@inproceedings{416553eeeb804288bea2db771da56cad,
title = "LSTMVAEF: Vivid Layout via LSTM-Based Variational Autoencoder Framework",
abstract = "The lack of training data is still a challenge in the Document Layout Analysis task (DLA). Synthetic data is an effective way to tackle this challenge. In this paper, we propose an LSTM-based Variational Autoencoder framework (LSTMVAF) to synthesize layouts for DLA. Compared with the previous method, our method can generate more complicated layouts and only need training data from DLA without extra annotation. We use LSTM models as basic models to learn the potential representing of class and position information of elements within a page. It is worth mentioning that we design a weight adaptation strategy to help model train faster. The experiment shows our model can generate more vivid layouts that only need a few real document pages.",
keywords = "Document Layout Analysis, Document generation, Variational Autoencoder",
author = "Jie He and Xingjiao Wu and Wenxin Hu and Jing Yang",
note = "Publisher Copyright: {\textcopyright} 2021, Springer Nature Switzerland AG.; 16th International Conference on Document Analysis and Recognition, ICDAR 2021 ; Conference date: 05-09-2021 Through 10-09-2021",
year = "2021",
doi = "10.1007/978-3-030-86331-9\_12",
language = "英语",
isbn = "9783030863302",
series = "Lecture Notes in Computer Science (including subseries Lecture Notes in Artificial Intelligence and Lecture Notes in Bioinformatics)",
publisher = "Springer Science and Business Media Deutschland GmbH",
pages = "176--189",
editor = "Josep Llad{\'o}s and Daniel Lopresti and Seiichi Uchida",
booktitle = "Document Analysis and Recognition – ICDAR 2021 - 16th International Conference, Proceedings",
address = "德国",
}