UAVM (Audio + Video)

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.

Audio2 results

Audio ClassificationonAudioSet
Test mAP· uses extra data· 2022-07-29
0.504
best: 0.558 (OmniVec2)
SOTA
UAVM: Towards Unifying Audio and Visual Models arXiv:2208.00061
Audio ClassificationonVGGSound
Top 1 Accuracy· uses extra data· 2022-07-29
65.8
best: 69.8 (Mirasol3B)
SOTA
UAVM: Towards Unifying Audio and Visual Models arXiv:2208.00061

Methodology2 results

ClassificationonAudioSet
Test mAP· uses extra data· 2022-07-29
0.504
best: 0.558 (OmniVec2)
SOTA
UAVM: Towards Unifying Audio and Visual Models arXiv:2208.00061
ClassificationonVGGSound
Top 1 Accuracy· uses extra data· 2022-07-29
65.8
best: 69.8 (Mirasol3B)
SOTA
UAVM: Towards Unifying Audio and Visual Models arXiv:2208.00061