Gesture2Text: A Generalizable Decoder for Word-Gesture Keyboards in XR Through Trajectory Coarse Discretization and Pre-training
IEEE Transactions on Visualization and Computer Graphics (TVCG), 30(11):7118–7128 (ISMAR 2024) · November 2024
Citation
Shen, J., Khaldi, K., Zhou, E., Surale, H.B. & Karlson, A. (2024). Gesture2Text: A Generalizable Decoder for Word-Gesture Keyboards in XR Through Trajectory Coarse Discretization and Pre-training. IEEE Transactions on Visualization and Computer Graphics, 30(11):7118–7128.
Junxiao Shen, Khadija Khaldi, Enmin Zhou, Hemant Bhaskar Surale, Amy Karlson
First pre-trained foundation model for word-gesture decoding in XR. Trajectory coarse discretization plus pre-training generalizes across keyboard layouts, improving accuracy by ~40% over prior methods.