On the Benefit of Generative Foundation Models for Human Activity Recognition
This addresses data scarcity for researchers and practitioners in human activity recognition, but it is incremental as it builds on existing generative AI advancements without presenting new results.
The paper tackles the problem of limited annotated data in human activity recognition by proposing the use of generative AI, such as LLMs and motion synthesis models, to autonomously generate virtual IMU data from text descriptions, and it highlights several research pathways like generating benchmark datasets and developing HAR-specific foundational models.
In human activity recognition (HAR), the limited availability of annotated data presents a significant challenge. Drawing inspiration from the latest advancements in generative AI, including Large Language Models (LLMs) and motion synthesis models, we believe that generative AI can address this data scarcity by autonomously generating virtual IMU data from text descriptions. Beyond this, we spotlight several promising research pathways that could benefit from generative AI for the community, including the generating benchmark datasets, the development of foundational models specific to HAR, the exploration of hierarchical structures within HAR, breaking down complex activities, and applications in health sensing and activity summarization.