@inproceedings{4712e64f727d43ffa3dfc7f2fcf14241,
title = "Temporal invariant factor disentangled model for representation learning",
abstract = "This paper focuses on disentangling different kinds of underlying explanatory factors from image sequences. From the temporal perspective, we divide the explanatory factors into the temporal-invariant factor and the temporal-variant factor. The temporal-invariant factor corresponds to the categorical concept of objects in an image sequence while the temporal-variant factor describes the object appearance changing. We propose a disentangled model to disentangle from an image sequence the temporal-invariant factor that is used as an object representation insensitive to appearance changes. Our model is built upon the variational auto-encoder (VAE) and the recurrent neural network (RNN) to independently approximate the posterior distributions of the factor in an unsupervised manner. Experimental results on the HeadPose image database show the effectiveness of the proposed method.",
keywords = "Disentangled model, Representation learning, Temporal invariant factor, Unsupervised learning",
author = "Weichao Shen and Yuwei Wu and Yunde Jia",
note = "Publisher Copyright: {\textcopyright} Springer Nature Switzerland AG 2019.; 2nd Chinese Conference on Pattern Recognition and Computer Vision, PRCV 2019 ; Conference date: 08-11-2019 Through 11-11-2019",
year = "2019",
doi = "10.1007/978-3-030-31723-2\_33",
language = "English",
isbn = "9783030317225",
series = "Lecture Notes in Computer Science (including subseries Lecture Notes in Artificial Intelligence and Lecture Notes in Bioinformatics)",
publisher = "Springer",
pages = "391--402",
editor = "Zhouchen Lin and Liang Wang and Tieniu Tan and Jian Yang and Guangming Shi and Nanning Zheng and Xilin Chen and Yanning Zhang",
booktitle = "Pattern Recognition and Computer Vision 2nd Chinese Conference, PRCV 2019, Proceedings, Part II",
address = "Germany",
}