| Paper | Code | Top 1 Accuracy - Act. | Top 1 Accuracy - Noun | Top 1 Accuracy - Verb | Top 5 Accuracy - Act. | Top 5 Accuracy - Noun | Top 5 Accuracy - Verb | ModelName | ReleaseDate |
|---|---|---|---|---|---|---|---|---|---|
| Predicting the Next Action by Modeling the Abstract Goal | 13.28 | 22.36 | 41.41 | 24.24 | 41.62 | 73.10 | Abstract Goal | 2022-09-12 | |
| Anticipative Video Transformer | ✓ Link | 10.41 | 15.64 | 30.66 | 24.27 | 40.76 | 72.17 | AVT+ | 2021-06-03 |
| Learning to Anticipate Egocentric Actions by Imagination | 9.25 | 15.50 | 29.33 | 22.19 | 35.78 | 70.67 | ImagineRNN | 2021-01-13 | |
| What Would You Expect? Anticipating Egocentric Actions with Rolling-Unrolling LSTMs and Modality Attention | ✓ Link | 8.16 | 15.19 | 27.01 | 21.10 | 34.38 | 69.55 | RULSTM [24, 23] | 2019-05-22 |
| RED: Reinforced Encoder-Decoder Networks for Action Anticipation | ✓ Link | 2.65 | 7.81 | 22.52 | 7.57 | 21.42 | 62.65 | ED | 2017-07-16 |
| Scaling Egocentric Vision: The EPIC-KITCHENS Dataset | ✓ Link | 2.39 | 10.41 | 25.30 | 6.63 | 29.50 | 68.32 | ATSN | 2018-04-08 |
| Scaling Egocentric Vision: The EPIC-KITCHENS Dataset | ✓ Link | 2.29 | 9.97 | 25.23 | 9.35 | 27.38 | 68.66 | 2SCNN | 2018-04-08 |