[1511.05298] Structural-RNN: Deep Learning on Spatio-Temporal Graphs

CVPR 2016 Best Student Paper: Structural-RNN: Deep Learning on Spatio-Temporal Graphs  #cvpr

  • The proposed method is generic and principled as it can be used for transforming any spatio-temporal graph through employing a certain set of well defined steps.
  • That is while many problems in computer vision inherently have an underlying high-level structure and can benefit from it.
  • We expect the method to empower new approaches to problem formulation through high-level spatio-temporal graphs and Recurrent Neural Networks.
  • Spatio-temporal graphs are a popular tool for imposing such high-level intuitions in the formulation of real world problems.
  • We develop a scalable method for casting an arbitrary spatio-temporal graph as a rich RNN mixture that is feedforward, fully differentiable, and jointly trainable.

Read the full article, click here.


@quantombone: “CVPR 2016 Best Student Paper: Structural-RNN: Deep Learning on Spatio-Temporal Graphs #cvpr”


One hundred percent of your contribution will fund improvements and new initiatives to benefit arXiv’s global scientific community. Please join the Simons Foundation and our generous member organizations and research labs in supporting arXiv.


[1511.05298] Structural-RNN: Deep Learning on Spatio-Temporal Graphs