{
  "id": "1511.05298",
  "version": "v1",
  "published": "2015-11-17T07:49:58.000Z",
  "updated": "2015-11-17T07:49:58.000Z",
  "title": "Structural-RNN: Deep Learning on Spatio-Temporal Graphs",
  "authors": [
    "Ashesh Jain",
    "Amir R. Zamir",
    "Silvio Savarese",
    "Ashutosh Saxena"
  ],
  "comment": "Video https://cs.stanford.edu/people/ashesh/srnn",
  "categories": [
    "cs.LG",
    "cs.NE"
  ],
  "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 flexible 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 a new convenient approach to problem formulation through high-level spatio-temporal graphs and Recurrent Neural Networks, and be of broad interest to the community.",
  "revisions": [
    {
      "version": "v1",
      "updated": "2015-11-17T07:49:58.000Z"
    }
  ],
  "analyses": {
    "keywords": [
      "deep learning",
      "high-level spatio-temporal graphs",
      "deep recurrent neural network architectures",
      "structural-rnn",
      "real world problems"
    ],
    "note": {
      "typesetting": "TeX",
      "pages": 0,
      "language": "en",
      "license": "arXiv",
      "status": "editable",
      "adsabs": "2015arXiv151105298J"
    }
  }
}