Video Question Answering on EgoTaskQA indirect
47.82Accuracy (World)VideoDistill
Evaluation Results
| Method | Links | |||||||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| VideoDistill2024.04 | 47.82 | 44.77 | 49.61 | 35.04 | 45.13 | 52.83 | 43.97 | 43.75 | 30.34 | 45.97 | 49.77 | 53.98 | 0.25 | |
| PSAC2024.04 | 44.74 | 42.25 | 48.38 | 35.37 | 43.36 | 29.11 | 39.94 | 42.53 | 30.06 | 30.97 | 43.29 | 57.2 | 4.9 | |
| HCRNvision usage=full vision2024.04 | 44.04 | 41.56 | 47.02 | 30.11 | 42.02 | 46.32 | 43.64 | 39.69 | 29.61 | 32.2 | 41.81 | 56.27 | 1.5 | |
| VisualBERT2024.04 | 40 | 37.01 | 36.02 | 26.02 | 38.9 | 31.37 | 37.63 | 32.75 | 27.49 | 22.63 | 32.02 | 55.59 | 2.4 | |
| HME2024.04 | 35.91 | 33.06 | 31.73 | 25.07 | 34.48 | 27.79 | 35.07 | 29.16 | 25.12 | 19.08 | 31.6 | 47.65 | 17.7 | |
| BERT2024.04 | 34.96 | 31.78 | 23.56 | 19.7 | 33.09 | 15.58 | 34.59 | 27.38 | 26.91 | 2.808 | 21.96 | 55.28 | 6.4 | |
| HCRNvision usage=w/o vision2024.04 | 33.61 | 30.76 | 23.98 | 19.25 | 30.73 | 13.68 | 34.75 | 28.11 | 28.18 | 4.13 | 21.24 | 50.71 | 5.4 | |
| HGA2024.04 | 31.29 | 28.36 | 20.42 | 17.74 | 29.01 | 15.16 | 33.01 | 24 | 26.15 | 7.02 | 17.67 | 47.22 | 22.9 | |
| ClipBERT2024.04 | 26.51 | 24.08 | 14.66 | 20.09 | 24.35 | 10.32 | 26.29 | 22.46 | 25.25 | 10.49 | 15.29 | 35.26 | 39.6 |