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 6 本研究模型的结构消融实验结果

Tab.6 Experimental results of structure ablation of proposed model

% 结构调整 Acc 无预训练参数初始化 89.72 Head=4 88.71 Head=8 94.44 Head=12 98.54 Head=16 97.31 双空间自注意力模块 92.96