Audio-Visual Event Classification on AVE
0.934AccuracyAGSP-DSA
Evaluation Results
| Method | Links | |||
|---|---|---|---|---|
| AGSP-DSALearning Rate=0.001, Optimizer=Adam, Batch Size=64, Epochs=100, GCN Layers=3, Hidden Units=128, Dropout Rate=0.3, Chebyshev Order=3, Fusion Strategy=Semantic-aware Attention2026.01 | 0.934 | 0.911 | 0.898 | |
| MM-GNN2026.01 | 0.892 | 0.877 | 0.863 | |
| MMT2026.01 | 0.869 | 0.853 | 0.847 | |
| Late Fusion2026.01 | 0.846 | 0.832 | 0.821 | |
| UCMKDSetting=Paired2026.06 | 0.5307 | — | — | |
| FitNetSetting=Paired2026.06 | 0.4925 | — | — | |
| Vanilla KDSetting=Paired2026.06 | 0.4901 | — | — | |
| ReviewSetting=Paired2026.06 | 0.4892 | — | — | |
| C2KDSetting=Paired2026.06 | 0.4715 | — | — | |
| RLDSetting=Paired2026.06 | 0.4287 | — | — | |
| RKDSetting=Paired2026.06 | 0.4254 | — | — | |
| DKDSetting=Paired2026.06 | 0.3408 | — | — | |
| UCMKDSetting=Paired2026.06 | 0.335 | — | — | |
| C2KDSetting=Paired2026.06 | 0.3333 | — | — | |
| Vanilla KDSetting=Paired2026.06 | 0.2985 | — | — | |
| RKDSetting=Paired2026.06 | 0.2786 | — | — | |
| FitNetSetting=Paired2026.06 | 0.2587 | — | — | |
| RLDSetting=Paired2026.06 | 0.228 | — | — | |
| DKDSetting=Paired2026.06 | 0.228 | — | — | |
| ReviewSetting=Paired2026.06 | 0.223 | — | — |