Action Recognition on Epic-Kitchens (test)
63.24Average ScoreSimMMDG
Evaluation results
| Method | Links | ||||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|
| SimMMDGVideo Backbone=SlowFast, Audio Backbone=ResNet-182023.10 | 63.24 | — | — | — | — | — | — | 57.93 | 65.47 | 66.32 | |
| Supervised TargetBackbone=I3D2021.10 | 61.5 | 57 | 57 | 64 | 64 | 63.7 | 63.7 | — | — | — | |
| RNA-NetVideo Backbone=SlowFast, Audio Backbone=ResNet-182023.10 | 57.51 | — | — | — | — | — | — | 52.18 | 59.47 | 60.88 | |
| SimMMDGVideo Backbone=I3D, Audio Backbone=BN-Inception2023.10 | 56.73 | — | — | — | — | — | — | 54.25 | 58.67 | 57.28 | |
| MM-SADAVideo Backbone=SlowFast, Audio Backbone=ResNet-182023.10 | 56.25 | — | — | — | — | — | — | 49.2 | 60.4 | 59.14 | |
| SimMMDGModality=Video + Audio, Setting=Single-source DG, Backbone=SlowFast + ResNet-182023.10 | 54.84 | 51.49 | 49.88 | 54 | 60.53 | 52.26 | 60.88 | — | — | — | |
| DeepAllVideo Backbone=SlowFast, Audio Backbone=ResNet-182023.10 | 53.34 | — | — | — | — | — | — | 47.13 | 55.73 | 57.17 | |
| DeepAllModality=Video + Audio, Setting=Single-source DG, Backbone=SlowFast + ResNet-182023.10 | 51.24 | 44.6 | 48.05 | 52.27 | 56.67 | 51.75 | 54.11 | — | — | — | |
| RNA-NetVideo Backbone=I3D, Audio Backbone=BN-Inception2023.10 | 51.06 | — | — | — | — | — | — | 45.65 | 51.64 | 55.88 | |
| MM-SADAModality=Video + Audio, Setting=Single-source DG, Backbone=SlowFast + ResNet-182023.10 | 50.97 | 51.49 | 42.99 | 50.67 | 54 | 50.1 | 56.57 | — | — | — | |
| RNA-NetModality=Video + Audio, Setting=Single-source DG, Backbone=SlowFast + ResNet-182023.10 | 49.75 | 43.68 | 49.66 | 45.6 | 55.87 | 46.3 | 57.39 | — | — | — | |
| MM-SADAVideo Backbone=I3D, Audio Backbone=BN-Inception2023.10 | 48.13 | — | — | — | — | — | — | 39.79 | 52.73 | 51.87 | |
| IBN-NetVideo Backbone=I3D, Audio Backbone=BN-Inception2023.10 | 47.55 | — | — | — | — | — | — | 44.46 | 49.21 | 48.97 | |
| AVSAVideo Backbone=I3D, Audio Backbone=BN-Inception2023.10 | 47.32 | — | — | — | — | — | — | 42.78 | 47.38 | 51.79 | |
| Gradient BlendingVideo Backbone=I3D, Audio Backbone=BN-Inception2023.10 | 47.27 | — | — | — | — | — | — | 41.97 | 48.4 | 51.43 | |
| Co-AttentionVideo Backbone=I3D, Audio Backbone=BN-Inception2023.10 | 46.44 | — | — | — | — | — | — | 40.87 | 43.57 | 54.88 | |
| TBNVideo Backbone=I3D, Audio Backbone=BN-Inception2023.10 | 46.33 | — | — | — | — | — | — | 42.35 | 47.45 | 49.2 | |
| Non-LocalVideo Backbone=I3D, Audio Backbone=BN-Inception2023.10 | 46.1 | — | — | — | — | — | — | 45.72 | 43.08 | 49.49 | |
| SENetVideo Backbone=I3D, Audio Backbone=BN-Inception2023.10 | 45.56 | — | — | — | — | — | — | 42.82 | 42.81 | 51.07 | |
| DeepAllVideo Backbone=I3D, Audio Backbone=BN-Inception2023.10 | 44.67 | — | — | — | — | — | — | 43.19 | 39.35 | 51.47 | |
| CoMixBackbone=I3D2021.10 | 43.2 | 38.6 | 42.3 | 42.9 | 49.2 | 40.9 | 45.2 | — | — | — | |
| TA3NBackbone=I3D2021.10 | 39.9 | 40.9 | 39.9 | 34.2 | 44.2 | 37.4 | 42.8 | — | — | — | |
| DANNBackbone=I3D2021.10 | 39.2 | 38.3 | 38.8 | 37.7 | 42.1 | 36.6 | 41.9 | — | — | — | |
| ADDABackbone=I3D2021.10 | 37.4 | 36.3 | 36.1 | 35.4 | 31.4 | 31.9 | 40.8 | — | — | — | |
| Source OnlyBackbone=I3D2021.10 | 35.3 | 35.4 | 34.6 | 32.8 | 35.8 | 34.1 | 39.1 | — | — | — |