Action Anticipation On Epic Kitchens 100 Test
평가 지표
recall@5
평가 결과
이 벤치마크에서 각 모델의 성능 결과
모델 이름 | recall@5 | Paper Title | Repository |
|---|---|---|---|
| InAViT | 23.75 | Interaction Region Visual Transformer for Egocentric Action Anticipation | - |
| TempAgg | 12.6 | Technical Report: Temporal Aggregate Representations | - |
| AVT+ | 12.6 | Anticipative Video Transformer | - |
| RULSTM | 11.2 | Rolling-Unrolling LSTMs for Action Anticipation from First-Person Video | - |
| AVT++ | 16.7 | Anticipative Video Transformer | - |
| TBN | 11.0 | Multi-Modal Temporal Convolutional Network for Anticipating Actions in Egocentric Videos | - |
| AFFT | 14.9 | Anticipative Feature Fusion Transformer for Multi-Modal Action Anticipation | - |
| Abstract Goal | 14.29 | Predicting the Next Action by Modeling the Abstract Goal | - |
0 of 8 row(s) selected.