EGO-TOPO: Environment Affordances from Egocentric Video - Facebook Research

First-person video naturally brings the use of a physical environment to the forefront, since it shows the camera wearer interacting fluidly in a space based on his intentions. However, current methods largely separate the observed actions from the persistent space itself. We introduce a model for environment affordances that is learned directly from egocentric video.

Abstract · Copy Link · Share in Twitter · Share in Facebook ...

Lee mas