MBT (A)

Reported on 4 benchmarks across 2 tasks · 1 paper · 2 SOTA

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

Audio2 results

Audio ClassificationonVGGSound
Top 1 Accuracy· 2021-06-30
52.3
best: 69.8 (Mirasol3B)
SOTA
Attention Bottlenecks for Multimodal Fusion arXiv:2107.00135
Audio ClassificationonVGGSound
Top 5 Accuracy· 2021-06-30
78.1
best: 85.7 (MMT (Audio-Visual))
Attention Bottlenecks for Multimodal Fusion arXiv:2107.00135

Methodology2 results

ClassificationonVGGSound
Top 1 Accuracy· 2021-06-30
52.3
best: 69.8 (Mirasol3B)
SOTA
Attention Bottlenecks for Multimodal Fusion arXiv:2107.00135
ClassificationonVGGSound
Top 5 Accuracy· 2021-06-30
78.1
best: 85.7 (MMT (Audio-Visual))
Attention Bottlenecks for Multimodal Fusion arXiv:2107.00135