Time extrapolator CNN versus LSTM decoder

abduallahmohamed / Social-STGCNN

Code for "Social-STGCNN: A Social Spatio-Temporal Graph Convolutional Neural Network for Human Trajectory Prediction" CVPR 2020

MIT License

483 stars 141 forks source link

Time extrapolator CNN versus LSTM decoder #41

Closed arsalsyed closed 3 years ago

arsalsyed commented 3 years ago

Hi,

I was just wondering what would happen if instead of TXPCNN (for 12 steps into future) we encode graph convolutions and then feed it in LSTM to decode trajectories. something like Grip ++ (https://arxiv.org/pdf/1907.07792.pdf). your thoughts?

Thanks Arsal

abduallahmohamed commented 3 years ago

Hi Arsal, I'm really not sure how it will work when this swap happens, but my reasonsing to use CNN instead of LSTM/GRU is this paper: An Empirical Evaluation of Generic Convolutional and Recurrent Networks for Sequence Modeling

Thanks