Structural-RNN: Deep Learning on Spatio-Temporal Graphs

TL;DR

This paper introduces a scalable method to integrate high-level spatio-temporal graphs with Recurrent Neural Networks, enabling improved modeling of complex structured sequences in tasks like human motion and object interactions.

Contribution

It presents a generic, differentiable approach to convert any spatio-temporal graph into a trainable RNN mixture, enhancing sequence modeling with high-level structure.

Findings

Significant performance improvements over state-of-the-art methods.

Effective modeling of human motion and object interactions.

Flexible and principled graph-to-RNN transformation.

Abstract

Deep Recurrent Neural Network architectures, though remarkably capable at modeling sequences, lack an intuitive high-level spatio-temporal structure. That is while many problems in computer vision inherently have an underlying high-level structure and can benefit from it. Spatio-temporal graphs are a popular tool for imposing such high-level intuitions in the formulation of real world problems. In this paper, we propose an approach for combining the power of high-level spatio-temporal graphs and sequence learning success of Recurrent Neural Networks~(RNNs). 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. 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. The evaluations of the proposed approach on a diverse set of problems, ranging from modeling human motion to object interactions, shows improvement over the state-of-the-art with a large margin. We expect this method to empower new approaches to problem formulation through high-level spatio-temporal graphs and Recurrent Neural Networks.