Corpus ID: 221095936

Adversarial Generative Grammars for Human Activity Prediction

  title={Adversarial Generative Grammars for Human Activity Prediction},
  author={A. Piergiovanni and A. Angelova and A. Toshev and M. Ryoo},
  • A. Piergiovanni, A. Angelova, +1 author M. Ryoo
  • Published 2020
  • Computer Science
  • ArXiv
  • In this paper we propose an adversarial generative grammar model for future prediction. The objective is to learn a model that explicitly captures temporal dependencies, providing a capability to forecast multiple, distinct future activities. Our adversarial grammar is designed so that it can learn stochastic production rules from the data distribution, jointly with its latent non-terminal representations. Being able to select multiple production rules during inference leads to different… CONTINUE READING

    Figures and Tables from this paper.


    Publications referenced by this paper.
    Generative Adversarial Nets
    • 17,735
    • PDF
    Learning Phrase Representations using RNN Encoder-Decoder for Statistical Machine Translation
    • 9,475
    • PDF
    SeqGAN: Sequence Generative Adversarial Nets with Policy Gradient
    • 1,100
    • PDF
    Image-to-Image Translation with Conditional Adversarial Networks
    • 6,258
    • PDF
    Unsupervised Learning for Physical Interaction through Video Prediction
    • 581
    • PDF
    Deep Generative Image Models using a Laplacian Pyramid of Adversarial Networks
    • 1,447
    • PDF
    Recurrent Network Models for Human Dynamics
    • 363
    • Highly Influential
    • PDF
    Stochastic Adversarial Video Prediction
    • 173
    • PDF
    Large Scale GAN Training for High Fidelity Natural Image Synthesis
    • 1,175
    • PDF