基于视觉Transformer时空自注意力的工人行为识别

陆昱翔,徐冠华,唐波

Worker behavior recognition based on temporal and spatial self-attention of vision Transformer

Yu-xiang LU,Guan-hua XU,Bo TANG

表 1 不同模型在UCF101数据集上的评估实验结果

Tab.1 Results evaluated by different models on UCF101 dataset

模型 Accmin/% Accmax/% Accavg/% TPR/% F1 C3D[23] 85.17 85.42 85.32 98.35 0.7412 ViT[17] 88.39 88.71 88.54 96.48 0.8557 P3D[24] 88.51 88.65 88.59 96.43 0.7994 Conv-LSTM[25] 88.53 88.68 88.61 98.16 0.8235 本研究 93.25 93.68 93.44 99.21 0.9226