LoadingsequenceDiagram participant Input as Input Features (x_i) participant GCN as GCN Layers participant LSTM as LSTM Layer participant Attention as Optional Attention Layer participant Output as Output Prediction Input->>GCN: Spatial feature processing GCN->>LSTM: Temporal feature processing L...
GCN_CONV.py GCN_GRU.py GCN_GRU_BI.py GCN_GRU_BI_Attention.py GCN_GRU_BI_Multi_Attention.py GCN_GRU_TeacherForcing.py GCN_LSTM.py GCN_LSTM_BI.py GCN_LSTM_BI_Attention.py GCN_LSTM_BI_Multi_Attention.py GCN_LSTM_BI_Multi_Attention_Weather.py GCN_LSTM_BI_Multi_Attention_Weather_Separat...
建立了LSTM与ST-GCN融合的城市盗窃犯罪时空分布预测模型,并利用实际案例数据进行了验证.本文的研究内容和所取得的成果如下.(1)建立了LSTM与ST-GCN融合的城市盗窃犯罪预测模型.模型共分为3个模块,即时序特征提取模块,时空特征提取模块和特征融合模块.时序特征提取模块使用LSTM网络作为基础模型,用于提取每个社区的盗窃案件...
对于前端子任务,通过融合时空图卷积网络和长短期记忆网络,提出了一种有效的 ST-GCN-LSTM 模型。对于第二个子任务,采用YOLO v3模型进行手持物体识别。然后,我们构建了一个机器人与人类交互的框架。最后, "点击查看英文标题和摘要" 更新日期:2021-03-01
The advantages of this multi-task model are that 1) it effectively combines the 3D skeleton data and 2D image data for human intention recognition; 2) the ST-GCN-LSTM model owns merits from both the Graph Convolutional Networks and the Long Short Term Memory Network, which improves the ...
Robot recognizing humans intention and interacting with humans based on a multi-task model combining ST-GCN-LSTM model and YOLO model - ScienceDirect C Liu,X Li,Q Li,... 被引量: 0发表: 2021年 Tracking and detection of basketball movements using multi-feature data fusion and hybrid YOLO-T2...
Robot recognizing humans intention and interacting with humans based on a multi-task model combining ST-GCN-LSTM model and YOLO model - ScienceDirectChunfang LiuXiaoli LiQing LiYaxin XueHuijun LiuYize Gao