GENEA Challenge 2023 Human-Likeness subjective evaluation data

This repository contains human-likeness user-study response data and associated analyses from the GENEA Challenge 2023. The code was written by Gustav Eje Henter and is released under a Creative Commons Attribution 4.0 International (CC BY 4.0) license.

The archive contains:
* This README.txt file.
* A LICENSE.txt file.
* A JSON file containing all human-likeness user-study responses included in the analyses.
* MATLAB .m files for reproducing the above analyses (both tables and figures).
* A folder called "output" that contains all files written by the analysis script, including .mat files with all the results computed by each analysis, as well as files created when compiling the final, pretty-looking pdf figures.
* A file output.txt that contains all output written to the MATLAB Command Window when running the analyses.

Requirements:
* MATLAB and MATLAB Image Processing Toolbox
* distinguishable_colors.m by Timothy E. Holy (https://www.mathworks.com/matlabcentral/fileexchange/29702-generate-maximally-perceptually-distinct-colors)
* fragmaster by Augustin Martin Domingo and Tilman Vogel (https://ctan.org/pkg/fragmaster), a LaTeX utility
This was last tested on 2023-10-08 on MATLAB version 9.10.0.1739362 (R2021a) Update 5, running on macOS version 13.2 build 22D49.

To re-generate/reproduce the contents in the "output" folder:
0. Ensure that all requirements are met.
1. Run through the entire analysis script "run_analyses.m".
2. Run the fragmaster command in the "output" folder.

Attribution:
If you use this material in a scientific publication, please cite our latest paper on the GENEA Challenge 2023. At the time of writing (2023-10-08) this is our ACM ICMI 2023 paper. You can use the following BibTeX code to cite that work:
@inproceedings{kucherenko2023genea,
  author={Kucherenko, Taras and Nagy, Rajmund and Yoon, Youngwoo and Woo, Jieyeon and Nikolov, Teodor and Tsakov, Mihail and Henter, Gustav Eje},
  title={The {GENEA} {C}hallenge 2023: {A} large-scale evaluation of gesture generation models in monadic and dyadic settings},
  booktitle = {Proceedings of the ACM International Conference on Multimodal Interaction},
  publisher = {ACM},
  series = {ICMI '23},
  year={2023}
}

To find more GENEA Challenge 2023 material on the web, please see:
* https://svito-zar.github.io/GENEAchallenge2023/
* https://genea-workshop.github.io/2023/challenge/

If you have any questions or comments, please contact:
* Gustav Eje Henter
* The GENEA Challenge organisers