- Task 1 - Strongly Contextualised - Method: Focus: A bottom-up approach for Scene Text VQA
- Method info
- Samples list
- Per sample details
Sample Ranking | Score |
---|---|
ss1.0 | 0.92 |
ssbaseline | 0.83 |
VTA | 0.60 |
Focus: A bottom-up approach for Scene Text VQA | 0.58 |
RUArt | 0.50 |
TRAN MINH TRIEU | 0.00 |
USTB-TQA | 0.00 |
USTB-TVQA | 0.00 |
Visual Question Answering via deep multimodal learning | 0.00 |
SMA | 0.00 |