Video Question Answering on TGIF-QA-R Transition curated (test)
73.8AccuracyCoVGT
Evaluation results
| Method | Links | |
|---|---|---|
| CoVGTPretrain Dataset=None, Pretrain Size=None, Text Encoder=RoBERTa2023.02 | 73.8 | |
| CoVGT (PT)Pretrain Dataset=WV, Pretrain Size=0.18M, Text Encoder=RoBERTa2023.02 | 73.2 | |
| VGT (PT)Pretrain Dataset=WV, Pretrain Size=0.18M, Text Encoder=BERT2023.02 | 71.5 | |
| VGTPretrain Dataset=None, Pretrain Size=None, Text Encoder=BERT2023.02 | 70.5 | |
| PGATPretrain Dataset=None, Pretrain Size=None, Text Encoder=GloVe2023.02 | 65.9 | |
| HCRNPretrain Dataset=None, Pretrain Size=None, Text Encoder=GloVe2023.02 | 63.9 |