AVT (Audio-Visual)
Reported on 4 benchmarks across 2 tasks
Note: results are matched by exact model name. Different papers may use the same name for different model variants.
Audio2 results
- Top 1 Accuracy63.9best: 69.8 (Mirasol3B)
- Top 5 Accuracy85best: 85.7 (MMT (Audio-Visual))
Methodology2 results
- Top 1 Accuracy63.9best: 69.8 (Mirasol3B)
- Top 5 Accuracy85best: 85.7 (MMT (Audio-Visual))