Contrastive Predictive Coding for Human Activity Recognition

TL;DR

This paper introduces Contrastive Predictive Coding (CPC) for human activity recognition, leveraging unlabeled data to improve recognition accuracy with limited labeled data by capturing long-term temporal structures.

Contribution

It presents a novel CPC framework tailored for HAR, effectively utilizing unlabeled data and temporal information to enhance feature representations.

Findings

CPC improves HAR accuracy with limited labeled data.

Self-supervised pre-training enhances recognition performance.

Effective long-term temporal feature extraction for real-life scenarios.

Abstract

Feature extraction is crucial for human activity recognition (HAR) using body-worn movement sensors. Recently, learned representations have been used successfully, offering promising alternatives to manually engineered features. Our work focuses on effective use of small amounts of labeled data and the opportunistic exploitation of unlabeled data that are straightforward to collect in mobile and ubiquitous computing scenarios. We hypothesize and demonstrate that explicitly considering the temporality of sensor data at representation level plays an important role for effective HAR in challenging scenarios. We introduce the Contrastive Predictive Coding (CPC) framework to human activity recognition, which captures the long-term temporal structure of sensor data streams. Through a range of experimental evaluations on real-life recognition tasks, we demonstrate its effectiveness for improved HAR. CPC-based pre-training is self-supervised, and the resulting learned representations can be integrated into standard activity chains. It leads to significantly improved recognition performance when only small amounts of labeled training data are available, thereby demonstrating the practical value of our approach.