cunjunyu / STAR

[ECCV 2020] Code for "Spatio-Temporal Graph Transformer Networks for Pedestrian Trajectory Prediction"
MIT License
338 stars 78 forks source link

About the Network structure of STAR #8

Closed pavolusakruto closed 3 years ago

pavolusakruto commented 3 years ago

Thank you for sharing! In your STAR architecture, I found that the Spacial and Temporal Transformers are constructed parallelly in the first encoder, while serially in the second encoder. So why parallel? and why serial? Could you please tell us theory behind it? Thank you!

cunjunyu commented 3 years ago

As we have communicated through email, I will close the issue for now.

chenyouru commented 7 months ago

I have the same question. Could you please tell me theory behind it?