CaltechAUTHORS
  A Caltech Library Service

Factorized Variational Autoencoders for Modeling Audience Reactions to Movies

Deng, Zhiwei and Navarathna, Rajitha and Carr, Peter and Mandt, Stephan and Yue, Yisong and Matthews, Iain and Mori, Greg (2017) Factorized Variational Autoencoders for Modeling Audience Reactions to Movies. In: 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR). IEEE , Piscataway, NJ. ISBN 978-1-5386-0457-1. http://resolver.caltech.edu/CaltechAUTHORS:20170721-141656092

[img] PDF - Submitted Version
See Usage Policy.

6Mb

Use this Persistent URL to link to this item: http://resolver.caltech.edu/CaltechAUTHORS:20170721-141656092

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 factorization 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 approach to a large dataset of facial expressions of movie-watching audiences (over 16 million faces). Our experiments show that compared to conventional linear factorization methods, our method achieves better reconstruction of the data, and further discovers interpretable latent factors.


Item Type:Book Section
Related URLs:
URLURL TypeDescription
https://doi.org/10.1109/CVPR.2017.637DOIArticle
http://ieeexplore.ieee.org/document/8100120PublisherArticle
https://www.disneyresearch.com/publication/factorized-variational-autoencoder/OrganizationArticle
Additional Information:© 2017 IEEE.
Record Number:CaltechAUTHORS:20170721-141656092
Persistent URL:http://resolver.caltech.edu/CaltechAUTHORS:20170721-141656092
Official Citation:Z. Deng et al., "Factorized Variational Autoencoders for Modeling Audience Reactions to Movies," 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Honolulu, HI, 2017, pp. 6014-6023. doi: 10.1109/CVPR.2017.637. URL: http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=8100120&isnumber=8099483
Usage Policy:No commercial reproduction, distribution, display or performance rights in this work are provided.
ID Code:79271
Collection:CaltechAUTHORS
Deposited By: Tony Diaz
Deposited On:21 Jul 2017 21:57
Last Modified:11 Jan 2018 18:45

Repository Staff Only: item control page