Learning Goals From Failure

CVPR  ·  2021  ·  Impact 3

Dave Epstein; Carl Vondrick;

HIGHLIGHT

We introduce a framework that predicts the goals behind observable human action in video.

RELATED

Papers      Patents     Grants     Venues     Experts    Cite    Share    Save

ABSTRACT

We introduce a framework that predicts the goals behind observable human action in video. Motivated by evidence in developmental psychology, we leverage video of unintentional action to learn video representations of goals without direct supervision. Our approach models videos as contextual trajectories that represent both low-level motion and high-level action features. Experiments and visualizations show our trained model is able to predict the underlying goals in video of unintentional action. We also propose a method to "automatically correct" unintentional action by leveraging gradient signals of our model to adjust latent trajectories. Although the model is trained with minimal supervision, it is competitive with or outperforms baselines trained on large (supervised) datasets of successfully executed goals, showing that observing unintentional action is crucial to learning about goals in video.

 Paraphrase     Questionfy     Wikify     Simplify     Summarize

Download