UAVM

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

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

Methodology2 results

ClassificationonVGG-Sound
Top-1 Accuracy· uses extra data· 2022-07-29
65.8
best: 66.2 (MMT)
SOTA
UAVM: Towards Unifying Audio and Visual Models arXiv:2208.00061
ClassificationonAudioSet
Average mAP· uses extra data· 2022-07-29
0.504
best: 0.512 (CAV-MAE)
SOTA
UAVM: Towards Unifying Audio and Visual Models arXiv:2208.00061

Miscellaneous2 results

Multi-modal ClassificationonVGG-Sound
Top-1 Accuracy· uses extra data· 2022-07-29
65.8
best: 66.2 (MMT)
SOTA
UAVM: Towards Unifying Audio and Visual Models arXiv:2208.00061
Multi-modal ClassificationonAudioSet
Average mAP· uses extra data· 2022-07-29
0.504
best: 0.512 (CAV-MAE)
SOTA
UAVM: Towards Unifying Audio and Visual Models arXiv:2208.00061