Neural swipe decoder trained with geometric augmentations on 1M+ swipes generalizes to unseen keyboard layouts by predicting per-point character locations and mapping via inference-time layout.
Leiva, Sunjun Kim, Wenzhe Cui, Xiaojun Bi, and Antti Oulasvirta
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
fields
cs.HC 3years
2026 3verdicts
UNVERDICTED 3representative citing papers
WSTypist is a new RL-based simulation model that reproduces human-like word suggestion strategies, individual differences, and adaptation to design changes in mobile text entry.
A user study maps intuitive starting/ending regions and shapes for non-axial and angular off-device swipes to support earable interaction.
citing papers explorer
-
FUTO Swipe: Layout-Agnostic Neural Swipe Decoding
Neural swipe decoder trained with geometric augmentations on 1M+ swipes generalizes to unseen keyboard layouts by predicting per-point character locations and mapping via inference-time layout.
-
Simulating Word Suggestion Usage in Mobile Typing to Guide Intelligent Text Entry Design
WSTypist is a new RL-based simulation model that reproduces human-like word suggestion strategies, individual differences, and adaptation to design changes in mobile text entry.
-
Exploring Above-neck Unimanual Swipe Gestures for Off-Device Earable Interaction
A user study maps intuitive starting/ending regions and shapes for non-axial and angular off-device swipes to support earable interaction.