ResearchBenchmarksVisual Question Answering on CoGenT (TestB)For AI assistantsMarkdownContent indexVisual Question Answering on CoGenT (TestB)Follow78.8AccuracyFiLM63.30467.32771.3575.373Apr 26, 2021Evaluation resultsMethodMethodLinksAccuracyFiLMtraining condition=A,...training condition=A, fine-tuned on condition B=false2021.0478.8MDETRtraining condition=A,...training condition=A, fine-tuned on condition B=false2021.0476.7NS-VQAtraining condition=A,...training condition=A, fine-tuned on condition B=false, external program annotations=true2021.0463.9