Jointly Modeling Spatio-Temporal Features of Tactile Signals for Action Classification

TL;DR

This paper introduces STAT, a transformer-based model that effectively captures both spatial and temporal features of tactile signals for improved action classification in healthcare and robotics.

Contribution

The paper proposes a novel spatio-temporal embedding and a temporal pretraining task within a transformer framework to enhance tactile signal analysis.

Findings

Outperforms state-of-the-art methods on a public dataset

Effectively models spatio-temporal features of tactile signals

Improves action classification accuracy

Abstract

Tactile signals collected by wearable electronics are essential in modeling and understanding human behavior. One of the main applications of tactile signals is action classification, especially in healthcare and robotics. However, existing tactile classification methods fail to capture the spatial and temporal features of tactile signals simultaneously, which results in sub-optimal performances. In this paper, we design Spatio-Temporal Aware tactility Transformer (STAT) to utilize continuous tactile signals for action classification. We propose spatial and temporal embeddings along with a new temporal pretraining task in our model, which aims to enhance the transformer in modeling the spatio-temporal features of tactile signals. Specially, the designed temporal pretraining task is to differentiate the time order of tubelet inputs to model the temporal properties explicitly. Experimental results on a public action classification dataset demonstrate that our model outperforms state-of-the-art methods in all metrics.