一作ACL 2026Poster· Natural Language Processing
Open Your Model’s Eyes: Video and Context-Aware Multimodal Backchannel Prediction
Min-Jae Kim · Jun-Yeong Moon · Mujeen Sung · Gyeong-Moon Park
摘要
Backchannels, which signal listener states like empathy and understanding, are fundamental to natural human interaction. However, current approaches rely solely on audio and text. This omits crucial visual cues, such as facial expressions and gestures, as well as broader conversational contexts,...