VLC-BERT: Visual Question Answering with Contextualized Commonsense Knowledge

Open paper

Benchmark	Model	Rank	Results
visual-question-answering-on-a-okvqa	VLC-BERT	#10	DA VQA Score: 38.05
visual-question-answering-on-ok-vqa	VLC-BERT	#21	Accuracy: 43.1