Exploring Missing Modality in Multimodal Egocentric Datasets

arXiv:2401.11470v2 Announce Type: replace
Abstract: Multimodal video understanding is crucial for analyzing egocentric videos, where integrating multiple sensory signals significantly enhances action recognition and moment localization. However, practical applications often grapple with incomplete modalities due to factors like privacy concerns, efficiency demands, or hardware malfunctions. Addressing this, our study delves into the impact of missing modalities on egocentric action recognition, particularly within transformer-based models. We introduce a novel concept -Missing Modality Token (MMT)-to maintain performance even when modalities are absent, …

abstract action recognition applications arxiv concerns cs.cv datasets efficiency hardware however impact localization moment multimodal multiple practical privacy recognition sensory study type understanding video videos video understanding