Factorized Variational Autoencoders for Modeling Audience Reactions to Movies

Zhiwei Deng, Rajitha Navarathna, Peter Carr, Stephan Mandt, Yisong Yue, Iain Matthews, Greg Mori

CVPR 2017

doi:10.1109/CVPR.2017.637 /cvpr/2017/deng2017cvpr-factorized/

Abstract

Matrix and tensor factorization methods are often used for finding underlying low-dimensional patterns from noisy data. In this paper, we study non-linear tensor factoriza- tion methods based on deep variational autoencoders. Our approach is well-suited for settings where the relationship between the latent representation to be learned and the raw data representation is highly complex. We apply our ap- proach to a large dataset of facial expressions of movie- watching audiences (over 16 million faces). Our experi- ments show that compared to conventional linear factoriza- tion methods, our method achieves better reconstruction of the data, and further discovers interpretable latent factors.

PDF CVPR Semantic Scholar

Cite

Text

Deng et al. "Factorized Variational Autoencoders for Modeling Audience Reactions to Movies." Conference on Computer Vision and Pattern Recognition, 2017. doi:10.1109/CVPR.2017.637

Markdown

[Deng et al. "Factorized Variational Autoencoders for Modeling Audience Reactions to Movies." Conference on Computer Vision and Pattern Recognition, 2017.](https://mlanthology.org/cvpr/2017/deng2017cvpr-factorized/) doi:10.1109/CVPR.2017.637

BibTeX

@inproceedings{deng2017cvpr-factorized,
  title     = {{Factorized Variational Autoencoders for Modeling Audience Reactions to Movies}},
  author    = {Deng, Zhiwei and Navarathna, Rajitha and Carr, Peter and Mandt, Stephan and Yue, Yisong and Matthews, Iain and Mori, Greg},
  booktitle = {Conference on Computer Vision and Pattern Recognition},
  year      = {2017},
  doi       = {10.1109/CVPR.2017.637},
  url       = {https://mlanthology.org/cvpr/2017/deng2017cvpr-factorized/}
}