Mouse2Vec: Learning Reusable Semantic Representations of Mouse Behaviour

要旨

The mouse is a pervasive input device used for a wide range of interactive applications. However, computational modelling of mouse behaviour typically requires time-consuming design and extraction of handcrafted features, or approaches that are application-specific. We instead propose Mouse2Vec – a novel self-supervised method designed to learn semantic representations of mouse behaviour that are reusable across users and applications. Mouse2Vec uses a Transformer-based encoder-decoder architecture, which is specifically geared for mouse data: During pretraining, the encoder learns an embedding of input mouse trajectories while the decoder reconstructs the input and simultaneously detects mouse click events. We show that the representations learned by our method can identify interpretable mouse behaviour clusters and retrieve similar mouse trajectories. We also demonstrate on three sample downstream tasks that the representations can be practically used to augment mouse data for training supervised methods and serve as an effective feature extractor.

著者
Guanhua Zhang
University of Stuttgart, Stuttgart, Germany
Zhiming Hu
University of Stuttgart, Stuttgart, Germany
Mihai Bâce
KU Leuven, Leuven, Belgium
Andreas Bulling
University of Stuttgart, Stuttgart, Germany
論文URL

https://doi.org/10.1145/3613904.3642141

動画

会議: CHI 2024

The ACM CHI Conference on Human Factors in Computing Systems (https://chi2024.acm.org/)

セッション: Input, Interaction and Time

317
4 件の発表
2024-05-16 18:00:00
2024-05-16 19:20:00