KVL-BERT: Knowledge Enhanced Visual-and-Linguistic BERT for Visual Commonsense Reasoning
Open paper
Benchmark
Model
Rank
Results
visual-question-answering-on-vcr-q-a-test
KVL-BERTLARGE
–
Accuracy: 76.4
visual-question-answering-on-vcr-q-ar-test
KVL-BERTLARGE
–
Accuracy: 60.3
visual-question-answering-on-vcr-qa-r-test
KVL-BERTLARGE
–
Accuracy: 78.6
Rank counts only results with a code link.