Audio-Visual Event Classification
Benchmarks
DatasetSOTA methodMetricTrendResultsLast updated
69.1Fusion Top-1 Acc
23
Apr 1, 2026
0.934Accuracy
20
Jun 11, 2026
49.1mAP (Audio-only)
16
Feb 26, 2026
42.4mAP (Audio-only)
11
Apr 10, 2026
42.4mAP (Audio)
10
Jun 25, 2026
52.1Fusion mAP
7
Feb 26, 2026