Comparison of Data Encodings and Machine Learning Architectures for User Identification on Arbitrary Motion Sequences
This repository contains data and code from the paper "Comparison of Data Encodings and Machine Learning Architectures for User Identification on Arbitrary Motion Sequences" published on the IEEE AIVR 2022 by Christian Rack, Andreas Hotho and Marc Erich Latoschik.
If you have any questions, feel free to open an issue or to contact Christian Rack.
data_preparation
contains the code required to prepare the data from the "Talking with Hands" dataset; the result is a HDF5 file, which we have also added tocode/data/talking_with_hands_data.hdf5
code
contains the code we used to train the machine learning models
We used the code published in this repository as basis for subsequent publications. As soon as these are accepted and published, we will either update this repository, or link to a new one.
@inproceedings{rack2022comparison,
author = {Rack, Christian and Hotho, Andreas and Latoschik, Marc Erich},
booktitle = {Proceedings of the IEEE International conference on artificial intelligence & Virtual Reality (IEEE AIVR)},
publisher = {IEEE},
title = {Comparison of Data Representations and Machine Learning Architectures for User Identification on Arbitrary Motion Sequences},
year = 2022
}