Learning to Answer Questions in Dynamic Audio-Visual Scenarios
Open paper
Benchmark
Model
Rank
Results
audio-visual-question-answering-music-avqa-v2
AVST
#5
Accuracy: 71.02
audio-visual-question-answering-on-music-avqa
ST-AVQA
#4
Acc: 71.52
Rank counts only results with a code link.