Paper ID: 2309.05943

Knowledge-Guided Short-Context Action Anticipation in Human-Centric Videos

Sarthak Bhagat, Simon Stepputtis, Joseph Campbell, Katia Sycara

This work focuses on anticipating long-term human actions, particularly using short video segments, which can speed up editing workflows through improved suggestions while fostering creativity by suggesting narratives. To this end, we imbue a transformer network with a symbolic knowledge graph for action anticipation in video segments by boosting certain aspects of the transformer's attention mechanism at run-time. Demonstrated on two benchmark datasets, Breakfast and 50Salads, our approach outperforms current state-of-the-art methods for long-term action anticipation using short video context by up to 9%.

Submitted: Sep 12, 2023