Ranking Distillation for Open-Ended Video Question Answering with Insufficient Labels
Open paper
Benchmark
Model
Rank
Results
visual-question-answering-on-msrvtt-qa
RADI-P
–
Accuracy: 0.482
visual-question-answering-on-msvd-qa
RADI-L
–
Accuracy: 0.560
Rank counts only results with a code link.