Answering Questions about Data Visualizations using Efficient Bimodal Fusion
Open paper
Benchmark
Model
Rank
Results
visual-question-answering-on-figureqa-test-1
PReFIL
#1
1:1 Accuracy: 94.88
visual-question-answering-on-plotqa-d1
PReFIL
#2
1:1 Accuracy: 57.91
visual-question-answering-on-plotqa-d2
PReFIL
#2
1:1 Accuracy: 10.37
Rank counts only results with a code link.