Video Question Answering on TGIF-QA Action original (test)
95AccuracyVGT
Evaluation results
| Method | Links | |
|---|---|---|
| VGTPretrain Dataset=None, Pretrain Size=None, Text Encoder=BERT2023.02 | 95 | |
| CoVGTPretrain Dataset=None, Pretrain Size=None, Text Encoder=RoBERTa2023.02 | 94.7 | |
| MERLOTPretrain Dataset=YT, CC, Pretrain Size=183M, Text Encoder=BERT2023.02 | 94 | |
| VGT (PT)Pretrain Dataset=WV, Pretrain Size=0.18M, Text Encoder=BERT2023.02 | 93.1 | |
| CoVGT (PT)Pretrain Dataset=WV, Pretrain Size=0.18M, Text Encoder=RoBERTa2023.02 | 91.3 | |
| MASNPretrain Dataset=None, Pretrain Size=None, Text Encoder=GloVe2023.02 | 84.4 | |
| MHNPretrain Dataset=None, Pretrain Size=None, Text Encoder=GloVe2023.02 | 83.5 | |
| ClipBERTPretrain Dataset=VG, COCO, Pretrain Size=None, Text Encoder=BERT2023.02 | 82.8 | |
| PGATPretrain Dataset=None, Pretrain Size=None, Text Encoder=GloVe2023.02 | 80.6 | |
| SiaSReaPretrain Dataset=VG, COCO, Pretrain Size=None, Text Encoder=BERT2023.02 | 79.7 | |
| HAIRPretrain Dataset=None, Pretrain Size=None, Text Encoder=GloVe2023.02 | 77.8 | |
| HQGAPretrain Dataset=None, Pretrain Size=None, Text Encoder=BERT2023.02 | 76.9 | |
| B2APretrain Dataset=None, Pretrain Size=None, Text Encoder=GloVe2023.02 | 75.9 | |
| HGAPretrain Dataset=None, Pretrain Size=None, Text Encoder=GloVe2023.02 | 75.4 | |
| HCRNPretrain Dataset=None, Pretrain Size=None, Text Encoder=GloVe2023.02 | 75 | |
| HOSTRPretrain Dataset=None, Pretrain Size=None, Text Encoder=GloVe2023.02 | 75 | |
| LGCNPretrain Dataset=None, Pretrain Size=None, Text Encoder=GloVe2023.02 | 74.3 |