Method: Visual Question Answering via deep multimodal learning - Sample num 36 - Task 1 - Strongly Contextualised - ICDAR 2019 Robust Reading Challenge on Scene Text Visual Question Answering

Sample 36 of 4102

Sample Ranking	Score
RUArt	1.00
USTB-TQA	0.50
VTA	0.50
Visual Question Answering via deep multimodal learning	0.50
SMA	0.50
ssbaseline	0.50
ss1.0	0.50
TRAN MINH TRIEU	0.00
USTB-TVQA	0.00
Focus: A bottom-up approach for Scene Text VQA	0.00