English

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

Computer Vision and Pattern Recognition 2023-09-13 v1 Artificial Intelligence

Abstract

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%.

Keywords

Cite

@article{arxiv.2309.05943,
  title  = {Knowledge-Guided Short-Context Action Anticipation in Human-Centric Videos},
  author = {Sarthak Bhagat and Simon Stepputtis and Joseph Campbell and Katia Sycara},
  journal= {arXiv preprint arXiv:2309.05943},
  year   = {2023}
}

Comments

ICCV 2023 Workshop on AI for Creative Video Editing and Understanding