Video Question Answering on TGIF-QA-R Action curated (test)
61AccuracyCoVGT (PT)
Evaluation results
| Method | Links | |
|---|---|---|
| CoVGT (PT)Pretrain Dataset=WV, Pretrain Size=0.18M, Text Encoder=RoBERTa2023.02 | 61 | |
| CoVGTPretrain Dataset=None, Pretrain Size=None, Text Encoder=RoBERTa2023.02 | 60.8 | |
| VGT (PT)Pretrain Dataset=WV, Pretrain Size=0.18M, Text Encoder=BERT2023.02 | 60.5 | |
| VGTPretrain Dataset=None, Pretrain Size=None, Text Encoder=BERT2023.02 | 59.9 | |
| PGATPretrain Dataset=None, Pretrain Size=None, Text Encoder=GloVe2023.02 | 58.7 | |
| HCRNPretrain Dataset=None, Pretrain Size=None, Text Encoder=GloVe2023.02 | 55.7 |