VinVL+L: Enriching Visual Representation with Location Context in VQA
Open paper
Benchmark
Model
Rank
Results
visual-question-answering-on-gqa-test2019
VinVL+L
#1
Accuracy: 64.85
Binary: 82.59
Open: 49.19
Consistency: 94.0
…
Rank counts only results with a code link.