Dyadic Conversation Engagement Dataset

该数据集包含了34名参与者在进行日常双人对话时的数据，记录了他们的言语和非言语线索，同时还包括了参与者自我报告的参与度评分。数据集还包含了通过智能眼镜录制的参与者视野、头部动作和注视点数据，以及使用外部麦克风录制的音频。该数据集的规模涉及34名参与者，形成了19个独特的对话对。该数据集的任务是预测双边互动中的参与度。

This dataset comprises data collected from 34 participants during their daily two-person conversational interactions, capturing both their verbal and nonverbal cues, alongside self-reported engagement ratings provided by the participants. It also includes data on participants’ visual field, head movements and gaze points recorded via smart glasses, as well as audio recordings acquired using external microphones. The dataset involves 34 participants, forming 19 unique conversational dyads. The core task of this dataset is to predict engagement in bilateral interactions.