Video Question Answering on EgoTaskQA (normal)
47.32Accuracy (World)VideoDistill
Evaluation Results
| Method | Links | ||||||||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| VideoDistilltraining from scratch=true2024.04 | 47.32 | 52.53 | 36.95 | 47.2 | 40.43 | 49.64 | 42.53 | 16.35 | 54.64 | 72.37 | 71.47 | — | — | 45.02 | |
| Glance-Focustraining_mode=supervised2024.01 | 46.53 | 51.88 | 34.31 | 46.68 | 40.36 | 46.8 | 42.18 | 15.68 | 50.98 | 71.23 | 69.71 | 32.79 | 70.25 | 44.27 | |
| Glance-Focustraining_mode=unsupervised2024.01 | 44.65 | 52.07 | 33.17 | 44.48 | 39 | 46.66 | 42.45 | 15.68 | 45.97 | 70.44 | 68.69 | 31.26 | 69.8 | 43.06 | |
| HCRN2024.01 | 44.27 | 49.77 | 31.36 | 43.48 | 36.56 | 48 | 40.6 | 14.92 | 45.31 | 68.28 | 67.38 | 30.23 | 69.42 | 42.2 | |
| HCRN2024.04 | 44.27 | 49.77 | 31.36 | 43.48 | 36.56 | 48 | 40.6 | 14.92 | 45.31 | 68.28 | 67.38 | — | — | 42.2 | |
| ClipBERT2024.01 | 42.15 | 40.94 | 27.63 | 38.45 | 31.5 | 46.75 | 42.39 | 22.91 | 21.8 | 54.36 | 66.58 | 27.7 | 67.52 | 39.87 | |
| ClipBERT2024.04 | 42.15 | 40.94 | 27.63 | 38.45 | 31.5 | 46.75 | 42.39 | 22.91 | 21.8 | 54.36 | 66.58 | — | — | 39.87 | |
| HME2024.04 | 41.91 | 48.92 | 27.98 | 41.45 | 35.88 | 44.13 | 38.85 | 14.99 | 36.05 | 63.44 | 68.87 | — | — | 40.16 | |
| PSAC2024.04 | 40.76 | 46.19 | 30.59 | 40.63 | 31.98 | 41.89 | 37.99 | 14.75 | 36.53 | 61.89 | 65.05 | — | — | 38.9 | |
| VisualBERT2024.01 | 39.73 | 44.51 | 26.29 | 41.99 | 30.37 | 41.99 | 37.42 | 15.02 | 23.26 | 59.2 | 68.27 | 24.62 | 68.08 | 37.93 | |
| VisualBERT2024.04 | 39.73 | 44.51 | 26.29 | 41.99 | 30.37 | 41.99 | 37.42 | 15.02 | 23.26 | 59.2 | 68.27 | — | — | 37.93 | |
| HGA2024.04 | 38.82 | 42.12 | 23.43 | 38.04 | 25.57 | 41.94 | 35.97 | 15.08 | 19.09 | 55.65 | 68.38 | — | — | 36.77 |