Table 1 Prediction accuracy comparison of different modalities on UT-Interaction set 1 (%)
From: Human activity prediction using saliency-aware motion enhancement and weighted LSTM network
Modality | Accuracy with half videos | Accuracy with full videos |
|---|---|---|
RGB-SME | 87.6 | 93.8 |
OF-SME | 93.1 | 96.4 |
Two-modality fusion | 95.0 | 98.3 |