English

A Variational Auto-Encoder Model for Stochastic Point Processes

Computer Vision and Pattern Recognition 2019-04-09 v1 Machine Learning

Abstract

We propose a novel probabilistic generative model for action sequences. The model is termed the Action Point Process VAE (APP-VAE), a variational auto-encoder that can capture the distribution over the times and categories of action sequences. Modeling the variety of possible action sequences is a challenge, which we show can be addressed via the APP-VAE's use of latent representations and non-linear functions to parameterize distributions over which event is likely to occur next in a sequence and at what time. We empirically validate the efficacy of APP-VAE for modeling action sequences on the MultiTHUMOS and Breakfast datasets.

Keywords

Cite

@article{arxiv.1904.03273,
  title  = {A Variational Auto-Encoder Model for Stochastic Point Processes},
  author = {Nazanin Mehrasa and Akash Abdu Jyothi and Thibaut Durand and Jiawei He and Leonid Sigal and Greg Mori},
  journal= {arXiv preprint arXiv:1904.03273},
  year   = {2019}
}

Comments

CVPR 19

R2 v1 2026-06-23T08:31:03.131Z