ML Anthology

A Variational Auto-Encoder Model for Stochastic Point Processes

Nazanin Mehrasa, Akash Abdu Jyothi, Thibaut Durand, Jiawei He, Leonid Sigal, Greg Mori
CVPR 2019
doi:10.1109/CVPR.2019.00328 /cvpr/2019/mehrasa2019cvpr-variational/

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.

PDF CVPR Semantic Scholar

Cite

Text

Mehrasa et al. "A Variational Auto-Encoder Model for Stochastic Point Processes." Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2019. doi:10.1109/CVPR.2019.00328

Markdown

[Mehrasa et al. "A Variational Auto-Encoder Model for Stochastic Point Processes." Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2019.](https://mlanthology.org/cvpr/2019/mehrasa2019cvpr-variational/) doi:10.1109/CVPR.2019.00328

BibTeX

@inproceedings{mehrasa2019cvpr-variational,
  title     = {{A Variational Auto-Encoder Model for Stochastic Point Processes}},
  author    = {Mehrasa, Nazanin and Jyothi, Akash Abdu and Durand, Thibaut and He, Jiawei and Sigal, Leonid and Mori, Greg},
  booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition},
  year      = {2019},
  doi       = {10.1109/CVPR.2019.00328},
  url       = {https://mlanthology.org/cvpr/2019/mehrasa2019cvpr-variational/}
}