Learning the Predictability of the Future
| Autor: | Dídac Surís, Ruoshi Liu, Carl Vondrick |
|---|---|
| Jazyk: | angličtina |
| Rok vydání: | 2021 |
| Předmět: |
Structure (mathematical logic)
FOS: Computer and information sciences Hierarchy Computer Science - Machine Learning Computer science business.industry Hyperbolic geometry Hyperbolic space Computer Vision and Pattern Recognition (cs.CV) Image and Video Processing (eess.IV) Computer Science - Computer Vision and Pattern Recognition Electrical Engineering and Systems Science - Image and Video Processing Machine Learning (cs.LG) Pattern recognition (psychology) FOS: Electrical engineering electronic engineering information engineering Artificial intelligence Predictability Representation (mathematics) business Abstraction (linguistics) |
| Zdroj: | CVPR |
| Popis: | We introduce a framework for learning from unlabeled video what is predictable in the future. Instead of committing up front to features to predict, our approach learns from data which features are predictable. Based on the observation that hyperbolic geometry naturally and compactly encodes hierarchical structure, we propose a predictive model in hyperbolic space. When the model is most confident, it will predict at a concrete level of the hierarchy, but when the model is not confident, it learns to automatically select a higher level of abstraction. Experiments on two established datasets show the key role of hierarchical representations for action prediction. Although our representation is trained with unlabeled video, visualizations show that action hierarchies emerge in the representation. Website: https://hyperfuture.cs.columbia.edu |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|