Zero-Shot Anticipation for Instructional Activities
This work addresses the challenge of zero-shot anticipation in robotics, which is incremental as it builds on existing methods for knowledge transfer.
The authors tackled the problem of enabling robots to predict future actions in unseen instructional activities by developing a hierarchical model that transfers knowledge from text to visual data, achieving coherent multi-step natural language predictions.
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.