Fig. 16
From: Attention-guided saptio-temporal feature fusion for robus video surveillance anomaly detection

Comparison of recall across models: bar chart showing the recall performance of three models—EfficientNetV2B0 + HOG, ConvLSTM, and hybrid model-1 (ResNet-50 + YOLO-v4). EfficientNetV2B0 + HOG achieves the highest recall, indicating its strength in detecting true positives, followed by Hybrid Model-1 and ConvLSTM.