Action Recognition on EPIC-KITCHENS 1 (S1 Seen kitchens)
66.7Top-1 Accuracy (Verb)Temporal Aggregate Representations
Evaluation Results
| Method | Links | ||||||||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Temporal Aggregate RepresentationsAuxiliary Task=Verb + Noun classification2020.06 | 66.7 | 49.6 | 41.6 | 90.1 | 77 | 64.1 | — | — | — | — | — | — | — | — | |
| TBNModel Type=Ensemble2019.08 | 66.1 | 47.89 | 36.66 | 91.28 | 72.8 | 58.62 | 60.74 | 44.9 | 24.02 | 46.82 | 43.89 | 22.92 | — | — | |
| [43]2020.06 | 65.7 | 46.4 | 35.9 | 89.5 | 71.7 | 57.8 | — | — | — | — | — | — | — | — | |
| TBNModel Type=Single Model2019.08 | 64.75 | 46.03 | 34.8 | 90.7 | 71.34 | 56.65 | 55.67 | 43.65 | 22.07 | 45.55 | 42.3 | 21.31 | — | — | |
| Temporal Aggregate RepresentationsAuxiliary Task=None2020.06 | 63.2 | 49.5 | 41.3 | 87.3 | 70 | 63.5 | — | — | — | — | — | — | — | — | |
| LFB2020.06 | 60 | 45 | 32.7 | 88.4 | 71.8 | 55.3 | — | — | — | — | — | — | — | — | |
| LSTAModality=two stream2018.11 | 59.55 | 38.35 | 30.33 | 85.77 | 61.49 | 49.97 | 42.72 | 36.19 | 14.46 | 38.12 | 36.19 | 17.76 | — | — | |
| LSTAModality=RGB2018.11 | 58.25 | 38.93 | 30.16 | 86.57 | 62.96 | 50.16 | 44.09 | 36.3 | 16.54 | 37.32 | 36.52 | 19 | — | — | |
| RU2020.06 | 56.9 | 43.1 | 33.1 | 85.7 | 67.1 | 55.3 | — | — | — | — | — | — | — | — | |
| TSN w. AudioBackbone=TSN, Modality=w. Audio2019.08 | 55.49 | 36.27 | 23.95 | 87.04 | 64.17 | 44.26 | 53.85 | 30.94 | 13.55 | 30.6 | 29.82 | 11.11 | — | — | |
| TSNModality=two stream2018.11 | 48.23 | 36.71 | 20.54 | 84.09 | 62.32 | 39.79 | 47.26 | 35.42 | 11.57 | 22.33 | 30.53 | 9.78 | — | — | |
| [8] (from leaderboard)Source=leaderboard2019.08 | 48.23 | 36.71 | 20.54 | 84.09 | 62.32 | 39.79 | 47.26 | 35.42 | 11.57 | 22.33 | 30.53 | 9.78 | — | — | |
| TSN2020.06 | 48.2 | 33.7 | 20.5 | 84.1 | 62.3 | 39.8 | — | — | — | — | — | — | — | — | |
| TSNModality=RGB2018.11 | 45.68 | 36.8 | 19.86 | 85.56 | 64.19 | 41.89 | 61.64 | 34.32 | 11.02 | 23.81 | 31.62 | 9.76 | — | — | |
| 2SCNNModality=two stream2018.11 | 42.16 | 29.14 | 13.23 | 80.58 | 53.7 | 30.36 | 29.39 | 30.73 | 5.92 | 14.83 | 21.1 | 4.93 | — | — | |
| 2SCNNModality=RGB2018.11 | 40.44 | 30.46 | 13.67 | 83.04 | 57.05 | 33.25 | 34.74 | 28.23 | 6.66 | 15.9 | 23.23 | 5.47 | — | — | |
| Attention Clusters2019.08 | 40.39 | 19.37 | 11.09 | 78.13 | 41.73 | 24.36 | 21.17 | 9.65 | 2.5 | 14.89 | 11.5 | 3.41 | — | — | |
| Action BanksInput Modality=RGB, Number of frames=8, Number of crops=10, Resolution=full res2020.04 | — | — | — | — | — | — | — | — | — | — | — | — | 60 | 88.4 | |
| Action BanksInput Modality=RGB, Number of frames=8, Number of crops=10, Resolution=full res2020.04 | — | — | — | — | — | — | — | — | — | — | — | — | 32.7 | 55.3 | |
| TRNInput Modality=RGB, Number of frames=8, Number of crops=102020.04 | — | — | — | — | — | — | — | — | — | — | — | — | 58.8 | 86.6 | |
| TRNInput Modality=RGB, Number of frames=8, Number of crops=102020.04 | — | — | — | — | — | — | — | — | — | — | — | — | 26.6 | 46.1 | |
| TRN-MultiscaleInput Modality=RGB, Number of frames=8, Number of crops=102020.04 | — | — | — | — | — | — | — | — | — | — | — | — | 60.2 | 87.2 | |
| TRN-MultiscaleInput Modality=RGB, Number of frames=8, Number of crops=102020.04 | — | — | — | — | — | — | — | — | — | — | — | — | 28.2 | 47.9 | |
| TSMInput Modality=RGB, Number of frames=8, Number of crops=102020.04 | — | — | — | — | — | — | — | — | — | — | — | — | 57.9 | 87.1 | |
| TSMInput Modality=RGB, Number of frames=8, Number of crops=102020.04 | — | — | — | — | — | — | — | — | — | — | — | — | 28.2 | 49.1 | |
| TSM+W3Input Modality=RGB, Number of frames=8, Number of crops=102020.04 | — | — | — | — | — | — | — | — | — | — | — | — | 64.4 | 88.8 | |
| TSM+W3Input Modality=RGB, Number of frames=8, Number of crops=10, Resolution=full res2020.04 | — | — | — | — | — | — | — | — | — | — | — | — | 64.7 | 88.8 | |
| TSM+W3Input Modality=RGB, Number of frames=8, Number of crops=102020.04 | — | — | — | — | — | — | — | — | — | — | — | — | 33.5 | 53.9 | |
| TSM+W3Input Modality=RGB, Number of frames=8, Number of crops=10, Resolution=full res2020.04 | — | — | — | — | — | — | — | — | — | — | — | — | 34.2 | 54.6 | |
| TSNInput Modality=RGB, Number of frames=8, Number of crops=102020.04 | — | — | — | — | — | — | — | — | — | — | — | — | 49.7 | 87.2 | |
| TSNInput Modality=RGB, Number of frames=8, Number of crops=102020.04 | — | — | — | — | — | — | — | — | — | — | — | — | 24 | 46.1 |