Group Emotion Recognition on VGAF 2023 (test)
76.85AccuracyLiu et al.
Evaluation results
| Method | Links | |
|---|---|---|
| Liu et al.Modalities=Audio+Video, Individual features=true2026.05 | 76.85 | |
| Ours v5Modalities=Audio + Synthetic video + Video, Aggregation strategy=Avg. Pooling, Context=EmotiW20232026.05 | 75.13 | |
| Ours v6Modalities=Audio + Synthetic video + Video, Aggregation strategy=Avg. Pooling, Context=EmotiW20232026.05 | 75.13 | |
| Ours v4Modalities=Synthetic video + Video, Aggregation strategy=Avg. Pooling, Context=EmotiW20232026.05 | 74.73 | |
| Wang et al.Modalities=Audio+Video2026.05 | 66.4 | |
| Sharma et al.Modalities=Audio+Video, Individual features=true2026.05 | 66 | |
| Ottl et al.Modalities=Audio2026.05 | 62.3 | |
| Petrova et al.Modalities=Video2026.05 | 59.13 | |
| Ours v1Modalities=Audio, Aggregation strategy=Avg. Pooling, Context=EmotiW20232026.05 | 55.29 | |
| Ours v2Modalities=Synthetic video, Aggregation strategy=Avg. Pooling, Context=EmotiW20232026.05 | 54.23 | |
| baselineModalities=A+V2026.05 | 47.88 |