papers AI Learner
The Github is limit! Click to go to the new site.

Zero-Shot Anticipation for Instructional Activities

2019-05-13
Fadime Sener, Angela Yao

Abstract

How can we teach a robot to predict what will happen next for an activity it has never seen before? We address this problem of zero-shot anticipation by presenting a hierarchical model that generalizes instructional knowledge from large-scale text-corpora and transfers the knowledge to the visual domain. Given a portion of an instructional video, our model predicts coherent and plausible actions multiple steps into the future, all in rich natural language. To demonstrate the anticipation capabilities of our model, we introduce the Tasty Videos dataset, a collection of 2511 recipes for zero-shot learning, recognition and anticipation.

Abstract (translated by Google)
URL

http://arxiv.org/abs/1812.02501

PDF

http://arxiv.org/pdf/1812.02501


Similar Posts

Comments