METHOD FOR RECOGNIZING ACTIVITIES USING SEPARATE SPATIAL AND TEMPORAL ATTENTION WEIGHTS

摘要

A device and a method for recognizing person activity in a sequence of frames (100) comprising: obtaining a set of consecutives 3D poses (103), obtaining a feature map (102), obtaining a vector of spatiotemporal features, obtaining a matrix of spatial attention weights, obtaining a matrix of temporal attention weights (110), modulating (106) the feature map using the matrix of spatial attention weights to obtain a spatially modulated feature map, modulating (111) the feature map using the vector of temporal attention weights to obtain a temporally modulated feature map, performing a convolution (114) of the spatially modulated feature map and of the temporally modulated feature map to obtain a convoluted feature map, performing a classification (115) using the convoluted feature map so as to determine the activity of the person in the video.