Variational Bayesian Sequence-to-Sequence Networks for Memory-Efficient Sign Language Translation
Abstract
Memory-efficient continuous Sign Language Translation is a significant challenge for the development of assisted technologies with real-time applicability for the deaf. In this work, we introduce a paradigm of designing recurrent deep networks whereby the output of the recurrent layer is derived from appropriate arguments from nonparametric statistics. A novel variational Bayesian sequence-to-sequence network architecture is proposed that consists of a) a full Gaussian posterior distribution for data-driven memory compression and b) a nonparametric Indian Buffet Process prior for regularization applied on the Gated Recurrent Unit non-gate weights. We dub our approach Stick-Breaking Recurrent network and show that it can achieve a substantial weight compression without diminishing modeling performance.
Cite
@article{arxiv.2102.06143,
title = {Variational Bayesian Sequence-to-Sequence Networks for Memory-Efficient Sign Language Translation},
author = {Harris Partaourides and Andreas Voskou and Dimitrios Kosmopoulos and Sotirios Chatzis and Dimitris N. Metaxas},
journal= {arXiv preprint arXiv:2102.06143},
year = {2021}
}