基于3D-CNN和时空注意力-卷积LSTM的抑郁症识别研究

Automatic depression estimation using 3D-CNN and STA-Conv LSTM from videos

针对目前抑郁症识别方法中没有有效地从序列信息中刻画长时特征表示的问题,本文提出了一种基于三维卷积神经网络(3D-CNN)、时空注意力-卷积长短时记忆网络(STA-ConvLSTM)和空间金字塔池化(SPP)的端到端的抑郁症识别方法,计算在数据库AVEC2013和AVEC2014测试集上的抑郁症识别结果,并将本文结果与已发表文献结果进行对比分析.结果表明:在数据库AVEC2013和AVEC2014测试集上,平均绝对误差均为8.60,均方根误差分别为10.32和10.27,文献结果比较表明本文的抑郁症识别结果优于当前大多数基于面部视频的抑郁症识别方法.

To represent the longterm temporal information from the facial image sequences,in this paper we propose to an end-to-end architecture,which adopts 3 D Convolutional Neural Network(3 D-CNN),Spatial Pyramid Pooling(SPP),and Spatial-Temporal Attention based ConvLSTM(STA-ConvLSTM)networks for depression recognition.On the test set of AVEC2013 and AVEC2014,this approach obtains the RMSE as 10.32 and 10.27,and the same MAE as 8.60,respectively,which are lower than those of most of the state of the art video-based depression recognition methods.