A Survey of IMU Based Cross-Modal Transfer Learning in Human Activity Recognition

TL;DR

This survey reviews how transfer learning techniques enable the use of IMU sensor data across different modalities to improve human activity recognition, highlighting current methods, datasets, and future directions.

Contribution

It categorizes and compares existing IMU-based cross-modal transfer learning approaches for HAR, clarifies related concepts, and discusses future research opportunities.

Findings

Identifies two main approaches: instance-based and feature-based transfer.

Provides a comprehensive comparison of multimodal HAR datasets.

Highlights the importance of cross-modal transfer for improved HAR performance.

Abstract

Despite living in a multi-sensory world, most AI models are limited to textual and visual understanding of human motion and behavior. In fact, full situational awareness of human motion could best be understood through a combination of sensors. In this survey we investigate how knowledge can be transferred and utilized amongst modalities for Human Activity/Action Recognition (HAR), i.e. cross-modality transfer learning. We motivate the importance and potential of IMU data and its applicability in cross-modality learning as well as the importance of studying the HAR problem. We categorize HAR related tasks by time and abstractness and then compare various types of multimodal HAR datasets. We also distinguish and expound on many related but inconsistently used terms in the literature, such as transfer learning, domain adaptation, representation learning, sensor fusion, and multimodal learning, and describe how cross-modal learning fits with all these concepts. We then review the literature in IMU-based cross-modal transfer for HAR. The two main approaches for cross-modal transfer are instance-based transfer, where instances of one modality are mapped to another (e.g. knowledge is transferred in the input space), or feature-based transfer, where the model relates the modalities in an intermediate latent space (e.g. knowledge is transferred in the feature space). Finally, we discuss future research directions and applications in cross-modal HAR.