Temporal Action Localization (Verb) on EPIC-Kitchens 100 (val)
33.1mAP@0.1AdaTAD
Evaluation Results
| Method | Links | ||||||
|---|---|---|---|---|---|---|---|
| AdaTADE2E=true, Backbone=VideoMAE-L2023.11 | 33.1 | 32.2 | 30.4 | 27.5 | 23.1 | 29.3 | |
| ActionFormerE2E=false, Backbone=VideoMAE-L2023.11 | 32.7 | 31.6 | 29.1 | 26.7 | 23.6 | 28.7 | |
| TriDetE2E=false, Backbone=SlowFast-R502023.11 | 28.6 | 27.4 | 26.1 | 24.2 | 20.8 | 25.4 | |
| ASLFeature=SlowFast2023.05 | 27.9 | — | 25.5 | — | 19.8 | 24.6 | |
| ASLE2E=false, Backbone=SlowFast-R502023.11 | 27.9 | — | 25.5 | — | 19.8 | 24.6 | |
| ActionFormerFeatures=SlowFast2022.02 | 26.6 | 25.4 | 24.2 | 22.3 | 19.1 | 23.5 | |
| ActionformerFeature=SlowFast2023.05 | 26.6 | — | 24.2 | — | 19.1 | 23.5 | |
| ActionFormerE2E=false, Backbone=SlowFast-R502023.11 | 26.6 | 25.4 | 24.2 | 22.3 | 19.1 | 23.5 | |
| AdaTADE2E=true, Backbone=SlowFast-R502023.11 | 26.5 | 25.7 | 23.9 | 21.7 | 17.6 | 23.1 | |
| G-TADFeatures=SlowFast2022.02 | 12.1 | 11 | 9.4 | 8.1 | 6.5 | 9.4 | |
| G-TADFeature=SlowFast2023.05 | 12.1 | — | 9.4 | — | 6.5 | 9.4 | |
| G-TADE2E=false, Backbone=SlowFast-R502023.11 | 12.1 | 11 | 9.4 | 8.1 | 6.5 | 9.4 | |
| AGT2021.01 | 12.01 | 10.25 | 8.15 | 7.12 | 6.14 | — | |
| BMNFeatures=SlowFast2022.02 | 10.8 | 9.8 | 8.4 | 7.1 | 5.6 | 8.4 | |
| BMNFeature=SlowFast2023.05 | 10.8 | — | 8.4 | — | 5.6 | 8.4 | |
| BMNE2E=false, Backbone=SlowFast-R502023.11 | 10.8 | 8.8 | 8.4 | 7.1 | 5.6 | 8.4 | |
| Damen et al.2021.01 | 10.51 | 9.24 | 7.67 | 6.4 | 5.12 | — | |
| AGT2021.01 | 7.78 | 6.92 | 5.53 | 4.22 | 3.86 | — | |
| Damen et al.2021.01 | 6.78 | 6.03 | 4.94 | 4.04 | 3.35 | — |