EgoAdapt: Enhancing Robustness in Egocentric Interactive Speaker Detection Under Missing Modalities

ArXi:2603.18082v1 Announce Type: cross TTM (Talking to Me) task is a pivotal component in understanding human social interactions, aiming to determine who is engaged in conversation with the camera-wearer. Traditional models often face challenges in real-world scenarios due to missing visual data, neglecting the role of head orientation, and background noise. This study addresses these limitations by