@inproceedings{ullerich2022thumbpitch,
	title = {ThumbPitch: Enriching Thumb Interaction on Mobile Touchscreens using Deep Learning},
	author = {Jamie Ullerich and Maximiliane Windl and Andreas Bulling and Sven Mayer},
	year = {2022},
	booktitle = {Proceedings of the 34th Australian Conference on Human-Computer Interaction Proceedings},
	publisher = {Association for Computing Machinery},
	address = {Canberra, NSW, Australia},
	series = {OzCHI'22},
	doi = {10.1145/3572921.3572925},
	url = {https://sven-mayer.com/wp-content/uploads/2022/08/ullerich2022thumbpitch.pdf},
	date = {2022-11-29},
	abstract = {Today touchscreens are one of the most common input devices for everyday ubiquitous interaction. Yet, capacitive touchscreens are limited in expressiveness; thus, a large body of work has focused on extending the input capabilities of touchscreens. One promising approach is to use index finger orientation; however, this requires a two-handed interaction and poses ergonomic constraints. We propose using the thumb's pitch as an additional input dimension to counteract these limitations, enabling one-handed interaction scenarios. Our deep convolutional neural network detecting the thumb's pitch is trained on more than 230,000 ground truth images recorded using a motion tracking system. We highlight the potential of ThumbPitch by proposing several use cases that exploit the higher expressiveness, especially for one-handed scenarios. We tested three use cases in a validation study and validated our model. Our model achieved a mean error of only 11.9°.},
	keywords = {capacitive sensing, deep learning, input methods, interaction technique, mobile device, mobile interaction, neural networks, touchscreen}
}