Leland Stanford Junior University

Toyota Research Institute, Inc.

Haoye Cai

Adrien David Gaidon

Kuan-Hui Lee

Juan Carlos Niebles Duque

Ehsan Adeli-Mosabbeb

De-An Huang

Boxiao Pan

A method for scene perception using video captioning based on a spatio-temporal graph model is described. The method includes decomposing the spatio-temporal graph model of a scene in input video into a spatial graph and a temporal graph. The method also includes modeling a two branch framework having an object branch and a scene branch according to the spatial graph and the temporal graph to learn object interactions between the object branch and the scene branch. The method further includes transferring the learned object interactions from the object branch to the scene branch as privileged information. The method also includes captioning the scene by aligning language logits from the object branch and the scene branch according to the learned object interactions.

Spatio-temporal graph for video captioning with knowledge distillation

Growing community of inventors

Palo Alto, CA, United States of America

Haoye Cai