Gaze-Guided Graph Neural Network for Action Anticipation Conditioned on Intention

arXiv:2404.07347v1 Announce Type: cross
Abstract: Humans utilize their gaze to concentrate on essential information while perceiving and interpreting intentions in videos. Incorporating human gaze into computational algorithms can significantly enhance model performance in video understanding tasks. In this work, we address a challenging and innovative task in video understanding: predicting the actions of an agent in a video based on a partial video. We introduce the Gaze-guided Action Anticipation algorithm, which establishes a visual-semantic graph from the video input. Our …

abstract algorithms arxiv computational cs.cv cs.hc cs.lg graph graph neural network human humans information network neural network performance tasks type understanding video videos video understanding work