Noun Action Localization on Epic-Kitchens-100
35mAP@0.1ActionFormer + TAdaFormer-L/14
Evaluation Results
| Method | Links | ||||||
|---|---|---|---|---|---|---|---|
| ActionFormer + TAdaFormer-L/14Model=ActionFormer + TAdaFormer-L/142023.08 | 35 | 33.42 | 30.98 | 27.32 | 22.36 | 29.82 | |
| ActionVLM-L-3BVision=VideoMAEv1-L, E2E=true2026.01 | 32.8 | 32.1 | 30.7 | 28.2 | 26.1 | 30 | |
| AdaTADVision=VideoMAEv1-L, E2E=true2026.01 | 32.4 | 31.6 | 30.1 | 27.4 | 24.6 | 29.3 | |
| ActionFormerVision=VideoMAEv1-L, E2E=false2026.01 | 31.3 | 29.7 | 27.2 | 25.3 | 21.3 | 26.9 | |
| ActionFormer + TAdaConvNeXt-SModel=ActionFormer + TAdaConvNeXt-S2023.08 | 29.21 | 27.94 | 26.22 | 23.54 | 18.73 | 25.13 | |
| ActionFormer + SlowFast & ViViTModel=ActionFormer + SlowFast & ViViT2023.08 | 28.61 | 27.14 | 24.92 | 22.13 | 18.69 | 24.3 | |
| BMN + TAdaFormer-L/14Model=BMN + TAdaFormer-L/142023.08 | 27.75 | 26.28 | 24.51 | 21.86 | 17.97 | 23.67 | |
| ActionFormerVision=SlowFast, E2E=false2026.01 | 25.8 | 24.7 | 22.8 | 20.8 | 17.5 | 22.3 | |
| ActionFormer + SlowFastModel=ActionFormer + SlowFast2023.08 | 25.21 | 24.11 | 22.66 | 20.47 | 16.97 | 21.88 | |
| BMN + TAdaConvNeXt-SModel=BMN + TAdaConvNeXt-S2023.08 | 21.9 | 20.92 | 19.33 | 17.22 | 14.68 | 18.81 | |
| BMN + TAda2DModel=BMN + TAda2D2023.08 | 20.54 | 19.32 | 17.94 | 15.77 | 13.39 | 17.39 | |
| BMN + TSNModel=BMN + TSN2023.08 | 15.11 | 14.15 | 12.78 | 10.94 | 8.89 | 12.37 |