Structural-RNN: Deep Learning on Spatio-Temporal Graphs. CVPR, 2016. (oral, best student paper award)

Structural-RNN: Deep Learning on Spatio-Temporal Graphs. CVPR, 2016. (oral, best student paper award)

https://arxiv.org/pdf/1511.05298.pdf

This paper proposes a scalable and principled approach for casting an arbitrary spatio-temporal graph as a rich Recurrent Neural Network (RNN).

Such architectures are crucial for applications relating to user activities and interactions with their home environments.