Open Fujiry0 opened 4 years ago
I just read this and I find the explanation to be terrible... I don't understand how to obtain the mean and covariance of the assumed Gaussian from the model. Also, it seems the second network with convolution seems to mean convolution in 2D space (as the code use Conv2d), but I don't understand the meaning of this tensor that needs the conv2d as it is not explained in the paper.
Paper: http://openaccess.thecvf.com/content_CVPR_2020/papers/Mohamed_Social-STGCNN_A_Social_Spatio-Temporal_Graph_Convolutional_Neural_Network_for_Human_CVPR_2020_paper.pdf
Short summary: Social Spatio-Temporal Graph Convolutional Neural Network (Social-STGCNN), which substitutes the need of aggregation methods by modeling the interactions as a graph.
Overcome the limitation of existing methods
Details
GitHub: https://github.com/abduallahmohamed/Social-STGCNN