In this paper, we address the challenge of understanding human activities from an egocentric perspective. Traditional activity recognition techniques face unique challenges in egocentric videos due to the highly dynamic nature of the head during many activities. We propose a framework that seeks to address these challenges in a way that is independent of network architecture by restricting the ego-video input to a stabilized, hand-focused video. We demonstrate that this straightforward video transformation alone outperforms existing egocentric video baselines on the Ego-Exo4D Fine-Grained Keystep Recognition benchmark without requiring any alteration of the underlying model infrastructure.
Chavis et al. (2025) studied this question.