Emotion-Conditioned Short-Horizon Human Pose Forecasting with a Lightweight Predictive World Model

ArXi:2604.23532v1 Announce Type: new Short-term human pose prediction plays a crucial role in interactive systems, assistive robots, and emotion-aware human-computer interaction[1-3]. While current trajectory prediction models primarily rely on geometric motion cues, they often overlook the underlying emotional signals influencing human motion dynamics[4-5]. This paper investigates whether facial expression-derived emotion embeddings can provide auxiliary conditional signals for short-term pose prediction.