EquiAV

Reported on 6 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.

Audio3 results

Audio ClassificationonBalanced Audio Set
Mean AP· 2024-03-14
42.4
SOTA
EquiAV: Leveraging Equivariance for Audio-Visual Contrastive Learning arXiv:2403.09502
Audio ClassificationonAudioSet
Test mAP· 2024-03-14
0.546
best: 0.558 (OmniVec2)
EquiAV: Leveraging Equivariance for Audio-Visual Contrastive Learning arXiv:2403.09502
Audio ClassificationonVGGSound
Top 1 Accuracy· uses extra data· 2024-03-14
67.1
best: 69.8 (Mirasol3B)
EquiAV: Leveraging Equivariance for Audio-Visual Contrastive Learning arXiv:2403.09502

Methodology3 results

ClassificationonBalanced Audio Set
Mean AP· 2024-03-14
42.4
SOTA
EquiAV: Leveraging Equivariance for Audio-Visual Contrastive Learning arXiv:2403.09502
ClassificationonAudioSet
Test mAP· 2024-03-14
0.546
best: 0.558 (OmniVec2)
EquiAV: Leveraging Equivariance for Audio-Visual Contrastive Learning arXiv:2403.09502
ClassificationonVGGSound
Top 1 Accuracy· uses extra data· 2024-03-14
67.1
best: 69.8 (Mirasol3B)
EquiAV: Leveraging Equivariance for Audio-Visual Contrastive Learning arXiv:2403.09502