Re-thinking Human Activity Recognition with Hierarchy-aware Label Relationship Modeling

arXiv:2403.05557v1 Announce Type: cross
Abstract: Human Activity Recognition (HAR) has been studied for decades, from data collection, learning models, to post-processing and result interpretations. However, the inherent hierarchy in the activities remains relatively under-explored, despite its significant impact on model performance and interpretation. In this paper, we propose H-HAR, by rethinking the HAR tasks from a fresh perspective by delving into their intricate global label relationships. Rather than building multiple classifiers separately for multi-layered activities, we explore the efficacy of …

abstract arxiv collection cs.hc cs.lg data data collection eess.sp however human impact interpretation modeling paper performance post-processing processing recognition relationship thinking type