M3PT: 人物認識ブロックワイズ注意機構を備えたマルチモーダル多人数ソーシャルシグナル予測トランスフォーマ
M3PT: A Transformer for Multimodal, Multi-Party Social Signal Prediction with Person-aware Blockwise Attention
多人数会話における身体姿勢・頭部姿勢・発話・食事行動などのマルチモーダルなソーシャルシグナルを、モダリティと時間のブロックワイズ注意マスクを持つ因果トランスフォーマで同時に予測する単一モデルM3PTを提案した。
著者: Yiming Tang, Abrar Anwar, Jesse Thomason
分類: cs.LG, cs.AI, cs.RO
原文アブストラクト
Understanding social signals in multi-party conversations is important for human-robot interaction and artificial social intelligence. Social signals include body pose, head pose, speech, and context-specific activities like acquiring and taking bites of food when dining. Past work in multi-party interaction tends to build task-specific models for predicting social signals. In this work, we address the challenge of predicting multimodal social signals in multi-party settings in a single model. We introduce M3PT, a causal transformer architecture with modality and temporal blockwise attention masking to simultaneously process multiple social cues across multiple participants and their temporal interactions. We train and evaluate M3PT on the Human-Human Commensality Dataset (HHCD), and demonstrate that using multiple modalities improves bite timing and speaking status prediction. Source code: https://github.com/AbrarAnwar/masked-social-signals/.
