132 citations · 182 across the 25 of their papers we have counts for
Showing cs.MMShow all
2 papers · 1 filter
cs.MM2026
EgoAdapt: Enhancing Robustness in Egocentric Interactive Speaker Detection Under Missing Modalities
Xinyuan Qian, Xinjia Zhu, Alessio Brutti +1
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 m…
cs.MM2022★ 6 cited
Predict-and-Update Network: Audio-Visual Speech Recognition Inspired by Human Speech Perception
Jiadong Wang, Xinyuan Qian, Haizhou Li
Audio and visual signals complement each other in human speech perception, so do they in speech recognition. The visual hint is less evident than the acoustic hint, but more robust…