Temporal Feature Alignment in Contrastive Self-Supervised Learning for Human Activity Recognition

TL;DR

This paper introduces a novel temporal feature alignment method within contrastive self-supervised learning for human activity recognition, leveraging dynamic time warping to improve feature robustness in unlabeled data scenarios.

Contribution

It proposes integrating dynamic time warping into a contrastive SSL framework to enhance temporal feature alignment for human activity recognition.

Findings

Outperforms recent SSL baselines in feature robustness

Surpasses supervised models in semi-supervised learning

Effective in both unimodal and multimodal settings

Abstract

Automated Human Activity Recognition has long been a problem of great interest in human-centered and ubiquitous computing. In the last years, a plethora of supervised learning algorithms based on deep neural networks has been suggested to address this problem using various modalities. While every modality has its own limitations, there is one common challenge. Namely, supervised learning requires vast amounts of annotated data which is practically hard to collect. In this paper, we benefit from the self-supervised learning paradigm (SSL) that is typically used to learn deep feature representations from unlabeled data. Moreover, we upgrade a contrastive SSL framework, namely SimCLR, widely used in various applications by introducing a temporal feature alignment procedure for Human Activity Recognition. Specifically, we propose integrating a dynamic time warping (DTW) algorithm in a latent space to force features to be aligned in a temporal dimension. Extensive experiments have been conducted for the unimodal scenario with inertial modality as well as in multimodal settings using inertial and skeleton data. According to the obtained results, the proposed approach has a great potential in learning robust feature representations compared to the recent SSL baselines, and clearly outperforms supervised models in semi-supervised learning. The code for the unimodal case is available via the following link: https://github.com/bulatkh/csshar_tfa.