D-TANNaQ=false2023.12 | 2.52 | 3.22 | 11.9 | — | — | — | 9.25 | — | — | — | 1.58 | 5.69 | — | — | — | 5.69 | 6.07 | |
| 2D-TANFeatures=CLIP ViT-B/322025.10 | 2.52 | — | — | — | — | — | 9.25 | — | — | — | 1.58 | 5.69 | — | — | — | 4.76 | — | |
| DenoiseLocfirst-stage model=false2023.04 | 0.86 | 1.06 | 4.07 | 6.75 | 20.07 | 31.35 | 3.34 | 5.44 | 15.67 | 24.09 | 0.57 | 2.17 | 3.5 | 9.73 | 14.75 | — | — | |
| Moment-DETRfirst-stage model=false2023.04 | 0.24 | 0.31 | 1.52 | 2.79 | 11.08 | 19.65 | 1.14 | 2.06 | 7.97 | 14.29 | 0.16 | 0.68 | 1.2 | 4.71 | 8.46 | — | — |