Modelling the Distribution of Human Motion for Sign Language Assessment
Abstract
Sign Language Assessment (SLA) tools are useful to aid in language learning and are underdeveloped. Previous work has focused on isolated signs or comparison against a single reference video to assess Sign Languages (SL). This paper introduces a novel SLA tool designed to evaluate the comprehensibility of SL by modelling the natural distribution of human motion. We train our pipeline on data from native signers and evaluate it using SL learners. We compare our results to ratings from a human raters study and find strong correlation between human ratings and our tool. We visually demonstrate our tools ability to detect anomalous results spatio-temporally, providing actionable feedback to aid in SL learning and assessment.
Cite
Text
Cory et al. "Modelling the Distribution of Human Motion for Sign Language Assessment." European Conference on Computer Vision Workshops, 2024. doi:10.1007/978-3-031-92591-7_1Markdown
[Cory et al. "Modelling the Distribution of Human Motion for Sign Language Assessment." European Conference on Computer Vision Workshops, 2024.](https://mlanthology.org/eccvw/2024/cory2024eccvw-modelling/) doi:10.1007/978-3-031-92591-7_1BibTeX
@inproceedings{cory2024eccvw-modelling,
title = {{Modelling the Distribution of Human Motion for Sign Language Assessment}},
author = {Cory, Oliver and Sincan, Ozge Mercanoglu and Vowels, Matthew J. and Battisti, Alessia and Holzknecht, Franz and Tissi, Katja and Sidler-Miserez, Sandra and Haug, Tobias and Ebling, Sarah and Bowden, Richard},
booktitle = {European Conference on Computer Vision Workshops},
year = {2024},
pages = {1-19},
doi = {10.1007/978-3-031-92591-7_1},
url = {https://mlanthology.org/eccvw/2024/cory2024eccvw-modelling/}
}