Learning to recognize touch gestures: recurrent vs. convolutional features and dynamic sampling
This work addresses the problem of touch gesture recognition for multi-user contexts on big devices, offering a novel approach with strong specific gains.
The authors tackled the problem of recognizing touch gestures on big devices by proposing a fully automatic method that learns general models adaptable to different gestures, user styles, and hardware variations, achieving close to perfect performance on a standard dataset and outperforming the state of the art.
We propose a fully automatic method for learning gestures on big touch devices in a potentially multi-user context. The goal is to learn general models capable of adapting to different gestures, user styles and hardware variations (e.g. device sizes, sampling frequencies and regularities). Based on deep neural networks, our method features a novel dynamic sampling and temporal normalization component, transforming variable length gestures into fixed length representations while preserving finger/surface contact transitions, that is, the topology of the signal. This sequential representation is then processed with a convolutional model capable, unlike recurrent networks, of learning hierarchical representations with different levels of abstraction. To demonstrate the interest of the proposed method, we introduce a new touch gestures dataset with 6591 gestures performed by 27 people, which is, up to our knowledge, the first of its kind: a publicly available multi-touch gesture dataset for interaction. We also tested our method on a standard dataset of symbolic touch gesture recognition, the MMG dataset, outperforming the state of the art and reporting close to perfect performance.