LAVISH

Reported on 2 benchmarks across 1 task · 1 paper · 2 SOTA

Note: results are matched by exact model name. Different papers may use the same name for different model variants.

Computer Vision2 results

Audio-visual Question AnsweringonMUSIC-AVQA
Acc· 2022-12-15
77.08
best: 80.7 (VAST)
SOTA
Vision Transformers are Parameter-Efficient Audio-Visual Learners arXiv:2212.07983
Audio-visual Question AnsweringonMUSIC-AVQA v2.0
Accuracy· 2022-12-15
73.18
best: 79.15 (Meerkat)
SOTA
Vision Transformers are Parameter-Efficient Audio-Visual Learners arXiv:2212.07983